MyArxiv
Computer Vision and Pattern Recognition 151
Whole-Body Conditioned Egocentric Video Prediction
We train models to Predict Ego-centric Video from human Actions (PEVA), given the past video and an action represented by the relative 3D body pose. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, our model learns to simulate how physical human actions shape the environment from a first-person point of view. We train an auto-regressive conditional diffusion transformer on Nymeria, a large-scale dataset of real-world egocentric video and body pose capture. We further design a hierarchical evaluation protocol with increasingly challenging tasks, enabling a comprehensive analysis of the model's embodied prediction and control abilities. Our work represents an initial attempt to tackle the challenges of modeling complex real-world environments and embodied agent behaviors with video prediction from the perspective of a human.
comment: Project Page: https://dannytran123.github.io/PEVA
☆ SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark
We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS), where the task is to produce a voxel-based Anomaly Volume. Moreover, SiM3D focuses on a scenario of high interest in manufacturing: single-instance anomaly detection, where only one object, either real or synthetic, is available for training. In this respect, SiM3D stands out as the first ADS benchmark that addresses the challenge of generalising from synthetic training data to real test data. SiM3D includes a novel multimodal multiview dataset acquired using top-tier industrial sensors and robots. The dataset features multiview high-resolution images (12 Mpx) and point clouds (7M points) for 333 instances of eight types of objects, alongside a CAD model for each type. We also provide manually annotated 3D segmentation GTs for anomalous test samples. To establish reference baselines for the proposed multiview 3D ADS task, we adapt prominent singleview methods and assess their performance using novel metrics that operate on Anomaly Volumes.
☆ SAM4D: Segment Anything in Camera and LiDAR Streams ICCV2025
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space, enabling seamless cross-modal prompting and interaction. Additionally, we propose Motion-aware Cross-modal Memory Attention (MCMA), which leverages ego-motion compensation to enhance temporal consistency and long-horizon feature retrieval, ensuring robust segmentation across dynamically changing autonomous driving scenes. To avoid annotation bottlenecks, we develop a multi-modal automated data engine that synergizes VFM-driven video masklets, spatiotemporal 4D reconstruction, and cross-modal masklet fusion. This framework generates camera-LiDAR aligned pseudo-labels at a speed orders of magnitude faster than human annotation while preserving VFM-derived semantic fidelity in point cloud representations. We conduct extensive experiments on the constructed Waymo-4DSeg, which demonstrate the powerful cross-modal segmentation ability and great potential in data annotation of proposed SAM4D.
comment: Accepted by ICCV2025, Project Page: https://SAM4D-Project.github.io
☆ HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation
Recent progress in vision-language segmentation has significantly advanced grounded visual understanding. However, these models often exhibit hallucinations by producing segmentation masks for objects not grounded in the image content or by incorrectly labeling irrelevant regions. Existing evaluation protocols for segmentation hallucination primarily focus on label or textual hallucinations without manipulating the visual context, limiting their capacity to diagnose critical failures. In response, we introduce HalluSegBench, the first benchmark specifically designed to evaluate hallucinations in visual grounding through the lens of counterfactual visual reasoning. Our benchmark consists of a novel dataset of 1340 counterfactual instance pairs spanning 281 unique object classes, and a set of newly introduced metrics that quantify hallucination sensitivity under visually coherent scene edits. Experiments on HalluSegBench with state-of-the-art vision-language segmentation models reveal that vision-driven hallucinations are significantly more prevalent than label-driven ones, with models often persisting in false segmentation, highlighting the need for counterfactual reasoning to diagnose grounding fidelity.
comment: Project webpage: https://plan-lab.github.io/hallusegbench/
☆ DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion
Reconstructing 3D objects from a single image is a long-standing challenge, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they generally assume fully visible inputs and fail when parts of the object are occluded. This leads to inconsistent views and degraded 3D reconstruction quality. To overcome this limitation, we propose an end-to-end framework for occlusion-aware multi-view generation. Our method directly synthesizes six structurally consistent novel views from a single partially occluded image, enabling downstream 3D reconstruction without requiring prior inpainting or manual annotations. We construct a self-supervised training pipeline using the Pix2Gestalt dataset, leveraging occluded-unoccluded image pairs and pseudo-ground-truth views to teach the model structure-aware completion and view consistency. Without modifying the original architecture, we fully fine-tune the view synthesis model to jointly learn completion and multi-view generation. Additionally, we introduce the first benchmark for occlusion-aware reconstruction, encompassing diverse occlusion levels, object categories, and mask patterns. This benchmark provides a standardized protocol for evaluating future methods under partial occlusions. Our code is available at https://github.com/Quyans/DeOcc123.
☆ StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning ICCV 2025
Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods still face two key issues that limit the potential of SSM: Destroying the adjacency of 3D points during SSM processing and failing to retain long-sequence memory as the input length increases in downstream tasks. To address these issues, we propose StruMamba3D, a novel paradigm for self-supervised point cloud representation learning. It enjoys several merits. First, we design spatial states and use them as proxies to preserve spatial dependencies among points. Second, we enhance the SSM with a state-wise update strategy and incorporate a lightweight convolution to facilitate interactions between spatial states for efficient structure modeling. Third, our method reduces the sensitivity of pre-trained Mamba-based models to varying input lengths by introducing a sequence length-adaptive strategy. Experimental results across four downstream tasks showcase the superior performance of our method. In addition, our method attains the SOTA 95.1% accuracy on ModelNet40 and 92.75% accuracy on the most challenging split of ScanObjectNN without voting strategy.
comment: Accepted by ICCV 2025
☆ Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval ACL 2025
Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities. Traditional methods learn a single-vector embedding to represent semantics of each sample, but struggle to capture nuanced and diverse relationships that can exist across modalities. Set-based approaches, which represent each sample with multiple embeddings, offer a promising alternative, as they can capture richer and more diverse relationships. In this paper, we show that, despite their promise, these set-based representations continue to face issues including sparse supervision and set collapse, which limits their effectiveness. To address these challenges, we propose Maximal Pair Assignment Similarity to optimize one-to-one matching between embedding sets which preserve semantic diversity within the set. We also introduce two loss functions to further enhance the representations: Global Discriminative Loss to enhance distinction among embeddings, and Intra-Set Divergence Loss to prevent collapse within each set. Our method achieves state-of-the-art performance on MS-COCO and Flickr30k without relying on external data.
comment: Accepted at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025 Main)
☆ ResQ: A Novel Framework to Implement Residual Neural Networks on Analog Rydberg Atom Quantum Computers ICCV
Research in quantum machine learning has recently proliferated due to the potential of quantum computing to accelerate machine learning. An area of machine learning that has not yet been explored is neural ordinary differential equation (neural ODE) based residual neural networks (ResNets), which aim to improve the effectiveness of neural networks using the principles of ordinary differential equations. In this work, we present our insights about why analog Rydberg atom quantum computers are especially well-suited for ResNets. We also introduce ResQ, a novel framework to optimize the dynamics of Rydberg atom quantum computers to solve classification problems in machine learning using analog quantum neural ODEs.
comment: ResQ will appear in the Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2025
☆ Exploring the Design Space of 3D MLLMs for CT Report Generation
Multimodal Large Language Models (MLLMs) have emerged as a promising way to automate Radiology Report Generation (RRG). In this work, we systematically investigate the design space of 3D MLLMs, including visual input representation, projectors, Large Language Models (LLMs), and fine-tuning techniques for 3D CT report generation. We also introduce two knowledge-based report augmentation methods that improve performance on the GREEN score by up to 10\%, achieving the 2nd place on the MICCAI 2024 AMOS-MM challenge. Our results on the 1,687 cases from the AMOS-MM dataset show that RRG is largely independent of the size of LLM under the same training protocol. We also show that larger volume size does not always improve performance if the original ViT was pre-trained on a smaller volume size. Lastly, we show that using a segmentation mask along with the CT volume improves performance. The code is publicly available at https://github.com/bowang-lab/AMOS-MM-Solution
☆ WAFT: Warping-Alone Field Transforms for Optical Flow
We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow. WAFT is similar to RAFT but replaces cost volume with high-resolution warping, achieving better accuracy with lower memory cost. This design challenges the conventional wisdom that constructing cost volumes is necessary for strong performance. WAFT is a simple and flexible meta-architecture with minimal inductive biases and reliance on custom designs. Compared with existing methods, WAFT ranks 1st on Spring and KITTI benchmarks, achieves the best zero-shot generalization on KITTI, while being up to 4.1x faster than methods with similar performance. Code and model weights are available at https://github.com/princeton-vl/WAFT.
☆ MADrive: Memory-Augmented Driving Scene Modeling
Recent advances in scene reconstruction have pushed toward highly realistic modeling of autonomous driving (AD) environments using 3D Gaussian splatting. However, the resulting reconstructions remain closely tied to the original observations and struggle to support photorealistic synthesis of significantly altered or novel driving scenarios. This work introduces MADrive, a memory-augmented reconstruction framework designed to extend the capabilities of existing scene reconstruction methods by replacing observed vehicles with visually similar 3D assets retrieved from a large-scale external memory bank. Specifically, we release MAD-Cars, a curated dataset of ${\sim}70$K 360{\deg} car videos captured in the wild and present a retrieval module that finds the most similar car instances in the memory bank, reconstructs the corresponding 3D assets from video, and integrates them into the target scene through orientation alignment and relighting. The resulting replacements provide complete multi-view representations of vehicles in the scene, enabling photorealistic synthesis of substantially altered configurations, as demonstrated in our experiments. Project page: https://yandex-research.github.io/madrive/
☆ G$^{2}$D: Boosting Multimodal Learning with Gradient-Guided Distillation ICCV 2025
Multimodal learning aims to leverage information from diverse data modalities to achieve more comprehensive performance. However, conventional multimodal models often suffer from modality imbalance, where one or a few modalities dominate model optimization, leading to suboptimal feature representation and underutilization of weak modalities. To address this challenge, we introduce Gradient-Guided Distillation (G$^{2}$D), a knowledge distillation framework that optimizes the multimodal model with a custom-built loss function that fuses both unimodal and multimodal objectives. G$^{2}$D further incorporates a dynamic sequential modality prioritization (SMP) technique in the learning process to ensure each modality leads the learning process, avoiding the pitfall of stronger modalities overshadowing weaker ones. We validate G$^{2}$D on multiple real-world datasets and show that G$^{2}$D amplifies the significance of weak modalities while training and outperforms state-of-the-art methods in classification and regression tasks. Our code is available at https://github.com/rAIson-Lab/G2D.
comment: Accepted at ICCV 2025
☆ GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation ICCV 2025
Creating high-quality, generalizable speech-driven 3D talking heads remains a persistent challenge. Previous methods achieve satisfactory results for fixed viewpoints and small-scale audio variations, but they struggle with large head rotations and out-of-distribution (OOD) audio. Moreover, they are constrained by the need for time-consuming, identity-specific training. We believe the core issue lies in the lack of sufficient 3D priors, which limits the extrapolation capabilities of synthesized talking heads. To address this, we propose GGTalker, which synthesizes talking heads through a combination of generalizable priors and identity-specific adaptation. We introduce a two-stage Prior-Adaptation training strategy to learn Gaussian head priors and adapt to individual characteristics. We train Audio-Expression and Expression-Visual priors to capture the universal patterns of lip movements and the general distribution of head textures. During the Customized Adaptation, individual speaking styles and texture details are precisely modeled. Additionally, we introduce a color MLP to generate fine-grained, motion-aligned textures and a Body Inpainter to blend rendered results with the background, producing indistinguishable, photorealistic video frames. Comprehensive experiments show that GGTalker achieves state-of-the-art performance in rendering quality, 3D consistency, lip-sync accuracy, and training efficiency.
comment: ICCV 2025, Project page: https://vincenthu19.github.io/GGTalker/
☆ Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration
Large Vision-Language Models (LVLMs) have demonstrated significant advancements in multimodal understanding, yet they are frequently hampered by hallucination-the generation of text that contradicts visual input. Existing training-free decoding strategies exhibit critical limitations, including the use of static constraints that do not adapt to semantic drift during generation, inefficiency stemming from the need for multiple forward passes, and degradation of detail due to overly rigid intervention rules. To overcome these challenges, this paper introduces Dynamic Logits Calibration (DLC), a novel training-free decoding framework designed to dynamically align text generation with visual evidence at inference time. At the decoding phase, DLC step-wise employs CLIP to assess the semantic alignment between the input image and the generated text sequence. Then, the Relative Visual Advantage (RVA) of candidate tokens is evaluated against a dynamically updated contextual baseline, adaptively adjusting output logits to favor tokens that are visually grounded. Furthermore, an adaptive weighting mechanism, informed by a real-time context alignment score, carefully balances the visual guidance while ensuring the overall quality of the textual output. Extensive experiments conducted across diverse benchmarks and various LVLM architectures (such as LLaVA, InstructBLIP, and MiniGPT-4) demonstrate that DLC significantly reduces hallucinations, outperforming current methods while maintaining high inference efficiency by avoiding multiple forward passes. Overall, we present an effective and efficient decoding-time solution to mitigate hallucinations, thereby enhancing the reliability of LVLMs for more practices. Code will be released on Github.
☆ Lightweight Physics-Informed Zero-Shot Ultrasound Plane Wave Denoising
Ultrasound Coherent Plane Wave Compounding (CPWC) enhances image contrast by combining echoes from multiple steered transmissions. While increasing the number of angles generally improves image quality, it drastically reduces the frame rate and can introduce blurring artifacts in fast-moving targets. Moreover, compounded images remain susceptible to noise, particularly when acquired with a limited number of transmissions. We propose a zero-shot denoising framework tailored for low-angle CPWC acquisitions, which enhances contrast without relying on a separate training dataset. The method divides the available transmission angles into two disjoint subsets, each used to form compound images that include higher noise levels. The new compounded images are then used to train a deep model via a self-supervised residual learning scheme, enabling it to suppress incoherent noise while preserving anatomical structures. Because angle-dependent artifacts vary between the subsets while the underlying tissue response is similar, this physics-informed pairing allows the network to learn to disentangle the inconsistent artifacts from the consistent tissue signal. Unlike supervised methods, our model requires no domain-specific fine-tuning or paired data, making it adaptable across anatomical regions and acquisition setups. The entire pipeline supports efficient training with low computational cost due to the use of a lightweight architecture, which comprises only two convolutional layers. Evaluations on simulation, phantom, and in vivo data demonstrate superior contrast enhancement and structure preservation compared to both classical and deep learning-based denoising methods.
☆ Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
Deep neural networks have set the state-of-the-art in computer vision tasks such as bounding box detection and semantic segmentation. Object detectors and segmentation models assign confidence scores to predictions, reflecting the model's uncertainty in object detection or pixel-wise classification. However, these confidence estimates are often miscalibrated, as their architectures and loss functions are tailored to task performance rather than probabilistic foundation. Even with well calibrated predictions, object detectors fail to quantify uncertainty outside detected bounding boxes, i.e., the model does not make a probability assessment of whether an area without detected objects is truly free of obstacles. This poses a safety risk in applications such as automated driving, where uncertainty in empty areas remains unexplored. In this work, we propose an object detection model grounded in spatial statistics. Bounding box data matches realizations of a marked point process, commonly used to describe the probabilistic occurrence of spatial point events identified as bounding box centers, where marks are used to describe the spatial extension of bounding boxes and classes. Our statistical framework enables a likelihood-based training and provides well-defined confidence estimates for whether a region is drivable, i.e., free of objects. We demonstrate the effectiveness of our method through calibration assessments and evaluation of performance.
comment: 15 pages, 4 figures, 3 tables
☆ TITAN: Query-Token based Domain Adaptive Adversarial Learning ICCV 2025
We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a self-supervised approach using a student-teacher (ST) framework where pseudo-labels are generated via a source-pretrained model for further fine-tuning. We observe that the performance of a student model often degrades drastically, due to the collapse of the teacher model, primarily caused by high noise in pseudo-labels, resulting from domain bias, discrepancies, and a significant domain shift across domains. To obtain reliable pseudo-labels, we propose a Target-based Iterative Query-Token Adversarial Network (TITAN), which separates the target images into two subsets: those similar to the source (easy) and those dissimilar (hard). We propose a strategy to estimate variance to partition the target domain. This approach leverages the insight that higher detection variances correspond to higher recall and greater similarity to the source domain. Also, we incorporate query-token-based adversarial modules into a student-teacher baseline framework to reduce the domain gaps between two feature representations. Experiments conducted on four natural imaging datasets and two challenging medical datasets have substantiated the superior performance of TITAN compared to existing state-of-the-art (SOTA) methodologies. We report an mAP improvement of +22.7, +22.2, +21.1, and +3.7 percent over the current SOTA on C2F, C2B, S2C, and K2C benchmarks, respectively.
comment: ICCV 2025
☆ Global and Local Entailment Learning for Natural World Imagery ICCV 2025
Learning the hierarchical structure of data in vision-language models is a significant challenge. Previous works have attempted to address this challenge by employing entailment learning. However, these approaches fail to model the transitive nature of entailment explicitly, which establishes the relationship between order and semantics within a representation space. In this work, we introduce Radial Cross-Modal Embeddings (RCME), a framework that enables the explicit modeling of transitivity-enforced entailment. Our proposed framework optimizes for the partial order of concepts within vision-language models. By leveraging our framework, we develop a hierarchical vision-language foundation model capable of representing the hierarchy in the Tree of Life. Our experiments on hierarchical species classification and hierarchical retrieval tasks demonstrate the enhanced performance of our models compared to the existing state-of-the-art models. Our code and models are open-sourced at https://vishu26.github.io/RCME/index.html.
comment: Accepted at ICCV 2025
☆ Logios : An open source Greek Polytonic Optical Character Recognition system
In this paper, we present an Optical Character Recognition (OCR) system specifically designed for the accurate recognition and digitization of Greek polytonic texts. By leveraging the combined strengths of convolutional layers for feature extraction and recurrent layers for sequence learning, our system addresses the unique challenges posed by Greek polytonic scripts. This approach aims to overcome the limitations of traditional OCR methods, offering significant improvements in accuracy and efficiency. We release the underlying model as an open-source library and make our OCR platform available for academic use.
☆ Evaluation of Traffic Signals for Daily Traffic Pattern
The turning movement count data is crucial for traffic signal design, intersection geometry planning, traffic flow, and congestion analysis. This work proposes three methods called dynamic, static, and hybrid configuration for TMC-based traffic signals. A vision-based tracking system is developed to estimate the TMC of six intersections in Las Vegas using traffic cameras. The intersection design, route (e.g. vehicle movement directions), and signal configuration files with compatible formats are synthesized and imported into Simulation of Urban MObility for signal evaluation with realistic data. The initial experimental results based on estimated waiting times indicate that the cycle time of 90 and 120 seconds works best for all intersections. In addition, four intersections show better performance for dynamic signal timing configuration, and the other two with lower performance have a lower ratio of total vehicle count to total lanes of the intersection leg. Since daily traffic flow often exhibits a bimodal pattern, we propose a hybrid signal method that switches between dynamic and static methods, adapting to peak and off-peak traffic conditions for improved flow management. So, a built-in traffic generator module creates vehicle routes for 4 hours, including peak hours, and a signal design module produces signal schedule cycles according to static, dynamic, and hybrid methods. Vehicle count distributions are weighted differently for each zone (i.e., West, North, East, South) to generate diverse traffic patterns. The extended experimental results for 6 intersections with 4 hours of simulation time imply that zone-based traffic pattern distributions affect signal design selection. Although the static method works great for evenly zone-based traffic distribution, the hybrid method works well for highly weighted traffic at intersection pairs of the West-East and North-South zones.
☆ Spatial Mental Modeling from Limited Views
Can Vision Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models, internal representations of unseen space, to reason about layout, perspective, and motion. Our new MindCube benchmark with 21,154 questions across 3,268 images exposes this critical gap, where existing VLMs exhibit near-random performance. Using MindCube, we systematically evaluate how well VLMs build robust spatial mental models through representing positions (cognitive mapping), orientations (perspective-taking), and dynamics (mental simulation for "what-if" movements). We then explore three approaches to help VLMs approximate spatial mental models, including unseen intermediate views, natural language reasoning chains, and cognitive maps. The significant improvement comes from a synergistic approach, "map-then-reason", that jointly trains the model to first generate a cognitive map and then reason upon it. By training models to reason over these internal maps, we boosted accuracy from 37.8% to 60.8% (+23.0%). Adding reinforcement learning pushed performance even further to 70.7% (+32.9%). Our key insight is that such scaffolding of spatial mental models, actively constructing and utilizing internal structured spatial representations with flexible reasoning processes, significantly improves understanding of unobservable space.
comment: Preprint version
☆ Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of the conditional term. However, the high guidance scale often results in oversaturation and unrealistic artifacts. In this paper, we introduce a new perspective based on low-frequency signals, identifying the accumulation of redundant information in these signals as the key factor behind oversaturation and unrealistic artifacts. Building on this insight, we propose low-frequency improved classifier-free guidance (LF-CFG) to mitigate these issues. Specifically, we introduce an adaptive threshold-based measurement to pinpoint the locations of redundant information. We determine a reasonable threshold by analyzing the change rate of low-frequency information between prior and current steps. We then apply a down-weight strategy to reduce the impact of redundant information in the low-frequency signals. Experimental results demonstrate that LF-CFG effectively alleviates oversaturation and unrealistic artifacts across various diffusion models, including Stable Diffusion-XL, Stable Diffusion 2.1, 3.0, 3.5, and SiT-XL.
☆ A Comprehensive Dataset for Underground Miner Detection in Diverse Scenario
Underground mining operations face significant safety challenges that make emergency response capabilities crucial. While robots have shown promise in assisting with search and rescue operations, their effectiveness depends on reliable miner detection capabilities. Deep learning algorithms offer potential solutions for automated miner detection, but require comprehensive training datasets, which are currently lacking for underground mining environments. This paper presents a novel thermal imaging dataset specifically designed to enable the development and validation of miner detection systems for potential emergency applications. We systematically captured thermal imagery of various mining activities and scenarios to create a robust foundation for detection algorithms. To establish baseline performance metrics, we evaluated several state-of-the-art object detection algorithms including YOLOv8, YOLOv10, YOLO11, and RT-DETR on our dataset. While not exhaustive of all possible emergency situations, this dataset serves as a crucial first step toward developing reliable thermal-based miner detection systems that could eventually be deployed in real emergency scenarios. This work demonstrates the feasibility of using thermal imaging for miner detection and establishes a foundation for future research in this critical safety application.
☆ ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing
While end-to-end video-to-audio generation has greatly improved, producing high-fidelity audio that authentically captures the nuances of visual content remains challenging. Like professionals in the creative industries, such generation requires sophisticated reasoning about items such as visual dynamics, acoustic environments, and temporal relationships. We present \textbf{ThinkSound}, a novel framework that leverages Chain-of-Thought (CoT) reasoning to enable stepwise, interactive audio generation and editing for videos. Our approach decomposes the process into three complementary stages: foundational foley generation that creates semantically coherent soundscapes, interactive object-centric refinement through precise user interactions, and targeted editing guided by natural language instructions. At each stage, a multimodal large language model generates contextually aligned CoT reasoning that guides a unified audio foundation model. Furthermore, we introduce \textbf{AudioCoT}, a comprehensive dataset with structured reasoning annotations that establishes connections between visual content, textual descriptions, and sound synthesis. Experiments demonstrate that ThinkSound achieves state-of-the-art performance in video-to-audio generation across both audio metrics and CoT metrics and excels in out-of-distribution Movie Gen Audio benchmark. The demo page is available at https://ThinkSound-Demo.github.io.
☆ Controllable 3D Placement of Objects with Scene-Aware Diffusion Models
Image editing approaches have become more powerful and flexible with the advent of powerful text-conditioned generative models. However, placing objects in an environment with a precise location and orientation still remains a challenge, as this typically requires carefully crafted inpainting masks or prompts. In this work, we show that a carefully designed visual map, combined with coarse object masks, is sufficient for high quality object placement. We design a conditioning signal that resolves ambiguities, while being flexible enough to allow for changing of shapes or object orientations. By building on an inpainting model, we leave the background intact by design, in contrast to methods that model objects and background jointly. We demonstrate the effectiveness of our method in the automotive setting, where we compare different conditioning signals in novel object placement tasks. These tasks are designed to measure edit quality not only in terms of appearance, but also in terms of pose and location accuracy, including cases that require non-trivial shape changes. Lastly, we show that fine location control can be combined with appearance control to place existing objects in precise locations in a scene.
☆ Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation
Atypical mitoses mark a deviation in the cell division process that can be an independent prognostically relevant marker for tumor malignancy. However, their identification remains challenging due to low prevalence, at times subtle morphological differences from normal mitoses, low inter-rater agreement among pathologists, and class imbalance in datasets. Building on the Atypical Mitosis dataset for Breast Cancer (AMi-Br), this study presents a comprehensive benchmark comparing deep learning approaches for automated atypical mitotic figure (AMF) classification, including baseline models, foundation models with linear probing, and foundation models fine-tuned with low-rank adaptation (LoRA). For rigorous evaluation, we further introduce two new hold-out AMF datasets - AtNorM-Br, a dataset of mitoses from the The TCGA breast cancer cohort, and AtNorM-MD, a multi-domain dataset of mitoses from the MIDOG++ training set. We found average balanced accuracy values of up to 0.8135, 0.7696, and 0.7705 on the in-domain AMi-Br and the out-of-domain AtNorm-Br and AtNorM-MD datasets, respectively, with the results being particularly good for LoRA-based adaptation of the Virchow-line of foundation models. Our work shows that atypical mitosis classification, while being a challenging problem, can be effectively addressed through the use of recent advances in transfer learning and model fine-tuning techniques. We make available all code and data used in this paper in this github repository: https://github.com/DeepMicroscopy/AMi-Br_Benchmark.
☆ HyperSORT: Self-Organising Robust Training with hyper-networks MICCAI 2025
Medical imaging datasets often contain heterogeneous biases ranging from erroneous labels to inconsistent labeling styles. Such biases can negatively impact deep segmentation networks performance. Yet, the identification and characterization of such biases is a particularly tedious and challenging task. In this paper, we introduce HyperSORT, a framework using a hyper-network predicting UNets' parameters from latent vectors representing both the image and annotation variability. The hyper-network parameters and the latent vector collection corresponding to each data sample from the training set are jointly learned. Hence, instead of optimizing a single neural network to fit a dataset, HyperSORT learns a complex distribution of UNet parameters where low density areas can capture noise-specific patterns while larger modes robustly segment organs in differentiated but meaningful manners. We validate our method on two 3D abdominal CT public datasets: first a synthetically perturbed version of the AMOS dataset, and TotalSegmentator, a large scale dataset containing real unknown biases and errors. Our experiments show that HyperSORT creates a structured mapping of the dataset allowing the identification of relevant systematic biases and erroneous samples. Latent space clusters yield UNet parameters performing the segmentation task in accordance with the underlying learned systematic bias. The code and our analysis of the TotalSegmentator dataset are made available: https://github.com/ImFusionGmbH/HyperSORT
comment: Accepted at MICCAI 2025
☆ EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splatting
Efficient three-dimensional reconstruction and real-time visualization are critical in surgical scenarios such as endoscopy. In recent years, 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in efficient 3D reconstruction and rendering. Most 3DGS-based Simultaneous Localization and Mapping (SLAM) methods only rely on the appearance constraints for optimizing both 3DGS and camera poses. However, in endoscopic scenarios, the challenges include photometric inconsistencies caused by non-Lambertian surfaces and dynamic motion from breathing affects the performance of SLAM systems. To address these issues, we additionally introduce optical flow loss as a geometric constraint, which effectively constrains both the 3D structure of the scene and the camera motion. Furthermore, we propose a depth regularisation strategy to mitigate the problem of photometric inconsistencies and ensure the validity of 3DGS depth rendering in endoscopic scenes. In addition, to improve scene representation in the SLAM system, we improve the 3DGS refinement strategy by focusing on viewpoints corresponding to Keyframes with suboptimal rendering quality frames, achieving better rendering results. Extensive experiments on the C3VD static dataset and the StereoMIS dynamic dataset demonstrate that our method outperforms existing state-of-the-art methods in novel view synthesis and pose estimation, exhibiting high performance in both static and dynamic surgical scenes. The source code will be publicly available upon paper acceptance.
☆ XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.
comment: Project Page: https://bytedance.github.io/XVerse Github Link: https://github.com/bytedance/XVerse
☆ Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction ICCV 2025
This paper presents an end-to-end framework for reconstructing 3D parametric curves directly from multi-view edge maps. Contrasting with existing two-stage methods that follow a sequential ``edge point cloud reconstruction and parametric curve fitting'' pipeline, our one-stage approach optimizes 3D parametric curves directly from 2D edge maps, eliminating error accumulation caused by the inherent optimization gap between disconnected stages. However, parametric curves inherently lack suitability for rendering-based multi-view optimization, necessitating a complementary representation that preserves their geometric properties while enabling differentiable rendering. We propose a novel bi-directional coupling mechanism between parametric curves and edge-oriented Gaussian components. This tight correspondence formulates a curve-aware Gaussian representation, \textbf{CurveGaussian}, that enables differentiable rendering of 3D curves, allowing direct optimization guided by multi-view evidence. Furthermore, we introduce a dynamically adaptive topology optimization framework during training to refine curve structures through linearization, merging, splitting, and pruning operations. Comprehensive evaluations on the ABC dataset and real-world benchmarks demonstrate our one-stage method's superiority over two-stage alternatives, particularly in producing cleaner and more robust reconstructions. Additionally, by directly optimizing parametric curves, our method significantly reduces the parameter count during training, achieving both higher efficiency and superior performance compared to existing approaches.
comment: Code: https://github.com/zhirui-gao/Curve-Gaussian Accepted by ICCV 2025
☆ FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detection
Few-shot industrial anomaly detection (FS-IAD) presents a critical challenge for practical automated inspection systems operating in data-scarce environments. While existing approaches predominantly focus on deriving prototypes from limited normal samples, they typically neglect to systematically incorporate query image statistics to enhance prototype representativeness. To address this issue, we propose FastRef, a novel and efficient prototype refinement framework for FS-IAD. Our method operates through an iterative two-stage process: (1) characteristic transfer from query features to prototypes via an optimizable transformation matrix, and (2) anomaly suppression through prototype alignment. The characteristic transfer is achieved through linear reconstruction of query features from prototypes, while the anomaly suppression addresses a key observation in FS-IAD that unlike conventional IAD with abundant normal prototypes, the limited-sample setting makes anomaly reconstruction more probable. Therefore, we employ optimal transport (OT) for non-Gaussian sampled features to measure and minimize the gap between prototypes and their refined counterparts for anomaly suppression. For comprehensive evaluation, we integrate FastRef with three competitive prototype-based FS-IAD methods: PatchCore, FastRecon, WinCLIP, and AnomalyDINO. Extensive experiments across four benchmark datasets of MVTec, ViSA, MPDD and RealIAD demonstrate both the effectiveness and computational efficiency of our approach under 1/2/4-shots.
comment: 18pages, 7figures, 6tables
☆ GenFlow: Interactive Modular System for Image Generation
Generative art unlocks boundless creative possibilities, yet its full potential remains untapped due to the technical expertise required for advanced architectural concepts and computational workflows. To bridge this gap, we present GenFlow, a novel modular framework that empowers users of all skill levels to generate images with precision and ease. Featuring a node-based editor for seamless customization and an intelligent assistant powered by natural language processing, GenFlow transforms the complexity of workflow creation into an intuitive and accessible experience. By automating deployment processes and minimizing technical barriers, our framework makes cutting-edge generative art tools available to everyone. A user study demonstrated GenFlow's ability to optimize workflows, reduce task completion times, and enhance user understanding through its intuitive interface and adaptive features. These results position GenFlow as a groundbreaking solution that redefines accessibility and efficiency in the realm of generative art.
☆ CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection ICCV 2025
Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point correspondences. However, differences in feature channel attention between images and point clouds may lead to degraded matching results, ultimately impairing registration accuracy. Furthermore, similar structures in the scene could lead to redundant correspondences in cross-modal matching. To address these issues, we propose Channel Adaptive Adjustment Module (CAA) and Global Optimal Selection Module (GOS). CAA enhances intra-modal features and suppresses cross-modal sensitivity, while GOS replaces local selection with global optimization. Experiments on RGB-D Scenes V2 and 7-Scenes demonstrate the superiority of our method, achieving state-of-the-art performance in image-to-point cloud registration.
comment: ICCV 2025 accepted
☆ ToosiCubix: Monocular 3D Cuboid Labeling via Vehicle Part Annotations
Many existing methods for 3D cuboid annotation of vehicles rely on expensive and carefully calibrated camera-LiDAR or stereo setups, limiting their accessibility for large-scale data collection. We introduce ToosiCubix, a simple yet powerful approach for annotating ground-truth cuboids using only monocular images and intrinsic camera parameters. Our method requires only about 10 user clicks per vehicle, making it highly practical for adding 3D annotations to existing datasets originally collected without specialized equipment. By annotating specific features (e.g., wheels, car badge, symmetries) across different vehicle parts, we accurately estimate each vehicle's position, orientation, and dimensions up to a scale ambiguity (8 DoF). The geometric constraints are formulated as an optimization problem, which we solve using a coordinate descent strategy, alternating between Perspective-n-Points (PnP) and least-squares subproblems. To handle common ambiguities such as scale and unobserved dimensions, we incorporate probabilistic size priors, enabling 9 DoF cuboid placements. We validate our annotations against the KITTI and Cityscapes3D datasets, demonstrating that our method offers a cost-effective and scalable solution for high-quality 3D cuboid annotation.
☆ CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations
2D scene graphs provide a structural and explainable framework for scene understanding. However, current work still struggles with the lack of accurate scene graph data. To overcome this data bottleneck, we present CoPa-SG, a synthetic scene graph dataset with highly precise ground truth and exhaustive relation annotations between all objects. Moreover, we introduce parametric and proto-relations, two new fundamental concepts for scene graphs. The former provides a much more fine-grained representation than its traditional counterpart by enriching relations with additional parameters such as angles or distances. The latter encodes hypothetical relations in a scene graph and describes how relations would form if new objects are placed in the scene. Using CoPa-SG, we compare the performance of various scene graph generation models. We demonstrate how our new relation types can be integrated in downstream applications to enhance planning and reasoning capabilities.
☆ ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
Cinematography, the fundamental visual language of film, is essential for conveying narrative, emotion, and aesthetic quality. While recent Vision-Language Models (VLMs) demonstrate strong general visual understanding, their proficiency in comprehending the nuanced cinematic grammar embedded within individual shots remains largely unexplored and lacks robust evaluation. This critical gap limits both fine-grained visual comprehension and the precision of AI-assisted video generation. To address this, we introduce \textbf{ShotBench}, a comprehensive benchmark specifically designed for cinematic language understanding. It features over 3.5k expert-annotated QA pairs from images and video clips, meticulously curated from over 200 acclaimed (predominantly Oscar-nominated) films and spanning eight key cinematography dimensions. Our evaluation of 24 leading VLMs on ShotBench reveals their substantial limitations: even the top-performing model achieves less than 60\% average accuracy, particularly struggling with fine-grained visual cues and complex spatial reasoning. To catalyze advancement in this domain, we construct \textbf{ShotQA}, a large-scale multimodal dataset comprising approximately 70k cinematic QA pairs. Leveraging ShotQA, we develop \textbf{ShotVL} through supervised fine-tuning and Group Relative Policy Optimization. ShotVL significantly outperforms all existing open-source and proprietary models on ShotBench, establishing new \textbf{state-of-the-art} performance. We open-source our models, data, and code to foster rapid progress in this crucial area of AI-driven cinematic understanding and generation.
☆ Generalizable Neural Electromagnetic Inverse Scattering
Solving Electromagnetic Inverse Scattering Problems (EISP) is fundamental in applications such as medical imaging, where the goal is to reconstruct the relative permittivity from scattered electromagnetic field. This inverse process is inherently ill-posed and highly nonlinear, making it particularly challenging. A recent machine learning-based approach, Img-Interiors, shows promising results by leveraging continuous implicit functions. However, it requires case-specific optimization, lacks generalization to unseen data, and fails under sparse transmitter setups (e.g., with only one transmitter). To address these limitations, we revisit EISP from a physics-informed perspective, reformulating it as a two stage inverse transmission-scattering process. This formulation reveals the induced current as a generalizable intermediate representation, effectively decoupling the nonlinear scattering process from the ill-posed inverse problem. Built on this insight, we propose the first generalizable physics-driven framework for EISP, comprising a current estimator and a permittivity solver, working in an end-to-end manner. The current estimator explicitly learns the induced current as a physical bridge between the incident and scattered field, while the permittivity solver computes the relative permittivity directly from the estimated induced current. This design enables data-driven training and generalizable feed-forward prediction of relative permittivity on unseen data while maintaining strong robustness to transmitter sparsity. Extensive experiments show that our method outperforms state-of-the-art approaches in reconstruction accuracy, generalization, and robustness. This work offers a fundamentally new perspective on electromagnetic inverse scattering and represents a major step toward cost-effective practical solutions for electromagnetic imaging.
☆ PanSt3R: Multi-view Consistent Panoptic Segmentation ICCV 2025
Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing approaches typically leverage off-the-shelf models to extract per-frame 2D panoptic segmentations, before optimizing an implicit geometric representation (often based on NeRF) to integrate and fuse the 2D predictions. We argue that relying on 2D panoptic segmentation for a problem inherently 3D and multi-view is likely suboptimal as it fails to leverage the full potential of spatial relationships across views. In addition to requiring camera parameters, these approaches also necessitate computationally expensive test-time optimization for each scene. Instead, in this work, we propose a unified and integrated approach PanSt3R, which eliminates the need for test-time optimization by jointly predicting 3D geometry and multi-view panoptic segmentation in a single forward pass. Our approach builds upon recent advances in 3D reconstruction, specifically upon MUSt3R, a scalable multi-view version of DUSt3R, and enhances it with semantic awareness and multi-view panoptic segmentation capabilities. We additionally revisit the standard post-processing mask merging procedure and introduce a more principled approach for multi-view segmentation. We also introduce a simple method for generating novel-view predictions based on the predictions of PanSt3R and vanilla 3DGS. Overall, the proposed PanSt3R is conceptually simple, yet fast and scalable, and achieves state-of-the-art performance on several benchmarks, while being orders of magnitude faster than existing methods.
comment: Accepted at ICCV 2025
☆ Automatic Reviewers Assignment to a Research Paper Based on Allied References and Publications Weight
Everyday, a vast stream of research documents is submitted to conferences, anthologies, journals, newsletters, annual reports, daily papers, and various periodicals. Many such publications use independent external specialists to review submissions. This process is called peer review, and the reviewers are called referees. However, it is not always possible to pick the best referee for reviewing. Moreover, new research fields are emerging in every sector, and the number of research papers is increasing dramatically. To review all these papers, every journal assigns a small team of referees who may not be experts in all areas. For example, a research paper in communication technology should be reviewed by an expert from the same field. Thus, efficiently selecting the best reviewer or referee for a research paper is a big challenge. In this research, we propose and implement program that uses a new strategy to automatically select the best reviewers for a research paper. Every research paper contains references at the end, usually from the same area. First, we collect the references and count authors who have at least one paper in the references. Then, we automatically browse the web to extract research topic keywords. Next, we search for top researchers in the specific topic and count their h-index, i10-index, and citations for the first n authors. Afterward, we rank the top n authors based on a score and automatically browse their homepages to retrieve email addresses. We also check their co-authors and colleagues online and discard them from the list. The remaining top n authors, generally professors, are likely the best referees for reviewing the research paper.
comment: IEEE Conference Proceedings (5 Pages)
☆ Holistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models
Surgical workflow analysis is essential in robot-assisted surgeries, yet the long duration of such procedures poses significant challenges for comprehensive video analysis. Recent approaches have predominantly relied on transformer models; however, their quadratic attention mechanism restricts efficient processing of lengthy surgical videos. In this paper, we propose a novel hierarchical input-dependent state space model that leverages the linear scaling property of state space models to enable decision making on full-length videos while capturing both local and global dynamics. Our framework incorporates a temporally consistent visual feature extractor, which appends a state space model head to a visual feature extractor to propagate temporal information. The proposed model consists of two key modules: a local-aggregation state space model block that effectively captures intricate local dynamics, and a global-relation state space model block that models temporal dependencies across the entire video. The model is trained using a hybrid discrete-continuous supervision strategy, where both signals of discrete phase labels and continuous phase progresses are propagated through the network. Experiments have shown that our method outperforms the current state-of-the-art methods by a large margin (+2.8% on Cholec80, +4.3% on MICCAI2016, and +12.9% on Heichole datasets). Code will be publicly available after paper acceptance.
☆ Multimodal LLMs for Visualization Reconstruction and Understanding
Visualizations are crucial for data communication, yet understanding them requires comprehension of both visual elements and their underlying data relationships. Current multimodal large models, while effective in natural image understanding, struggle with visualization due to their inability to decode the data-to-visual mapping rules and extract structured information. To address these challenges, we present a novel dataset and train multimodal visualization LLMs specifically designed for understanding. Our approach combines chart images with their corresponding vectorized representations, encoding schemes, and data features. The proposed vector format enables compact and accurate reconstruction of visualization content. Experimental results demonstrate significant improvements in both data extraction accuracy and chart reconstruction quality.
☆ LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning
Current vision-language models (VLMs) are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of specialized vision-language instruction-following data. We introduce a method for generating such data by integrating human keypoints with traditional visual features such as captions and bounding boxes, enabling more precise understanding of human-centric scenes. Our approach constructs a dataset comprising 200,328 samples tailored to fine-tune models for human-centric tasks, focusing on three areas: conversation, detailed description, and complex reasoning. We establish an Extended Human Pose and Action Understanding Benchmark (E-HPAUB) to assess model performance on human pose and action understanding. We fine-tune the LLaVA-1.5-7B model using this dataset and evaluate our resulting LLaVA-Pose model on the benchmark, achieving significant improvements. Experimental results show an overall improvement of 33.2% compared to the original LLaVA-1.5-7B model. These findings highlight the effectiveness of keypoint-integrated data in enhancing multimodal models for human-centric visual understanding. Code is available at https://github.com/Ody-trek/LLaVA-Pose.
comment: arXiv admin note: substantial text overlap with arXiv:2409.09306
☆ DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
Visual grounding in text-rich document images is a critical yet underexplored challenge for document intelligence and visual question answering (VQA) systems. We present \drishtikon, a multi-granular visual grounding framework designed to enhance interpretability and trust in VQA for complex, multilingual documents. Our approach integrates robust multi-lingual OCR, large language models, and a novel region matching algorithm to accurately localize answer spans at block, line, word, and point levels. We curate a new benchmark from the CircularsVQA test set, providing fine-grained, human-verified annotations across multiple granularities. Extensive experiments demonstrate that our method achieves state-of-the-art grounding accuracy, with line-level granularity offering the best trade-off between precision and recall. Ablation studies further highlight the benefits of multi-block and multi-line reasoning. Comparative evaluations with leading vision-language models reveal the limitations of current VLMs in precise localization, underscoring the effectiveness of our structured, alignment-based approach. Our findings pave the way for more robust and interpretable document understanding systems in real-world, text-centric scenarios. Code and dataset has been made available at https://github.com/kasuba-badri-vishal/DhrishtiKon.
comment: Work in progress
☆ Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing
The development of continual learning (CL) methods, which aim to learn new tasks in a sequential manner from the training data acquired continuously, has gained great attention in remote sensing (RS). The existing CL methods in RS, while learning new tasks, enhance robustness towards catastrophic forgetting. This is achieved by using a large number of labeled training samples, which is costly and not always feasible to gather in RS. To address this problem, we propose a novel continual self-supervised learning method in the context of masked autoencoders (denoted as CoSMAE). The proposed CoSMAE consists of two components: i) data mixup; and ii) model mixup knowledge distillation. Data mixup is associated with retaining information on previous data distributions by interpolating images from the current task with those from the previous tasks. Model mixup knowledge distillation is associated with distilling knowledge from past models and the current model simultaneously by interpolating their model weights to form a teacher for the knowledge distillation. The two components complement each other to regularize the MAE at the data and model levels to facilitate better generalization across tasks and reduce the risk of catastrophic forgetting. Experimental results show that CoSMAE achieves significant improvements of up to 4.94% over state-of-the-art CL methods applied to MAE. Our code is publicly available at: https://git.tu-berlin.de/rsim/CoSMAE.
comment: Accepted to IEEE Geoscience and Remote Sensing Letters. Our code is available at https://git.tu-berlin.de/rsim/CoSMAE
☆ HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation MICCAI 2025
Surgical Video Synthesis has emerged as a promising research direction following the success of diffusion models in general-domain video generation. Although existing approaches achieve high-quality video generation, most are unconditional and fail to maintain consistency with surgical actions and phases, lacking the surgical understanding and fine-grained guidance necessary for factual simulation. We address these challenges by proposing HieraSurg, a hierarchy-aware surgical video generation framework consisting of two specialized diffusion models. Given a surgical phase and an initial frame, HieraSurg first predicts future coarse-grained semantic changes through a segmentation prediction model. The final video is then generated by a second-stage model that augments these temporal segmentation maps with fine-grained visual features, leading to effective texture rendering and integration of semantic information in the video space. Our approach leverages surgical information at multiple levels of abstraction, including surgical phase, action triplets, and panoptic segmentation maps. The experimental results on Cholecystectomy Surgical Video Generation demonstrate that the model significantly outperforms prior work both quantitatively and qualitatively, showing strong generalization capabilities and the ability to generate higher frame-rate videos. The model exhibits particularly fine-grained adherence when provided with existing segmentation maps, suggesting its potential for practical surgical applications.
comment: Accepted at MICCAI 2025
☆ HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
With the rapid evolution of multimodal large language models, the capacity to deeply understand and interpret human intentions has emerged as a critical capability, which demands detailed and thoughtful reasoning. In recent studies, Reinforcement Learning (RL) has demonstrated potential in enhancing the reasoning capabilities of Large Language Models (LLMs). Nonetheless, the challenges associated with adapting RL to multimodal data and formats remain largely unaddressed. In this paper, we identify two issues in existing multimodal reasoning models: insufficient global context understanding and shortcut problems. Insufficient context understanding can happen when a model misinterprets multimodal context, resulting in incorrect answers. The shortcut problem occurs when the model overlooks crucial clues in multimodal inputs, directly addressing the query without considering the multimodal information. To tackle these issues, we emphasize the necessity for the model to reason with a clear understanding of the global context within multimodal inputs. This global context understanding can effectively prevent the model from overlooking key multimodal cues and ensure a thorough reasoning process. To ensure the accurate interpretation of multimodal context information, we implement a context reward judged by a large language model, alongside format and accuracy rewards. Additionally, to improve complex reasoning capability, we employ the LLM to assess the logical reward, determining whether the reasoning process successfully integrates multimodal information with logical methods. We also introduce a reasoning omni-modal benchmark, IntentBench, aimed at evaluating models in understanding complex human intentions and emotions. Our proposed method demonstrates advanced performance across multiple omni-modal benchmarks compared to other open-source omni-modal models.
☆ WordCon: Word-level Typography Control in Scene Text Rendering
Achieving precise word-level typography control within generated images remains a persistent challenge. To address it, we newly construct a word-level controlled scene text dataset and introduce the Text-Image Alignment (TIA) framework. This framework leverages cross-modal correspondence between text and local image regions provided by grounding models to enhance the Text-to-Image (T2I) model training. Furthermore, we propose WordCon, a hybrid parameter-efficient fine-tuning (PEFT) method. WordCon reparameterizes selective key parameters, improving both efficiency and portability. This allows seamless integration into diverse pipelines, including artistic text rendering, text editing, and image-conditioned text rendering. To further enhance controllability, the masked loss at the latent level is applied to guide the model to concentrate on learning the text region in the image, and the joint-attention loss provides feature-level supervision to promote disentanglement between different words. Both qualitative and quantitative results demonstrate the superiority of our method to the state of the art. The datasets and source code will be available for academic use.
☆ FairyGen: Storied Cartoon Video from a Single Child-Drawn Character
We propose FairyGen, an automatic system for generating story-driven cartoon videos from a single child's drawing, while faithfully preserving its unique artistic style. Unlike previous storytelling methods that primarily focus on character consistency and basic motion, FairyGen explicitly disentangles character modeling from stylized background generation and incorporates cinematic shot design to support expressive and coherent storytelling. Given a single character sketch, we first employ an MLLM to generate a structured storyboard with shot-level descriptions that specify environment settings, character actions, and camera perspectives. To ensure visual consistency, we introduce a style propagation adapter that captures the character's visual style and applies it to the background, faithfully retaining the character's full visual identity while synthesizing style-consistent scenes. A shot design module further enhances visual diversity and cinematic quality through frame cropping and multi-view synthesis based on the storyboard. To animate the story, we reconstruct a 3D proxy of the character to derive physically plausible motion sequences, which are then used to fine-tune an MMDiT-based image-to-video diffusion model. We further propose a two-stage motion customization adapter: the first stage learns appearance features from temporally unordered frames, disentangling identity from motion; the second stage models temporal dynamics using a timestep-shift strategy with frozen identity weights. Once trained, FairyGen directly renders diverse and coherent video scenes aligned with the storyboard. Extensive experiments demonstrate that our system produces animations that are stylistically faithful, narratively structured natural motion, highlighting its potential for personalized and engaging story animation. The code will be available at https://github.com/GVCLab/FairyGen
comment: Project Page: https://jayleejia.github.io/FairyGen/ ; Code: https://github.com/GVCLab/FairyGen
☆ Video Virtual Try-on with Conditional Diffusion Transformer Inpainter
Video virtual try-on aims to naturally fit a garment to a target person in consecutive video frames. It is a challenging task, on the one hand, the output video should be in good spatial-temporal consistency, on the other hand, the details of the given garment need to be preserved well in all the frames. Naively using image-based try-on methods frame by frame can get poor results due to severe inconsistency. Recent diffusion-based video try-on methods, though very few, happen to coincide with a similar solution: inserting temporal attention into image-based try-on model to adapt it for video try-on task, which have shown improvements but there still exist inconsistency problems. In this paper, we propose ViTI (Video Try-on Inpainter), formulate and implement video virtual try-on as a conditional video inpainting task, which is different from previous methods. In this way, we start with a video generation problem instead of an image-based try-on problem, which from the beginning has a better spatial-temporal consistency. Specifically, at first we build a video inpainting framework based on Diffusion Transformer with full 3D spatial-temporal attention, and then we progressively adapt it for video garment inpainting, with a collection of masking strategies and multi-stage training. After these steps, the model can inpaint the masked garment area with appropriate garment pixels according to the prompt with good spatial-temporal consistency. Finally, as other try-on methods, garment condition is added to the model to make sure the inpainted garment appearance and details are as expected. Both quantitative and qualitative experimental results show that ViTI is superior to previous works.
comment: 10 pages, 6 figures
☆ DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic ICCV 2025
Real-world object detection systems, such as those in autonomous driving and surveillance, must continuously learn new object categories and simultaneously adapt to changing environmental conditions. Existing approaches, Class Incremental Object Detection (CIOD) and Domain Incremental Object Detection (DIOD) only address one aspect of this challenge. CIOD struggles in unseen domains, while DIOD suffers from catastrophic forgetting when learning new classes, limiting their real-world applicability. To overcome these limitations, we introduce Dual Incremental Object Detection (DuIOD), a more practical setting that simultaneously handles class and domain shifts in an exemplar-free manner. We propose DuET, a Task Arithmetic-based model merging framework that enables stable incremental learning while mitigating sign conflicts through a novel Directional Consistency Loss. Unlike prior methods, DuET is detector-agnostic, allowing models like YOLO11 and RT-DETR to function as real-time incremental object detectors. To comprehensively evaluate both retention and adaptation, we introduce the Retention-Adaptability Index (RAI), which combines the Average Retention Index (Avg RI) for catastrophic forgetting and the Average Generalization Index for domain adaptability into a common ground. Extensive experiments on the Pascal Series and Diverse Weather Series demonstrate DuET's effectiveness, achieving a +13.12% RAI improvement while preserving 89.3% Avg RI on the Pascal Series (4 tasks), as well as a +11.39% RAI improvement with 88.57% Avg RI on the Diverse Weather Series (3 tasks), outperforming existing methods.
comment: Accepted at ICCV 2025
☆ Temporal Rate Reduction Clustering for Human Motion Segmentation ICCV 2025
Human Motion Segmentation (HMS), which aims to partition videos into non-overlapping human motions, has attracted increasing research attention recently. Existing approaches for HMS are mainly dominated by subspace clustering methods, which are grounded on the assumption that high-dimensional temporal data align with a Union-of-Subspaces (UoS) distribution. However, the frames in video capturing complex human motions with cluttered backgrounds may not align well with the UoS distribution. In this paper, we propose a novel approach for HMS, named Temporal Rate Reduction Clustering ($\text{TR}^2\text{C}$), which jointly learns structured representations and affinity to segment the frame sequences in video. Specifically, the structured representations learned by $\text{TR}^2\text{C}$ maintain temporally consistent and align well with a UoS structure, which is favorable for the HMS task. We conduct extensive experiments on five benchmark HMS datasets and achieve state-of-the-art performances with different feature extractors.
comment: The paper is accepted by ICCV 2025. The first two authors are equally contributed
☆ GANet-Seg: Adversarial Learning for Brain Tumor Segmentation with Hybrid Generative Models
This work introduces a novel framework for brain tumor segmentation leveraging pre-trained GANs and Unet architectures. By combining a global anomaly detection module with a refined mask generation network, the proposed model accurately identifies tumor-sensitive regions and iteratively enhances segmentation precision using adversarial loss constraints. Multi-modal MRI data and synthetic image augmentation are employed to improve robustness and address the challenge of limited annotated datasets. Experimental results on the BraTS dataset demonstrate the effectiveness of the approach, achieving high sensitivity and accuracy in both lesion-wise Dice and HD95 metrics than the baseline. This scalable method minimizes the dependency on fully annotated data, paving the way for practical real-world applications in clinical settings.
☆ DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation
We introduce DiMPLe (Disentangled Multi-Modal Prompt Learning), a novel approach to disentangle invariant and spurious features across vision and language modalities in multi-modal learning. Spurious correlations in visual data often hinder out-of-distribution (OOD) performance. Unlike prior methods focusing solely on image features, DiMPLe disentangles features within and across modalities while maintaining consistent alignment, enabling better generalization to novel classes and robustness to distribution shifts. Our method combines three key objectives: (1) mutual information minimization between invariant and spurious features, (2) spurious feature regularization, and (3) contrastive learning on invariant features. Extensive experiments demonstrate DiMPLe demonstrates superior performance compared to CoOp-OOD, when averaged across 11 diverse datasets, and achieves absolute gains of 15.27 in base class accuracy and 44.31 in novel class accuracy.
☆ Real-Time ESFP: Estimating, Smoothing, Filtering, and Pose-Mapping
This paper presents ESFP, an end-to-end pipeline that converts monocular RGB video into executable joint trajectories for a low-cost 4-DoF desktop arm. ESFP comprises four sequential modules. (1) Estimating: ROMP lifts each frame to a 24-joint 3-D skeleton. (2) Smoothing: the proposed HPSTM-a sequence-to-sequence Transformer with self-attention-combines long-range temporal context with a differentiable forward-kinematics decoder, enforcing constant bone lengths and anatomical plausibility while jointly predicting joint means and full covariances. (3) Filtering: root-normalized trajectories are variance-weighted according to HPSTM's uncertainty estimates, suppressing residual noise. (4) Pose-Mapping: a geometric retargeting layer transforms shoulder-elbow-wrist triples into the uArm's polar workspace, preserving wrist orientation.
☆ ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation ICCV 2025
Training-free open-vocabulary semantic segmentation (OVS) aims to segment images given a set of arbitrary textual categories without costly model fine-tuning. Existing solutions often explore attention mechanisms of pre-trained models, such as CLIP, or generate synthetic data and design complex retrieval processes to perform OVS. However, their performance is limited by the capability of reliant models or the suboptimal quality of reference sets. In this work, we investigate the largely overlooked data quality problem for this challenging dense scene understanding task, and identify that a high-quality reference set can significantly benefit training-free OVS. With this observation, we introduce a data-quality-oriented framework, comprising a data pipeline to construct a reference set with well-paired segment-text embeddings and a simple similarity-based retrieval to unveil the essential effect of data. Remarkably, extensive evaluations on ten benchmark datasets demonstrate that our method outperforms all existing training-free OVS approaches, highlighting the importance of data-centric design for advancing OVS without training. Our code is available at https://github.com/xiweix/ReME .
comment: Accepted to ICCV 2025
☆ BitMark for Infinity: Watermarking Bitwise Autoregressive Image Generative Models
State-of-the-art text-to-image models like Infinity generate photorealistic images at an unprecedented speed. These models operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size. However, their impressive generative power comes with a growing risk: as their outputs increasingly populate the Internet, they are likely to be scraped and reused as training data-potentially by the very same models. This phenomenon has been shown to lead to model collapse, where repeated training on generated content, especially from the models' own previous versions, causes a gradual degradation in performance. A promising mitigation strategy is watermarking, which embeds human-imperceptible yet detectable signals into generated images-enabling the identification of generated content. In this work, we introduce BitMark, a robust bitwise watermarking framework for Infinity. Our method embeds a watermark directly at the bit level of the token stream across multiple scales (also referred to as resolutions) during Infinity's image generation process. Our bitwise watermark subtly influences the bits to preserve visual fidelity and generation speed while remaining robust against a spectrum of removal techniques. Furthermore, it exhibits high radioactivity, i.e., when watermarked generated images are used to train another image generative model, this second model's outputs will also carry the watermark. The radioactive traces remain detectable even when only fine-tuning diffusion or image autoregressive models on images watermarked with our BitMark. Overall, our approach provides a principled step toward preventing model collapse in image generative models by enabling reliable detection of generated outputs.
☆ MedPrompt: LLM-CNN Fusion with Weight Routing for Medical Image Segmentation and Classification
Current medical image analysis systems are typically task-specific, requiring separate models for classification and segmentation, and lack the flexibility to support user-defined workflows. To address these challenges, we introduce MedPrompt, a unified framework that combines a few-shot prompted Large Language Model (Llama-4-17B) for high-level task planning with a modular Convolutional Neural Network (DeepFusionLab) for low-level image processing. The LLM interprets user instructions and generates structured output to dynamically route task-specific pretrained weights. This weight routing approach avoids retraining the entire framework when adding new tasks-only task-specific weights are required, enhancing scalability and deployment. We evaluated MedPrompt across 19 public datasets, covering 12 tasks spanning 5 imaging modalities. The system achieves a 97% end-to-end correctness in interpreting and executing prompt-driven instructions, with an average inference latency of 2.5 seconds, making it suitable for near real-time applications. DeepFusionLab achieves competitive segmentation accuracy (e.g., Dice 0.9856 on lungs) and strong classification performance (F1 0.9744 on tuberculosis). Overall, MedPrompt enables scalable, prompt-driven medical imaging by combining the interpretability of LLMs with the efficiency of modular CNNs.
comment: 40 pages, 8 Tables, 9 Figures
☆ Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation ICCV 2025
Panoramic image processing is essential for omni-context perception, yet faces constraints like distortions, perspective occlusions, and limited annotations. Previous unsupervised domain adaptation methods transfer knowledge from labeled pinhole data to unlabeled panoramic images, but they require access to source pinhole data. To address these, we introduce a more practical task, i.e., Source-Free Occlusion-Aware Seamless Segmentation (SFOASS), and propose its first solution, called UNconstrained Learning Omni-Context Knowledge (UNLOCK). Specifically, UNLOCK includes two key modules: Omni Pseudo-Labeling Learning and Amodal-Driven Context Learning. While adapting without relying on source data or target labels, this framework enhances models to achieve segmentation with 360{\deg} viewpoint coverage and occlusion-aware reasoning. Furthermore, we benchmark the proposed SFOASS task through both real-to-real and synthetic-to-real adaptation settings. Experimental results show that our source-free method achieves performance comparable to source-dependent methods, yielding state-of-the-art scores of 10.9 in mAAP and 11.6 in mAP, along with an absolute improvement of +4.3 in mAPQ over the source-only method. All data and code will be made publicly available at https://github.com/yihong-97/UNLOCK.
comment: Accepted to ICCV 2025. All data and code will be made publicly available at https://github.com/yihong-97/UNLOCK
☆ GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding
Sequential grounding in 3D point clouds (SG3D) refers to locating sequences of objects by following text instructions for a daily activity with detailed steps. Current 3D visual grounding (3DVG) methods treat text instructions with multiple steps as a whole, without extracting useful temporal information from each step. However, the instructions in SG3D often contain pronouns such as "it", "here" and "the same" to make language expressions concise. This requires grounding methods to understand the context and retrieve relevant information from previous steps to correctly locate object sequences. Due to the lack of an effective module for collecting related historical information, state-of-the-art 3DVG methods face significant challenges in adapting to the SG3D task. To fill this gap, we propose GroundFlow -- a plug-in module for temporal reasoning on 3D point cloud sequential grounding. Firstly, we demonstrate that integrating GroundFlow improves the task accuracy of 3DVG baseline methods by a large margin (+7.5\% and +10.2\%) in the SG3D benchmark, even outperforming a 3D large language model pre-trained on various datasets. Furthermore, we selectively extract both short-term and long-term step information based on its relevance to the current instruction, enabling GroundFlow to take a comprehensive view of historical information and maintain its temporal understanding advantage as step counts increase. Overall, our work introduces temporal reasoning capabilities to existing 3DVG models and achieves state-of-the-art performance in the SG3D benchmark across five datasets.
☆ Out-of-Distribution Semantic Occupancy Prediction
3D Semantic Occupancy Prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distribution scenes, making them susceptible to Out-of-Distribution (OoD) objects and long-tail distributions, which increases the risk of undetected anomalies and misinterpretations, posing safety hazards. To address these challenges, we introduce Out-of-Distribution Semantic Occupancy Prediction, targeting OoD detection in 3D voxel space. To fill the gaps in the dataset, we propose a Synthetic Anomaly Integration Pipeline that injects synthetic anomalies while preserving realistic spatial and occlusion patterns, enabling the creation of two datasets: VAA-KITTI and VAA-KITTI-360. We introduce OccOoD, a novel framework integrating OoD detection into 3D semantic occupancy prediction, with Voxel-BEV Progressive Fusion (VBPF) leveraging an RWKV-based branch to enhance OoD detection via geometry-semantic fusion. Experimental results demonstrate that OccOoD achieves state-of-the-art OoD detection with an AuROC of 67.34% and an AuPRCr of 29.21% within a 1.2m region, while maintaining competitive occupancy prediction performance. The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD.
comment: The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD
☆ Task-Aware KV Compression For Cost-Effective Long Video Understanding
Long-video understanding (LVU) remains a severe challenge for existing multimodal large language models (MLLMs), primarily due to the prohibitive computational cost. Recent approaches have explored KV compression to mitigate this issue, but they often suffer from significant information loss at high compression ratios. In this paper, we introduce Video-X^2L, which flexibly preserves critical video information for each LVU task. Video-X^2L involves two key operations. The first one is called bi-level KV compression. During the MLLM's pre-filling stage, Video-X^2L generates two types of compressed KVs: low-compression KVs (L-KVs) to capture fine-grained video details and high-compression KVs (H-KVs) to offer compact video representations. The second one is called selective KV re-loading. During the MLLM's decoding stage, Video-X^2L selectively re-loads L-KVs for the most critical video chunks while using H-KVs for other less important ones. This allows the MLLM to fully utilize task-specific information while maintaining the overall compactness. Video-X^2L is simple yet effective: it is free from additional training and directly compatible with existing KV-compressible MLLMs. We evaluate Video-X^2L with a variety of popular LVU benchmarks, including VideoMME, MLVU, LongVideoBench, and VNBench. Our experiment result shows that Video-X^2L outperforms existing KV-compression methods by a huge advantage while substantially saving the computation cost.
comment: 14 pages, 3 figures, 6 tables
☆ Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations
Joint Photographic Experts Group (JPEG) achieves data compression by quantizing Discrete Cosine Transform (DCT) coefficients, which inevitably introduces compression artifacts. Most existing JPEG quality enhancement methods operate in the pixel domain, suffering from the high computational costs of decoding. Consequently, direct enhancement of JPEG images in the DCT domain has gained increasing attention. However, current DCT-domain methods often exhibit limited performance. To address this challenge, we identify two critical types of correlations within the DCT coefficients of JPEG images. Building on this insight, we propose an Advanced DCT-domain JPEG Quality Enhancement (AJQE) method that fully exploits these correlations. The AJQE method enables the adaptation of numerous well-established pixel-domain models to the DCT domain, achieving superior performance with reduced computational complexity. Compared to the pixel-domain counterparts, the DCT-domain models derived by our method demonstrate a 0.35 dB improvement in PSNR and a 60.5% increase in enhancement throughput on average.
☆ Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Learning semantic representations from point sets of 3D object shapes is often challenged by significant geometric variations, primarily due to differences in data acquisition methods. Typically, training data is generated using point simulators, while testing data is collected with distinct 3D sensors, leading to a simulation-to-reality (Sim2Real) domain gap that limits the generalization ability of point classifiers. Current unsupervised domain adaptation (UDA) techniques struggle with this gap, as they often lack robust, domain-insensitive descriptors capable of capturing global topological information, resulting in overfitting to the limited semantic patterns of the source domain. To address this issue, we introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds. Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures, and by modeling the topological relations of local geometric features through a novel self-supervised learning task. Additionally, we propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training, effectively reducing the impact of noisy pseudo-labels and enhancing the robustness of the adaptation process. Experimental results on three public Sim2Real benchmarks validate the effectiveness of our TAM framework, showing consistent improvements over state-of-the-art methods across all evaluated tasks. The source code of this work will be available at https://github.com/zou-longkun/TAG.git.
☆ Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
Generating realistic 3D objects from single-view images requires natural appearance, 3D consistency, and the ability to capture multiple plausible interpretations of unseen regions. Existing approaches often rely on fine-tuning pretrained 2D diffusion models or directly generating 3D information through fast network inference or 3D Gaussian Splatting, but their results generally suffer from poor multiview consistency and lack geometric detail. To takle these issues, we present a novel method that seamlessly integrates geometry and perception priors without requiring additional model training to reconstruct detailed 3D objects from a single image. Specifically, we train three different Gaussian branches initialized from the geometry prior, perception prior and Gaussian noise, respectively. The geometry prior captures the rough 3D shapes, while the perception prior utilizes the 2D pretrained diffusion model to enhance multiview information. Subsequently, we refine 3D Gaussian branches through mutual interaction between geometry and perception priors, further enhanced by a reprojection-based strategy that enforces depth consistency. Experiments demonstrate the higher-fidelity reconstruction results of our method, outperforming existing methods on novel view synthesis and 3D reconstruction, demonstrating robust and consistent 3D object generation.
comment: 10 pages, 5 figures
☆ Robust Deep Learning for Myocardial Scar Segmentation in Cardiac MRI with Noisy Labels MICCAI 2025
The accurate segmentation of myocardial scars from cardiac MRI is essential for clinical assessment and treatment planning. In this study, we propose a robust deep-learning pipeline for fully automated myocardial scar detection and segmentation by fine-tuning state-of-the-art models. The method explicitly addresses challenges of label noise from semi-automatic annotations, data heterogeneity, and class imbalance through the use of Kullback-Leibler loss and extensive data augmentation. We evaluate the model's performance on both acute and chronic cases and demonstrate its ability to produce accurate and smooth segmentations despite noisy labels. In particular, our approach outperforms state-of-the-art models like nnU-Net and shows strong generalizability in an out-of-distribution test set, highlighting its robustness across various imaging conditions and clinical tasks. These results establish a reliable foundation for automated myocardial scar quantification and support the broader clinical adoption of deep learning in cardiac imaging.
comment: MICCAI 2025
☆ Tree-based Semantic Losses: Application to Sparsely-supervised Large Multi-class Hyperspectral Segmentation
Hyperspectral imaging (HSI) shows great promise for surgical applications, offering detailed insights into biological tissue differences beyond what the naked eye can perceive. Refined labelling efforts are underway to train vision systems to distinguish large numbers of subtly varying classes. However, commonly used learning methods for biomedical segmentation tasks penalise all errors equivalently and thus fail to exploit any inter-class semantics in the label space. In this work, we introduce two tree-based semantic loss functions which take advantage of a hierarchical organisation of the labels. We further incorporate our losses in a recently proposed approach for training with sparse, background-free annotations. Extensive experiments demonstrate that our proposed method reaches state-of-the-art performance on a sparsely annotated HSI dataset comprising $107$ classes organised in a clinically-defined semantic tree structure. Furthermore, our method enables effective detection of out-of-distribution (OOD) pixels without compromising segmentation performance on in-distribution (ID) pixels.
☆ Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion
Federated learning (FL) enables collaborative model training across decentralized clients without sharing local data, but is challenged by heterogeneity in data, computation, and communication. Pretrained vision-language models (VLMs), with their strong generalization and lightweight tuning via prompts, offer a promising solution. However, existing federated prompt-learning methods rely only on text prompts and overlook joint label-domain distribution shifts. In this paper, we propose a personalized FL framework based on dual-prompt learning and cross fusion, termed pFedDC. Specifically, each client maintains both global and local prompts across vision and language modalities: global prompts capture common knowledge shared across the federation, while local prompts encode client-specific semantics and domain characteristics. Meanwhile, a cross-fusion module is designed to adaptively integrate prompts from different levels, enabling the model to generate personalized representations aligned with each client's unique data distribution. Extensive experiments across nine datasets with various types of heterogeneity show that pFedDC consistently outperforms state-of-the-art methods.
☆ YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection
Surface defect detection in industrial scenarios is both crucial and technically demanding due to the wide variability in defect types, irregular shapes and sizes, fine-grained requirements, and complex material textures. Although recent advances in AI-based detectors have improved performance, existing methods often suffer from redundant features, limited detail sensitivity, and weak robustness under multiscale conditions. To address these challenges, we propose YOLO-FDA, a novel YOLO-based detection framework that integrates fine-grained detail enhancement and attention-guided feature fusion. Specifically, we adopt a BiFPN-style architecture to strengthen bidirectional multilevel feature aggregation within the YOLOv5 backbone. To better capture fine structural changes, we introduce a Detail-directional Fusion Module (DDFM) that introduces a directional asymmetric convolution in the second-lowest layer to enrich spatial details and fuses the second-lowest layer with low-level features to enhance semantic consistency. Furthermore, we propose two novel attention-based fusion strategies, Attention-weighted Concatenation (AC) and Cross-layer Attention Fusion (CAF) to improve contextual representation and reduce feature noise. Extensive experiments on benchmark datasets demonstrate that YOLO-FDA consistently outperforms existing state-of-the-art methods in terms of both accuracy and robustness across diverse types of defects and scales.
comment: 14 pages, 6 figures. Submitted to The 8th Chinese Conference on Pattern Recognition and Computer Vision
☆ Learning to See in the Extremely Dark ICCV 2025
Learning-based methods have made promising advances in low-light RAW image enhancement, while their capability to extremely dark scenes where the environmental illuminance drops as low as 0.0001 lux remains to be explored due to the lack of corresponding datasets. To this end, we propose a paired-to-paired data synthesis pipeline capable of generating well-calibrated extremely low-light RAW images at three precise illuminance ranges of 0.01-0.1 lux, 0.001-0.01 lux, and 0.0001-0.001 lux, together with high-quality sRGB references to comprise a large-scale paired dataset named See-in-the-Extremely-Dark (SIED) to benchmark low-light RAW image enhancement approaches. Furthermore, we propose a diffusion-based framework that leverages the generative ability and intrinsic denoising property of diffusion models to restore visually pleasing results from extremely low-SNR RAW inputs, in which an Adaptive Illumination Correction Module (AICM) and a color consistency loss are introduced to ensure accurate exposure correction and color restoration. Extensive experiments on the proposed SIED and publicly available benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/JianghaiSCU/SIED.
comment: Accepted by ICCV 2025
☆ GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction ICML 2025
Trajectory prediction for surrounding agents is a challenging task in autonomous driving due to its inherent uncertainty and underlying multimodality. Unlike prevailing data-driven methods that primarily rely on supervised learning, in this paper, we introduce a novel Graph-oriented Inverse Reinforcement Learning (GoIRL) framework, which is an IRL-based predictor equipped with vectorized context representations. We develop a feature adaptor to effectively aggregate lane-graph features into grid space, enabling seamless integration with the maximum entropy IRL paradigm to infer the reward distribution and obtain the policy that can be sampled to induce multiple plausible plans. Furthermore, conditioned on the sampled plans, we implement a hierarchical parameterized trajectory generator with a refinement module to enhance prediction accuracy and a probability fusion strategy to boost prediction confidence. Extensive experimental results showcase our approach not only achieves state-of-the-art performance on the large-scale Argoverse & nuScenes motion forecasting benchmarks but also exhibits superior generalization abilities compared to existing supervised models.
comment: Accepted by ICML 2025
☆ CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization ICCV 2025
In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient methods to incorporate changes are needed to maintain up-to-date, high-quality reconstructions without the computational overhead of re-optimizing the entire scene. This paper introduces CL-Splats, which incrementally updates Gaussian splatting-based 3D representations from sparse scene captures. CL-Splats integrates a robust change-detection module that segments updated and static components within the scene, enabling focused, local optimization that avoids unnecessary re-computation. Moreover, CL-Splats supports storing and recovering previous scene states, facilitating temporal segmentation and new scene-analysis applications. Our extensive experiments demonstrate that CL-Splats achieves efficient updates with improved reconstruction quality over the state-of-the-art. This establishes a robust foundation for future real-time adaptation in 3D scene reconstruction tasks.
comment: ICCV 2025, Project Page: https://cl-splats.github.io
☆ IPFormer-VideoLLM: Enhancing Multi-modal Video Understanding for Multi-shot Scenes
Video Large Language Models (VideoLLMs) have demonstrated remarkable understanding capabilities, but are found struggling to tackle multi-shot scenarios,e.g., video clips with varying camera angles or scene changes. This challenge can render failures such as instance identity forgetting and key frame negligence. In this work, we first attribute the challenge to the lack of multi-shot annotations among existing datasets and therefore we introduce a new dataset termed MultiClip-Bench, featuring dense descriptions and instruction-based question-answering pairs tailored for multi-shot scenarios. We empirically find that the training set significantly boosts the multi-shot performance, while the testing benchmark provides a reliable measure of the model capability in multi-shot scenarios. By further analyzing and discovering that current models only encode instance features in a discrete or lossy manner, at the risk of missing identity information, we then contribute a new model IPFormer-VideoLLM. Its key idea is the injection of instance-level features as instance prompts through an efficient attention-based connector. This allows for the aggregation of instance-specific information across scenes. Experiments demonstrate that our proposed dataset and model not only enhance the multi-scene video understanding significantly, but also offer distinct advantages across various video benchmarks.
☆ Pushing Trade-Off Boundaries: Compact yet Effective Remote Sensing Change Detection
Remote sensing change detection is essential for monitoring urban expansion, disaster assessment, and resource management, offering timely, accurate, and large-scale insights into dynamic landscape transformations. While deep learning has revolutionized change detection, the increasing complexity and computational demands of modern models have not necessarily translated into significant accuracy gains. Instead of following this trend, this study explores a more efficient approach, focusing on lightweight models that maintain high accuracy while minimizing resource consumption, which is an essential requirement for on-satellite processing. To this end, we propose FlickCD, which means quick flick then get great results, pushing the boundaries of the performance-resource trade-off. FlickCD introduces an Enhanced Difference Module (EDM) to amplify critical feature differences between temporal phases while suppressing irrelevant variations such as lighting and weather changes, thereby reducing computational costs in the subsequent change decoder. Additionally, the FlickCD decoder incorporates Local-Global Fusion Blocks, leveraging Shifted Window Self-Attention (SWSA) and Enhanced Global Self-Attention (EGSA) to efficiently capture semantic information at multiple scales, preserving both coarse- and fine-grained changes. Extensive experiments on four benchmark datasets demonstrate that FlickCD reduces computational and storage overheads by more than an order of magnitude while achieving state-of-the-art (SOTA) performance or incurring only a minor (<1\% F1) accuracy trade-off. The implementation code is publicly available at https://github.com/xulsh8/FlickCD.
comment: 12 pages
☆ OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography ICCV 2025
As one of the earliest ancient languages, Oracle Bone Script (OBS) encapsulates the cultural records and intellectual expressions of ancient civilizations. Despite the discovery of approximately 4,500 OBS characters, only about 1,600 have been deciphered. The remaining undeciphered ones, with their complex structure and abstract imagery, pose significant challenges for interpretation. To address these challenges, this paper proposes a novel two-stage semantic typography framework, named OracleFusion. In the first stage, this approach leverages the Multimodal Large Language Model (MLLM) with enhanced Spatial Awareness Reasoning (SAR) to analyze the glyph structure of the OBS character and perform visual localization of key components. In the second stage, we introduce Oracle Structural Vector Fusion (OSVF), incorporating glyph structure constraints and glyph maintenance constraints to ensure the accurate generation of semantically enriched vector fonts. This approach preserves the objective integrity of the glyph structure, offering visually enhanced representations that assist experts in deciphering OBS. Extensive qualitative and quantitative experiments demonstrate that OracleFusion outperforms state-of-the-art baseline models in terms of semantics, visual appeal, and glyph maintenance, significantly enhancing both readability and aesthetic quality. Furthermore, OracleFusion provides expert-like insights on unseen oracle characters, making it a valuable tool for advancing the decipherment of OBS.
comment: Accepted to ICCV 2025
☆ ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching
Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models that deliver high accuracy while operating in real-time continues to be a major challenge in computer vision. In the domain of cost-volume-based stereo matching, accurate disparity estimation depends heavily on large-scale cost volumes. However, such large volumes store substantial redundant information and also require computationally intensive aggregation units for processing and regression, making real-time performance unattainable. Conversely, small-scale cost volumes followed by lightweight aggregation units provide a promising route for real-time performance, but lack sufficient information to ensure highly accurate disparity estimation. To address this challenge, we propose the Enhanced Shuffle Mixer (ESM) to mitigate information loss associated with small-scale cost volumes. ESM restores critical details by integrating primary features into the disparity upsampling unit. It quickly extracts features from the initial disparity estimation and fuses them with image features. These features are mixed by shuffling and layer splitting then refined through a compact feature-guided hourglass network to recover more detailed scene geometry. The ESM focuses on local contextual connectivity with a large receptive field and low computational cost, leading to the reconstruction of a highly accurate disparity map at real-time. The compact version of ESMStereo achieves an inference speed of 116 FPS on high-end GPUs and 91 FPS on the AGX Orin.
comment: Under peer review
☆ EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception ICCV 2025
Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment, especially in resource-constrained environments. In this paper, we introduce EgoAdapt, a framework that adaptively performs cross-modal distillation and policy learning to enable efficient inference across different egocentric perception tasks, including egocentric action recognition, active speaker localization, and behavior anticipation. Our proposed policy module is adaptable to task-specific action spaces, making it broadly applicable. Experimental results on three challenging egocentric datasets EPIC-Kitchens, EasyCom, and Aria Everyday Activities demonstrate that our method significantly enhances efficiency, reducing GMACs by up to 89.09%, parameters up to 82.02%, and energy up to 9.6x, while still on-par and in many cases outperforming, the performance of corresponding state-of-the-art models.
comment: Accepted at ICCV 2025
☆ PoseMaster: Generating 3D Characters in Arbitrary Poses from a Single Image
3D characters play a crucial role in our daily entertainment. To improve the efficiency of 3D character modeling, recent image-based methods use two separate models to achieve pose standardization and 3D reconstruction of the A-pose character. However, these methods are prone to generating distorted and degraded images in the pose standardization stage due to self-occlusion and viewpoints, which further affects the geometric quality of the subsequent reconstruction process. To tackle these problems, we propose PoseMaster, an end-to-end controllable 3D character generation framework. Specifically, we unify pose transformation and 3D character generation into a flow-based 3D native generation framework. To achieve accurate arbitrary-pose control, we propose to leverage the 3D body bones existing in the skeleton of an animatable character as the pose condition. Furthermore, considering the specificity of multi-condition control, we randomly empty the pose condition and the image condition during training to improve the effectiveness and generalizability of pose control. Finally, we create a high-quality pose-control dataset derived from realistic character animation data to make the model learning the implicit relationships between skeleton and skinning weights. Extensive experiments show that PoseMaster outperforms current state-of-the-art techniques in both qualitative and quantitative evaluations for A-pose character generation while demonstrating its powerful ability to achieve precise control for arbitrary poses.
☆ SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification
Retrieving 3D objects in complex indoor environments using only a masked 2D image and a natural language description presents significant challenges. The ROOMELSA challenge limits access to full 3D scene context, complicating reasoning about object appearance, geometry, and semantics. These challenges are intensified by distorted viewpoints, textureless masked regions, ambiguous language prompts, and noisy segmentation masks. To address this, we propose SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification. SAMURAI integrates CLIP-based semantic matching with shape-guided re-ranking derived from binary silhouettes of masked regions, alongside a robust majority voting strategy. A dedicated preprocessing pipeline enhances mask quality by extracting the largest connected component and removing background noise. Our hybrid retrieval framework leverages both language and shape cues, achieving competitive performance on the ROOMELSA private test set. These results highlight the importance of combining shape priors with language understanding for robust open-world 3D object retrieval.
☆ Class-Agnostic Region-of-Interest Matching in Document Images ICDAR2025
Document understanding and analysis have received a lot of attention due to their widespread application. However, existing document analysis solutions, such as document layout analysis and key information extraction, are only suitable for fixed category definitions and granularities, and cannot achieve flexible applications customized by users. Therefore, this paper defines a new task named ``Class-Agnostic Region-of-Interest Matching'' (``RoI-Matching'' for short), which aims to match the customized regions in a flexible, efficient, multi-granularity, and open-set manner. The visual prompt of the reference document and target document images are fed into our model, while the output is the corresponding bounding boxes in the target document images. To meet the above requirements, we construct a benchmark RoI-Matching-Bench, which sets three levels of difficulties following real-world conditions, and propose the macro and micro metrics to evaluate. Furthermore, we also propose a new framework RoI-Matcher, which employs a siamese network to extract multi-level features both in the reference and target domains, and cross-attention layers to integrate and align similar semantics in different domains. Experiments show that our method with a simple procedure is effective on RoI-Matching-Bench, and serves as the baseline for further research. The code is available at https://github.com/pd162/RoI-Matching.
comment: Accepted by ICDAR2025
☆ Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features ICCV 2025
The ability of deep neural networks (DNNs) come from extracting and interpreting features from the data provided. By exploiting intermediate features in DNNs instead of relying on hard labels, we craft adversarial perturbation that generalize more effectively, boosting black-box transferability. These features ubiquitously come from supervised learning in previous work. Inspired by the exceptional synergy between self-supervised learning and the Transformer architecture, this paper explores whether exploiting self-supervised Vision Transformer (ViT) representations can improve adversarial transferability. We present dSVA -- a generative dual self-supervised ViT features attack, that exploits both global structural features from contrastive learning (CL) and local textural features from masked image modeling (MIM), the self-supervised learning paradigm duo for ViTs. We design a novel generative training framework that incorporates a generator to create black-box adversarial examples, and strategies to train the generator by exploiting joint features and the attention mechanism of self-supervised ViTs. Our findings show that CL and MIM enable ViTs to attend to distinct feature tendencies, which, when exploited in tandem, boast great adversarial generalizability. By disrupting dual deep features distilled by self-supervised ViTs, we are rewarded with remarkable black-box transferability to models of various architectures that outperform state-of-the-arts. Code available at https://github.com/spencerwooo/dSVA.
comment: 14 pages, 9 figures, to appear in ICCV 2025
☆ Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling
Text-guided diffusion models have become essential for high-quality image synthesis, enabling dynamic image editing. In image editing, two crucial aspects are editability, which determines the extent of modification, and faithfulness, which reflects how well unaltered elements are preserved. However, achieving optimal results is challenging because of the inherent trade-off between editability and faithfulness. To address this, we propose Faithfulness Guidance and Scheduling (FGS), which enhances faithfulness with minimal impact on editability. FGS incorporates faithfulness guidance to strengthen the preservation of input image information and introduces a scheduling strategy to resolve misalignment between editability and faithfulness. Experimental results demonstrate that FGS achieves superior faithfulness while maintaining editability. Moreover, its compatibility with various editing methods enables precise, high-quality image edits across diverse tasks.
comment: preprint
☆ Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability ICCV2025
Detectors often suffer from performance drop due to domain gap between training and testing data. Recent methods explore diffusion models applied to domain generalization (DG) and adaptation (DA) tasks, but still struggle with large inference costs and have not yet fully leveraged the capabilities of diffusion models. We propose to tackle these problems by extracting intermediate features from a single-step diffusion process, improving feature collection and fusion to reduce inference time by 75% while enhancing performance on source domains (i.e., Fitness). Then, we construct an object-centered auxiliary branch by applying box-masked images with class prompts to extract robust and domain-invariant features that focus on object. We also apply consistency loss to align the auxiliary and ordinary branch, balancing fitness and generalization while preventing overfitting and improving performance on target domains (i.e., Generalization). Furthermore, within a unified framework, standard detectors are guided by diffusion detectors through feature-level and object-level alignment on source domains (for DG) and unlabeled target domains (for DA), thereby improving cross-domain detection performance (i.e., Transferability). Our method achieves competitive results on 3 DA benchmarks and 5 DG benchmarks. Additionally, experiments on COCO generalization benchmark demonstrate that our method maintains significant advantages and show remarkable efficiency in large domain shifts and low-data scenarios. Our work shows the superiority of applying diffusion models to domain generalized and adaptive detection tasks and offers valuable insights for visual perception tasks across diverse domains. The code is available at \href{https://github.com/heboyong/Fitness-Generalization-Transferability}{Fitness-Generalization-Transferability}.
comment: Accepted by ICCV2025. arXiv admin note: text overlap with arXiv:2503.02101
☆ V2X-REALM: Vision-Language Model-Based Robust End-to-End Cooperative Autonomous Driving with Adaptive Long-Tail Modeling
Ensuring robust planning and decision-making under rare, diverse, and visually degraded long-tail scenarios remains a fundamental challenge for autonomous driving in urban environments. This issue becomes more critical in cooperative settings, where vehicles and infrastructure jointly perceive and reason across complex environments. To address this challenge, we propose V2X-REALM, a vision-language model (VLM)-based framework with adaptive multimodal learning for robust cooperative autonomous driving under long-tail scenarios. V2X-REALM introduces three core innovations: (i) a prompt-driven long-tail scenario generation and evaluation pipeline that leverages foundation models to synthesize realistic long-tail conditions such as snow and fog across vehicle- and infrastructure-side views, enriching training diversity efficiently; (ii) a gated multi-scenario adaptive attention module that modulates the visual stream using scenario priors to recalibrate ambiguous or corrupted features; and (iii) a multi-task scenario-aware contrastive learning objective that improves multimodal alignment and promotes cross-scenario feature separability. Extensive experiments demonstrate that V2X-REALM significantly outperforms existing baselines in robustness, semantic reasoning, safety, and planning accuracy under complex, challenging driving conditions, advancing the scalability of end-to-end cooperative autonomous driving.
☆ RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment ICCV 2025
Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain substantial redundancies, prompting the need for more data-efficient training paradigms. Data selection has shown promise to mitigate redundancy by identifying the most representative samples, thereby reducing training costs without compromising performance. Existing methods typically rely on static scoring metrics or pretrained models, overlooking the combined effect of selected samples and their evolving dynamics during training. We introduce the concept of epsilon-sample cover, which quantifies sample redundancy based on inter-sample relationships, capturing the intrinsic structure of the dataset. Based on this, we reformulate data selection as a reinforcement learning (RL) process and propose RL-Selector, where a lightweight RL agent optimizes the selection policy by leveraging epsilon-sample cover derived from evolving dataset distribution as a reward signal. Extensive experiments across benchmark datasets and diverse architectures demonstrate that our method consistently outperforms existing state-of-the-art baselines. Models trained with our selected datasets show enhanced generalization performance with improved training efficiency.
comment: ICCV 2025
☆ DidSee: Diffusion-Based Depth Completion for Material-Agnostic Robotic Perception and Manipulation
Commercial RGB-D cameras often produce noisy, incomplete depth maps for non-Lambertian objects. Traditional depth completion methods struggle to generalize due to the limited diversity and scale of training data. Recent advances exploit visual priors from pre-trained text-to-image diffusion models to enhance generalization in dense prediction tasks. However, we find that biases arising from training-inference mismatches in the vanilla diffusion framework significantly impair depth completion performance. Additionally, the lack of distinct visual features in non-Lambertian regions further hinders precise prediction. To address these issues, we propose \textbf{DidSee}, a diffusion-based framework for depth completion on non-Lambertian objects. First, we integrate a rescaled noise scheduler enforcing a zero terminal signal-to-noise ratio to eliminate signal leakage bias. Second, we devise a noise-agnostic single-step training formulation to alleviate error accumulation caused by exposure bias and optimize the model with a task-specific loss. Finally, we incorporate a semantic enhancer that enables joint depth completion and semantic segmentation, distinguishing objects from backgrounds and yielding precise, fine-grained depth maps. DidSee achieves state-of-the-art performance on multiple benchmarks, demonstrates robust real-world generalization, and effectively improves downstream tasks such as category-level pose estimation and robotic grasping.Project page: https://wenzhoulyu.github.io/DidSee/
☆ Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation
Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent spaces have reduced the number of tokens required by eliminating the need for a 2D grid structure. In this paper, we further advance compact discrete image representation by introducing 1D binary image latents. By representing each image as a sequence of binary vectors, rather than using traditional one-hot codebook tokens, our approach preserves high-resolution details while maintaining the compactness of 1D latents. To the best of our knowledge, our text-to-image models are the first to achieve competitive performance in both diffusion and auto-regressive generation using just 128 discrete tokens for images up to 1024x1024, demonstrating up to a 32-fold reduction in token numbers compared to standard VQ-VAEs. The proposed 1D binary latent space, coupled with simple model architectures, achieves marked improvements in speed training and inference speed. Our text-to-image models allow for a global batch size of 4096 on a single GPU node with 8 AMD MI300X GPUs, and the training can be completed within 200 GPU days. Our models achieve competitive performance compared to modern image generation models without any in-house private training data or post-training refinements, offering a scalable and efficient alternative to conventional tokenization methods.
☆ LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection
Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a new fusion detection baseline that uses a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. Based on this approach, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet), which introduces a novel attention-guided self-modulation feature fusion (ASFF) module that adaptively adjusts the responses of fusion features at both global and local levels based on attention information from different modalities, thereby promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that, compared to state-of-the-art methods, our approach achieves a favorable efficiency-accuracy trade-off, reducing the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy (mAP) by 1%-3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet.
☆ Multimodal Prompt Alignment for Facial Expression Recognition ICCV2025
Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs) like CLIP for various downstream tasks. Despite their success, current VLM-based facial expression recognition (FER) methods struggle to capture fine-grained textual-visual relationships, which are essential for distinguishing subtle differences between facial expressions. To address this challenge, we propose a multimodal prompt alignment framework for FER, called MPA-FER, that provides fine-grained semantic guidance to the learning process of prompted visual features, resulting in more precise and interpretable representations. Specifically, we introduce a multi-granularity hard prompt generation strategy that utilizes a large language model (LLM) like ChatGPT to generate detailed descriptions for each facial expression. The LLM-based external knowledge is injected into the soft prompts by minimizing the feature discrepancy between the soft prompts and the hard prompts. To preserve the generalization abilities of the pretrained CLIP model, our approach incorporates prototype-guided visual feature alignment, ensuring that the prompted visual features from the frozen image encoder align closely with class-specific prototypes. Additionally, we propose a cross-modal global-local alignment module that focuses on expression-relevant facial features, further improving the alignment between textual and visual features. Extensive experiments demonstrate our framework outperforms state-of-the-art methods on three FER benchmark datasets, while retaining the benefits of the pretrained model and minimizing computational costs.
comment: To appear in ICCV2025
☆ HybridQ: Hybrid Classical-Quantum Generative Adversarial Network for Skin Disease Image Generation
Machine learning-assisted diagnosis is gaining traction in skin disease detection, but training effective models requires large amounts of high-quality data. Skin disease datasets often suffer from class imbalance, privacy concerns, and object bias, making data augmentation essential. While classical generative models are widely used, they demand extensive computational resources and lengthy training time. Quantum computing offers a promising alternative, but existing quantum-based image generation methods can only yield grayscale low-quality images. Through a novel classical-quantum latent space fusion technique, our work overcomes this limitation and introduces the first classical-quantum generative adversarial network (GAN) capable of generating color medical images. Our model outperforms classical deep convolutional GANs and existing hybrid classical-quantum GANs in both image generation quality and classification performance boost when used as data augmentation. Moreover, the performance boost is comparable with that achieved using state-of-the-art classical generative models, yet with over 25 times fewer parameters and 10 times fewer training epochs. Such results suggest a promising future for quantum image generation as quantum hardware advances. Finally, we demonstrate the robust performance of our model on real IBM quantum machine with hardware noise.
☆ FedSC: Federated Learning with Semantic-Aware Collaboration KDD 2025
Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving. However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at multiple clients. A number of existing FL methods attempt to tackle data heterogeneity locally (e.g., regularizing local models) or globally (e.g., fine-tuning global model), often neglecting inherent semantic information contained in each client. To explore the possibility of using intra-client semantically meaningful knowledge in handling data heterogeneity, in this paper, we propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients. The core idea of FedSC is to construct relational prototypes and consistent prototypes at semantic-level, aiming to provide fruitful class underlying knowledge and stable convergence signals in a prototype-wise collaborative way. On the one hand, FedSC introduces an inter-contrastive learning strategy to bring instance-level embeddings closer to relational prototypes with the same semantics and away from distinct classes. On the other hand, FedSC devises consistent prototypes via a discrepancy aggregation manner, as a regularization penalty to constrain the optimization region of the local model. Moreover, a theoretical analysis for FedSC is provided to ensure a convergence guarantee. Experimental results on various challenging scenarios demonstrate the effectiveness of FedSC and the efficiency of crucial components.
comment: 12 pages, KDD 2025
☆ Bridging Video Quality Scoring and Justification via Large Multimodal Models
Classical video quality assessment (VQA) methods generate a numerical score to judge a video's perceived visual fidelity and clarity. Yet, a score fails to describe the video's complex quality dimensions, restricting its applicability. Benefiting from the linguistic output, adapting video large multimodal models (LMMs) to VQA via instruction tuning has the potential to address this issue. The core of the approach lies in the video quality-centric instruction data. Previous explorations mainly focus on the image domain, and their data generation processes heavily rely on human quality annotations and proprietary systems, limiting data scalability and effectiveness. To address these challenges, we propose the Score-based Instruction Generation (SIG) pipeline. Specifically, SIG first scores multiple quality dimensions of an unlabeled video and maps scores to text-defined levels. It then explicitly incorporates a hierarchical Chain-of-Thought (CoT) to model the correlation between specific dimensions and overall quality, mimicking the human visual system's reasoning process. The automated pipeline eliminates the reliance on expert-written quality descriptions and proprietary systems, ensuring data scalability and generation efficiency. To this end, the resulting Score2Instruct (S2I) dataset contains over 320K diverse instruction-response pairs, laying the basis for instruction tuning. Moreover, to advance video LMMs' quality scoring and justification abilities simultaneously, we devise a progressive tuning strategy to fully unleash the power of S2I. Built upon SIG, we further curate a benchmark termed S2I-Bench with 400 open-ended questions to better evaluate the quality justification capacity of video LMMs. Experimental results on the S2I-Bench and existing benchmarks indicate that our method consistently improves quality scoring and justification capabilities across multiple video LMMs.
comment: 15 pages, 4 figures, 8 tables
☆ User-in-the-Loop View Sampling with Error Peaking Visualization ICIP 2025
Augmented reality (AR) provides ways to visualize missing view samples for novel view synthesis. Existing approaches present 3D annotations for new view samples and task users with taking images by aligning the AR display. This data collection task is known to be mentally demanding and limits capture areas to pre-defined small areas due to the ideal but restrictive underlying sampling theory. To free users from 3D annotations and limited scene exploration, we propose using locally reconstructed light fields and visualizing errors to be removed by inserting new views. Our results show that the error-peaking visualization is less invasive, reduces disappointment in final results, and is satisfactory with fewer view samples in our mobile view synthesis system. We also show that our approach can contribute to recent radiance field reconstruction for larger scenes, such as 3D Gaussian splatting.
comment: Accepted at IEEE ICIP 2025, Project Page: https://mediated-reality.github.io/projects/yasunaga_icip25/
☆ The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
We introduce the Aging Multiverse, a framework for generating multiple plausible facial aging trajectories from a single image, each conditioned on external factors such as environment, health, and lifestyle. Unlike prior methods that model aging as a single deterministic path, our approach creates an aging tree that visualizes diverse futures. To enable this, we propose a training-free diffusion-based method that balances identity preservation, age accuracy, and condition control. Our key contributions include attention mixing to modulate editing strength and a Simulated Aging Regularization strategy to stabilize edits. Extensive experiments and user studies demonstrate state-of-the-art performance across identity preservation, aging realism, and conditional alignment, outperforming existing editing and age-progression models, which often fail to account for one or more of the editing criteria. By transforming aging into a multi-dimensional, controllable, and interpretable process, our approach opens up new creative and practical avenues in digital storytelling, health education, and personalized visualization.
☆ Detection of Breast Cancer Lumpectomy Margin with SAM-incorporated Forward-Forward Contrastive Learning
Complete removal of cancer tumors with a negative specimen margin during lumpectomy is essential in reducing breast cancer recurrence. However, 2D specimen radiography (SR), the current method used to assess intraoperative specimen margin status, has limited accuracy, resulting in nearly a quarter of patients requiring additional surgery. To address this, we propose a novel deep learning framework combining the Segment Anything Model (SAM) with Forward-Forward Contrastive Learning (FFCL), a pre-training strategy leveraging both local and global contrastive learning for patch-level classification of SR images. After annotating SR images with regions of known maligancy, non-malignant tissue, and pathology-confirmed margins, we pre-train a ResNet-18 backbone with FFCL to classify margin status, then reconstruct coarse binary masks to prompt SAM for refined tumor margin segmentation. Our approach achieved an AUC of 0.8455 for margin classification and segmented margins with a 27.4% improvement in Dice similarity over baseline models, while reducing inference time to 47 milliseconds per image. These results demonstrate that FFCL-SAM significantly enhances both the speed and accuracy of intraoperative margin assessment, with strong potential to reduce re-excision rates and improve surgical outcomes in breast cancer treatment. Our code is available at https://github.com/tbwa233/FFCL-SAM/.
comment: 19 pages, 7 figures, 3 tables
☆ VisionGuard: Synergistic Framework for Helmet Violation Detection
Enforcing helmet regulations among motorcyclists is essential for enhancing road safety and ensuring the effectiveness of traffic management systems. However, automatic detection of helmet violations faces significant challenges due to environmental variability, camera angles, and inconsistencies in the data. These factors hinder reliable detection of motorcycles and riders and disrupt consistent object classification. To address these challenges, we propose VisionGuard, a synergistic multi-stage framework designed to overcome the limitations of frame-wise detectors, especially in scenarios with class imbalance and inconsistent annotations. VisionGuard integrates two key components: Adaptive Labeling and Contextual Expander modules. The Adaptive Labeling module is a tracking-based refinement technique that enhances classification consistency by leveraging a tracking algorithm to assign persistent labels across frames and correct misclassifications. The Contextual Expander module improves recall for underrepresented classes by generating virtual bounding boxes with appropriate confidence scores, effectively addressing the impact of data imbalance. Experimental results show that VisionGuard improves overall mAP by 3.1% compared to baseline detectors, demonstrating its effectiveness and potential for real-world deployment in traffic surveillance systems, ultimately promoting safety and regulatory compliance.
☆ Inverse Scene Text Removal
Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects text regions and theninpaints them. Although STR has advanced through neural networksand synthetic data, misuse risks have increased. This paper investi-gates Inverse STR (ISTR), which analyzes STR-processed images andfocuses on binary classification (detecting whether an image has un-dergone STR) and localizing removed text regions. We demonstrate inexperiments that these tasks are achievable with high accuracies, en-abling detection of potential misuse and improving STR. We also at-tempt to recover the removed text content by training a text recognizerto understand its difficulty.
comment: 17 pages
☆ Style-Aligned Image Composition for Robust Detection of Abnormal Cells in Cytopathology
Challenges such as the lack of high-quality annotations, long-tailed data distributions, and inconsistent staining styles pose significant obstacles to training neural networks to detect abnormal cells in cytopathology robustly. This paper proposes a style-aligned image composition (SAIC) method that composes high-fidelity and style-preserved pathological images to enhance the effectiveness and robustness of detection models. Without additional training, SAIC first selects an appropriate candidate from the abnormal cell bank based on attribute guidance. Then, it employs a high-frequency feature reconstruction to achieve a style-aligned and high-fidelity composition of abnormal cells and pathological backgrounds. Finally, it introduces a large vision-language model to filter high-quality synthesis images. Experimental results demonstrate that incorporating SAIC-synthesized images effectively enhances the performance and robustness of abnormal cell detection for tail categories and styles, thereby improving overall detection performance. The comprehensive quality evaluation further confirms the generalizability and practicality of SAIC in clinical application scenarios. Our code will be released at https://github.com/Joey-Qi/SAIC.
comment: MIDL 2025 Oral
☆ DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting CVPR
Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Existing novel view synthesis methods are often constrained by their reliance on high-resolution images or strong assumptions about static geometry and rigid scene priors. Consequently, their approaches lack robustness in real-world environments with dynamic object and camera motion, leading to instability and degraded visual fidelity. To address this, we propose Motion-aware Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting (DBMovi-GS), a method designed for dynamic view synthesis from blurry monocular videos. Our model generates dense 3D Gaussians, restoring sharpness from blurry videos and reconstructing detailed 3D geometry of the scene affected by dynamic motion variations. Our model achieves robust performance in novel view synthesis under dynamic blurry scenes and sets a new benchmark in realistic novel view synthesis for blurry monocular video inputs.
comment: CVPRW 2025, Neural Fields Beyond Conventional Cameras
♻ ☆ TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography
Music-driven dance generation has garnered significant attention due to its wide range of industrial applications, particularly in the creation of group choreography. During the group dance generation process, however, most existing methods still face three primary issues: multi-dancer collisions, single-dancer foot sliding and abrupt swapping in the generation of long group dance. In this paper, we propose TCDiff++, a music-driven end-to-end framework designed to generate harmonious group dance. Specifically, to mitigate multi-dancer collisions, we utilize a dancer positioning embedding to better maintain the relative positioning among dancers. Additionally, we incorporate a distance-consistency loss to ensure that inter-dancer distances remain within plausible ranges. To address the issue of single-dancer foot sliding, we introduce a swap mode embedding to indicate dancer swapping patterns and design a Footwork Adaptor to refine raw motion, thereby minimizing foot sliding. For long group dance generation, we present a long group diffusion sampling strategy that reduces abrupt position shifts by injecting positional information into the noisy input. Furthermore, we integrate a Sequence Decoder layer to enhance the model's ability to selectively process long sequences. Extensive experiments demonstrate that our TCDiff++ achieves state-of-the-art performance, particularly in long-duration scenarios, ensuring high-quality and coherent group dance generation.
♻ ☆ Towards Scalable and Generalizable Earth Observation Data Mining via Foundation Model Composition
Foundation models are rapidly transforming Earth Observation data mining by enabling generalizable and scalable solutions for key tasks such as scene classification and semantic segmentation. While most efforts in the geospatial domain have focused on developing large models trained from scratch using massive Earth Observation datasets, an alternative strategy that remains underexplored is the reuse and combination of existing pretrained models. In this study, we investigate whether foundation models pretrained on remote sensing and general vision datasets can be effectively combined to improve performance across a diverse set of key Earth Observation tasks. Using the GEO-Bench benchmark, we evaluate several prominent models, including Prithvi, Hiera, and DOFA, on eleven datasets covering a range of spatial resolutions, sensor modalities, and task types. The results show that feature-level ensembling of smaller pretrained models can match or exceed the performance of much larger models, while requiring less training time and computational resources. Moreover, the study highlights the potential of applying knowledge distillation to transfer the strengths of ensembles into more compact models, offering a practical path for deploying foundation models in real-world Earth Observation applications.
♻ ☆ Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception IROS 2025
Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high uncertainty. Even though object pose estimation improves and uncertainty quantification research continues to make strides, few studies have connected them to the downstream task of robotic grasping. We propose a method for training lightweight, deep networks to predict whether a grasp guided by an image-based pose estimate will succeed before that grasp is attempted. We generate training data for our networks via object pose estimation on real images and simulated grasping. We also find that, despite high object variability in grasping trials, networks benefit from training on all objects jointly, suggesting that a diverse variety of objects can nevertheless contribute to the same goal.
comment: Accepted to IROS 2025
♻ ☆ Learning to Be a Transformer to Pinpoint Anomalies
To efficiently deploy strong, often pre-trained feature extractors, recent Industrial Anomaly Detection and Segmentation (IADS) methods process low-resolution images, e.g., 224x224 pixels, obtained by downsampling the original input images. However, while numerous industrial applications demand the identification of both large and small defects, downsampling the input image to a low resolution may hinder a method's ability to pinpoint tiny anomalies. We propose a novel Teacher--Student paradigm to leverage strong pre-trained features while processing high-resolution input images very efficiently. The core idea concerns training two shallow MLPs (the Students) by nominal images so as to mimic the mappings between the patch embeddings induced by the self-attention layers of a frozen vision Transformer (the Teacher). Indeed, learning these mappings sets forth a challenging pretext task that small-capacity models are unlikely to accomplish on out-of-distribution data such as anomalous images. Our method can spot anomalies from high-resolution images and runs way faster than competitors, achieving state-of-the-art performance on MVTec AD and the best segmentation results on VisA. We also propose novel evaluation metrics to capture robustness to defect size, i.e., the ability to preserve good localisation from large anomalies to tiny ones. Evaluating our method also by these metrics reveals its neatly superior performance.
comment: Accepted at IEEE Access
♻ ☆ CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequences ICCV2025
We introduce Canonical Consolidation Fields (CanFields). This novel method interpolates arbitrary-length sequences of independently sampled 3D point clouds into a unified, continuous, and coherent deforming shape. Unlike prior methods that oversmooth geometry or produce topological and geometric artifacts, CanFields optimizes fine-detailed geometry and deformation jointly in an unsupervised fitting with two novel bespoke modules. First, we introduce a dynamic consolidator module that adjusts the input and assigns confidence scores, balancing the optimization of the canonical shape and its motion. Second, we represent the motion as a diffeomorphic flow parameterized by a smooth velocity field. We have validated our robustness and accuracy on more than 50 diverse sequences, demonstrating its superior performance even with missing regions, noisy raw scans, and sparse data. Our project page is at: https://wangmiaowei.github.io/CanFields.github.io/.
comment: ICCV2025 Accepted
♻ ☆ SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model
With the rapid advancement of autonomous driving technology, a lack of data has become a major obstacle to enhancing perception model accuracy. Researchers are now exploring controllable data generation using world models to diversify datasets. However, previous work has been limited to studying image generation quality on specific public datasets. There is still relatively little research on how to build data generation engines for real-world application scenes to achieve large-scale data generation for challenging scenes. In this paper, a simulator-conditioned scene generation engine based on world model is proposed. By constructing a simulation system consistent with real-world scenes, simulation data and labels, which serve as the conditions for data generation in the world model, for any scenes can be collected. It is a novel data generation pipeline by combining the powerful scene simulation capabilities of the simulation engine with the robust data generation capabilities of the world model. In addition, a benchmark with proportionally constructed virtual and real data, is provided for exploring the capabilities of world models in real-world scenes. Quantitative results show that these generated images significantly improve downstream perception models performance. Finally, we explored the generative performance of the world model in urban autonomous driving scenarios. All the data and code will be available at https://github.com/Li-Zn-H/SimWorld.
comment: 8 pages, 4 figures
♻ ☆ Chain-of-Sketch: Enabling Global Visual Reasoning
Modern vision models have achieved remarkable success in benchmarks where local features provide critical information about the target. There is now a growing interest in tackling tasks requiring more global reasoning, where local features do not provide significant information. Minsky and Papert put forward such tasks in 1969 with their connectivity study, exposing the limitations of the perceptron model. In this paper, we introduce an expanded set of global visual datasets involving graphs, strings, mazes, and image grids. We show that large vision models still struggle to learn these tasks efficiently. Similarly, state-of-the-art multi-modal LLMs perform poorly on these datasets. We explain this learning inefficiency by means of the 'globality degree' measure. To mitigate this, we propose a method called chain-of-sketch (CoS). Similar to the chain-of-thought and scratchpad techniques used in language models, CoS breaks the original task into intermediate visual steps to help learn a complex task. In addition, we show that not all CoS strategies perform equally well. Our key insight is to impose a Markovian structure on the CoS frames. This leads to the introduction of 'inductive CoS' which achieves better out-of-distribution generalization and performs well even with smaller models compared to non-inductive variants.
comment: additional experiments added, title changed from "Visual Scratchpads: Enabling Global Reasoning in Vision" to "Chain-of-Sketch: Enabling Global Visual Reasoning"
♻ ☆ QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning ICCV 2025
The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on this approach, we further distinguish two critical types of quantized layers: those responsible for retaining essential temporal information and those particularly sensitive to bit-width reduction. By selectively finetuning these layers under both local and global supervision, we mitigate performance degradation while enhancing quantization efficiency. Our method demonstrates its efficacy across three high-resolution image generation tasks, obtaining state-of-the-art performance across multiple bit-width settings.
comment: ICCV 2025. Code is available at https://github.com/hatchetProject/QuEST
♻ ☆ AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration ICCV 2025
We present AnyCalib, a method for calibrating the intrinsic parameters of a camera from a single in-the-wild image, that is agnostic to the camera model. Current methods are predominantly tailored to specific camera models and/or require extrinsic cues, such as the direction of gravity, to be visible in the image. In contrast, we argue that the perspective and distortion cues inherent in images are sufficient for model-agnostic camera calibration. To demonstrate this, we frame the calibration process as the regression of the rays corresponding to each pixel. We show, for the first time, that this intermediate representation allows for a closed-form recovery of the intrinsics for a wide range of camera models, including but not limited to: pinhole, Brown-Conrady and Kannala-Brandt. Our approach also applies to edited -- cropped and stretched -- images. Experimentally, we demonstrate that AnyCalib consistently outperforms alternative methods, including 3D foundation models, despite being trained on orders of magnitude less data. Code is available at https://github.com/javrtg/AnyCalib.
comment: Accepted to ICCV 2025
♻ ☆ EgoM2P: Egocentric Multimodal Multitask Pretraining ICCV 2025
Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction, enabling systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mounted camera trajectories, is often infeasible, making standard supervised learning approaches difficult to scale. Furthermore, dynamic camera motion and the complex temporal and spatial structure of first-person video pose additional challenges for the direct application of existing multimodal foundation models. To address these challenges, we introduce a set of efficient temporal tokenizers and propose EgoM2P, a masked modeling framework that learns from temporally-aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding. This unified design supports multitasking across diverse egocentric perception and synthesis tasks, including gaze prediction, egocentric camera tracking, and monocular depth estimation from egocentric video, and also serves as a generative model for conditional egocentric video synthesis. Across these tasks, EgoM2P matches or outperforms specialist models while being an order of magnitude faster. We will fully open-source EgoM2P to support the community and advance egocentric vision research. Project page: https://egom2p.github.io/.
comment: Accepted by ICCV 2025
♻ ☆ Fake it till You Make it: Reward Modeling as Discriminative Prediction
An effective reward model plays a pivotal role in reinforcement learning for post-training enhancement of visual generative models. However, current approaches of reward modeling suffer from implementation complexity due to their reliance on extensive human-annotated preference data or meticulously engineered quality dimensions that are often incomplete and engineering-intensive. Inspired by adversarial training in generative adversarial networks (GANs), this paper proposes GAN-RM, an efficient reward modeling framework that eliminates manual preference annotation and explicit quality dimension engineering. Our method trains the reward model through discrimination between a small set of representative, unpaired target samples(denoted as Preference Proxy Data) and model-generated ordinary outputs, requiring only a few hundred target samples. Comprehensive experiments demonstrate our GAN-RM's effectiveness across multiple key applications including test-time scaling implemented as Best-of-N sample filtering, post-training approaches like Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO). Code and data will be released at https://github.com/Visualignment/GAN-RM.
♻ ☆ Materialist: Physically Based Editing Using Single-Image Inverse Rendering
Achieving physically consistent image editing remains a significant challenge in computer vision. Existing image editing methods typically rely on neural networks, which struggle to accurately handle shadows and refractions. Conversely, physics-based inverse rendering often requires multi-view optimization, limiting its practicality in single-image scenarios. In this paper, we propose Materialist, a method combining a learning-based approach with physically based progressive differentiable rendering. Given an image, our method leverages neural networks to predict initial material properties. Progressive differentiable rendering is then used to optimize the environment map and refine the material properties with the goal of closely matching the rendered result to the input image. Our approach enables a range of applications, including material editing, object insertion, and relighting, while also introducing an effective method for editing material transparency without requiring full scene geometry. Furthermore, Our envmap estimation method also achieves state-of-the-art performance, further enhancing the accuracy of image editing task. Experiments demonstrate strong performance across synthetic and real-world datasets, excelling even on challenging out-of-domain images. Project website: https://lez-s.github.io/materialist_project/
comment: Add acknowledgements, more authors and more results. Project website: https://lez-s.github.io/materialist_project/
♻ ☆ DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection ICCV 2025
Out-of-distribution (OOD) detection holds significant importance across many applications. While semantic and domain-shift OOD problems are well-studied, this work focuses on covariate shifts - subtle variations in the data distribution that can degrade machine learning performance. We hypothesize that detecting these subtle shifts can improve our understanding of in-distribution boundaries, ultimately improving OOD detection. In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics - a property we exploit for OOD detection. We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder (VAE) framework that harnesses this mechanism. During inference, batches consist of patches from the same image, ensuring a consistent data distribution that allows the model to rely on batch statistics. DisCoPatch uses the VAE's suboptimal outputs (generated and reconstructed) as negative samples to train the discriminator, thereby improving its ability to delineate the boundary between in-distribution samples and covariate shifts. By tightening this boundary, DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks. The proposed model not only excels in detecting covariate shifts, achieving 95.5% AUROC on ImageNet-1K(-C) but also outperforms all prior methods on public Near-OOD (95.0%) benchmarks. With a compact model size of 25MB, it achieves high OOD detection performance at notably lower latency than existing methods, making it an efficient and practical solution for real-world OOD detection applications. The code is publicly available.
comment: ICCV 2025
♻ ☆ Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling ICCV 2025
Masked Image Modeling (MIM) has become an essential method for building foundational visual models in remote sensing (RS). However, the limitations in size and diversity of existing RS datasets restrict the ability of MIM methods to learn generalizable representations. Additionally, conventional MIM techniques, which require reconstructing all tokens, introduce unnecessary computational overhead. To address these issues, we present a new pre-training pipeline for RS models, featuring the creation of a large-scale RS dataset and an efficient MIM approach. We curated a high-quality dataset named \textbf{OpticalRS-13M} by collecting publicly available RS datasets and processing them through exclusion, slicing, and deduplication. OpticalRS-13M comprises 13 million optical images covering various RS tasks, such as object detection and pixel segmentation. To enhance efficiency, we propose \textbf{SelectiveMAE}, a pre-training method that dynamically encodes and reconstructs semantically rich patch tokens, thereby reducing the inefficiencies of traditional MIM models caused by redundant background pixels in RS images. Extensive experiments show that OpticalRS-13M significantly improves classification, detection, and segmentation performance, while SelectiveMAE increases training efficiency over 2$\times$ times. This highlights the effectiveness and scalability of our pipeline in developing RS foundational models. The dataset, source code, and trained models will be released at https://github.com/MiliLab/SelectiveMAE.
comment: ICCV 2025
♻ ☆ OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation
Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts. However, rapid T2I model advancements reveal limitations in early benchmarks, lacking comprehensive evaluations, for example, the evaluation on reasoning, text rendering and style. Notably, recent state-of-the-art models, with their rich knowledge modeling capabilities, show promising results on the image generation problems requiring strong reasoning ability, yet existing evaluation systems have not adequately addressed this frontier. To systematically address these gaps, we introduce OneIG-Bench, a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimensions, including prompt-image alignment, text rendering precision, reasoning-generated content, stylization, and diversity. By structuring the evaluation, this benchmark enables in-depth analysis of model performance, helping researchers and practitioners pinpoint strengths and bottlenecks in the full pipeline of image generation. Specifically, OneIG-Bench enables flexible evaluation by allowing users to focus on a particular evaluation subset. Instead of generating images for the entire set of prompts, users can generate images only for the prompts associated with the selected dimension and complete the corresponding evaluation accordingly. Our codebase and dataset are now publicly available to facilitate reproducible evaluation studies and cross-model comparisons within the T2I research community.
♻ ☆ Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models limited to in-domain views, our method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images, and formulates novel-view synthesis as an inpainting task for both image and geometry. To ensure accurate alignment between generated images and geometry, we propose cross-modal attention distillation, where attention maps from the image diffusion branch are injected into a parallel geometry diffusion branch during both training and inference. This multi-task approach achieves synergistic effects, facilitating geometrically robust image synthesis as well as well-defined geometry prediction. We further introduce proximity-based mesh conditioning to integrate depth and normal cues, interpolating between point cloud and filtering erroneously predicted geometry from influencing the generation process. Empirically, our method achieves high-fidelity extrapolative view synthesis on both image and geometry across a range of unseen scenes, delivers competitive reconstruction quality under interpolation settings, and produces geometrically aligned colored point clouds for comprehensive 3D completion. Project page is available at https://cvlab-kaist.github.io/MoAI.
comment: Project page at https://cvlab-kaist.github.io/MoAI
♻ ☆ STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
The use of Multimodal Large Language Models (MLLMs) as an end-to-end solution for Embodied AI and Autonomous Driving has become a prevailing trend. While MLLMs have been extensively studied for visual semantic understanding tasks, their ability to perform precise and quantitative spatial-temporal understanding in real-world applications remains largely unexamined, leading to uncertain prospects. To evaluate models' Spatial-Temporal Intelligence, we introduce STI-Bench, a benchmark designed to evaluate MLLMs' spatial-temporal understanding through challenging tasks such as estimating and predicting the appearance, pose, displacement, and motion of objects. Our benchmark encompasses a wide range of robot and vehicle operations across desktop, indoor, and outdoor scenarios. The extensive experiments reveals that the state-of-the-art MLLMs still struggle in real-world spatial-temporal understanding, especially in tasks requiring precise distance estimation and motion analysis.
♻ ☆ Tackling fluffy clouds: robust field boundary delineation across global agricultural landscapes with Sentinel-1 and Sentinel-2 Time Series
Accurate delineation of agricultural field boundaries is essential for effective crop monitoring and resource management. However, competing methodologies often face significant challenges, particularly in their reliance on extensive manual efforts for cloud-free data curation and limited adaptability to diverse global conditions. In this paper, we introduce PTAViT3D, a deep learning architecture specifically designed for processing three-dimensional time series of satellite imagery from either Sentinel-1 (S1) or Sentinel-2 (S2). Additionally, we present PTAViT3D-CA, an extension of the PTAViT3D model incorporating cross-attention mechanisms to fuse S1 and S2 datasets, enhancing robustness in cloud-contaminated scenarios. The proposed methods leverage spatio-temporal correlations through a memory-efficient 3D Vision Transformer architecture, facilitating accurate boundary delineation directly from raw, cloud-contaminated imagery. We comprehensively validate our models through extensive testing on various datasets, including Australia's ePaddocks - CSIRO's national agricultural field boundary product - alongside public benchmarks Fields-of-the-World, PASTIS, and AI4SmallFarms. Our results consistently demonstrate state-of-the-art performance, highlighting excellent global transferability and robustness. Crucially, our approach significantly simplifies data preparation workflows by reliably processing cloud-affected imagery, thereby offering strong adaptability across diverse agricultural environments. Our code and models are publicly available at https://github.com/feevos/tfcl.
comment: revision 1, under review
♻ ☆ Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts CVPR 2025
Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many predictions. We investigate the roles of each component in the transformer decoder across these two training targets, including self-attention, cross-attention, and feed-forward network. Our empirical results demonstrate that any independent component in the decoder can effectively learn both targets simultaneously, even when other components are shared. This finding leads us to propose a multi-route training mechanism, featuring a primary route for one-to-one prediction and two auxiliary training routes for one-to-many prediction. We propose a novel instructive self-attention mechanism, integrated into the first auxiliary route, which dynamically and flexibly guides object queries for one-to-many prediction. For the second auxiliary route, we introduce a route-aware Mixture-of-Experts (MoE) to facilitate knowledge sharing while mitigating potential conflicts between routes. Additionally, we apply an MoE to low-scale features in the encoder, optimizing the balance between efficiency and effectiveness. The auxiliary routes are discarded during inference. We conduct extensive experiments across various object detection baselines, achieving consistent improvements as demonstrated in Fig. 1. Our method is highly flexible and can be readily adapted to other tasks. To demonstrate its versatility, we conduct experiments on both instance segmentation and panoptic segmentation, further validating its effectiveness. Project page: https://visual-ai.github.io/mrdetr/
comment: Under review. Extended version of our CVPR 2025 paper, see arXiv:2412.10028v3
♻ ☆ PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters. Traditional defense mechanisms, such as adversarial training, gradient masking, and input transformations, either impose substantial computational costs or compromise the test accuracy of non-adversarial inputs. To address these challenges, we propose an efficient defense mechanism, PuriDefense, that employs random patch-wise purifications with an ensemble of lightweight purification models at a low level of inference cost. These models leverage the local implicit function and rebuild the natural image manifold. Our theoretical analysis suggests that this approach slows down the convergence of query-based attacks by incorporating randomness into purifications. Extensive experiments on CIFAR-10 and ImageNet validate the effectiveness of our proposed purifier-based defense mechanism, demonstrating significant improvements in robustness against query-based attacks.
♻ ☆ Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes
While the human visual system employs distinct mechanisms to perceive salient and camouflaged objects, existing models struggle to disentangle these tasks. Specifically, salient object detection (SOD) models frequently misclassify camouflaged objects as salient, while camouflaged object detection (COD) models conversely misinterpret salient objects as camouflaged. We hypothesize that this can be attributed to two factors: (i) the specific annotation paradigm of current SOD and COD datasets, and (ii) the lack of explicit attribute relationship modeling in current models. Prevalent SOD/COD datasets enforce a mutual exclusivity constraint, assuming scenes contain either salient or camouflaged objects, which poorly aligns with the real world. Furthermore, current SOD/COD methods are primarily designed for these highly constrained datasets and lack explicit modeling of the relationship between salient and camouflaged objects. In this paper, to promote the development of unconstrained salient and camouflaged object detection, we construct a large-scale dataset, USC12K, which features comprehensive labels and four different scenes that cover all possible logical existence scenarios of both salient and camouflaged objects. To explicitly model the relationship between salient and camouflaged objects, we propose a model called USCNet, which introduces two distinct prompt query mechanisms for modeling inter-sample and intra-sample attribute relationships. Additionally, to assess the model's ability to distinguish between salient and camouflaged objects, we design an evaluation metric called CSCS. The proposed method achieves state-of-the-art performance across all scenes in various metrics. The code and dataset will be available at https://github.com/ssecv/USCNet.
comment: 18 pages, 11 figures
♻ ☆ Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework
Open-set Domain Adaptation (OSDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where novel classes - also referred to as target-private unknown classes - are present. Source-free Open-set Domain Adaptation (SF-OSDA) methods address OSDA without accessing labeled source data, making them particularly relevant under privacy constraints. However, SF-OSDA presents significant challenges due to distribution shifts and the introduction of novel classes. Existing SF-OSDA methods typically rely on thresholding the prediction entropy of a sample to identify it as either a known or unknown class, but fail to explicitly learn discriminative features for the target-private unknown classes. We propose Recall and Refine (RRDA), a novel SF-OSDA framework designed to address these limitations by explicitly learning features for target-private unknown classes. RRDA employs a two-stage process. First, we enhance the model's capacity to recognize unknown classes by training a target classifier with an additional decision boundary,guided by synthetic samples generated from target domain features. This enables the classifier to effectively separate known and unknown classes. Second, we adapt the entire model to the target domain, addressing both domain shifts and distinguishability to unknown classes. Any off-the-shelf source-free domain adaptation method (e.g. SHOT, AaD) can be seamlessly integrated into our framework at this stage. Extensive experiments on three benchmark datasets demonstrate that RRDA significantly outperforms existing SF-OSDA and OSDA methods.
comment: Accepted at TMLR 2025
♻ ☆ Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels SC
Finding correspondences between semantically similar points across images and object instances is one of the everlasting challenges in computer vision. While large pre-trained vision models have recently been demonstrated as effective priors for semantic matching, they still suffer from ambiguities for symmetric objects or repeated object parts. We propose to improve semantic correspondence estimation via 3D-aware pseudo-labeling. Specifically, we train an adapter to refine off-the-shelf features using pseudo-labels obtained via 3D-aware chaining, filtering wrong labels through relaxed cyclic consistency, and 3D spherical prototype mapping constraints. While reducing the need for dataset specific annotations compared to prior work, we set a new state-of-the-art on SPair-71k by over 4% absolute gain and by over 7% against methods with similar supervision requirements. The generality of our proposed approach simplifies extension of training to other data sources, which we demonstrate in our experiments.
comment: Project page: https://genintel.github.io/DIY-SC
♻ ☆ Semantic Scene Graph for Ultrasound Image Explanation and Scanning Guidance
Understanding medical ultrasound imaging remains a long-standing challenge due to significant visual variability caused by differences in imaging and acquisition parameters. Recent advancements in large language models (LLMs) have been used to automatically generate terminology-rich summaries orientated to clinicians with sufficient physiological knowledge. Nevertheless, the increasing demand for improved ultrasound interpretability and basic scanning guidance among non-expert users, e.g., in point-of-care settings, has not yet been explored. In this study, we first introduce the scene graph (SG) for ultrasound images to explain image content to ordinary and provide guidance for ultrasound scanning. The ultrasound SG is first computed using a transformer-based one-stage method, eliminating the need for explicit object detection. To generate a graspable image explanation for ordinary, the user query is then used to further refine the abstract SG representation through LLMs. Additionally, the predicted SG is explored for its potential in guiding ultrasound scanning toward missing anatomies within the current imaging view, assisting ordinary users in achieving more standardized and complete anatomical exploration. The effectiveness of this SG-based image explanation and scanning guidance has been validated on images from the left and right neck regions, including the carotid and thyroid, across five volunteers. The results demonstrate the potential of the method to maximally democratize ultrasound by enhancing its interpretability and usability for ordinaries.
♻ ☆ Enhancing Dynamic CT Image Reconstruction with Neural Fields and Optical Flow
In this paper, we investigate image reconstruction for dynamic Computed Tomography. The motion of the target with respect to the measurement acquisition rate leads to highly resolved in time but highly undersampled in space measurements. Such problems pose a major challenge: not accounting for the dynamics of the process leads to a poor reconstruction with non-realistic motion. Variational approaches that penalize time evolution have been proposed to relate subsequent frames and improve image quality based on classical grid-based discretizations. Neural fields have emerged as a novel way to parameterize the quantity of interest using a neural network with a low-dimensional input, benefiting from being lightweight, continuous, and biased towards smooth representations. The latter property has been exploited when solving dynamic inverse problems with neural fields by minimizing a data-fidelity term only. We investigate and show the benefits of introducing explicit motion regularizers for dynamic inverse problems based on partial differential equations, namely, the optical flow equation, for the optimization of neural fields. We compare it against its unregularized counterpart and show the improvements in the reconstruction. We also compare neural fields against a grid-based solver and show that the former outperforms the latter in terms of PSNR in this task.
♻ ☆ 3D Hierarchical Panoptic Segmentation in Real Orchard Environments Across Different Sensors IROS 2025
Crop yield estimation is a relevant problem in agriculture, because an accurate yield estimate can support farmers' decisions on harvesting or precision intervention. Robots can help to automate this process. To do so, they need to be able to perceive the surrounding environment to identify target objects such as trees and plants. In this paper, we introduce a novel approach to address the problem of hierarchical panoptic segmentation of apple orchards on 3D data from different sensors. Our approach is able to simultaneously provide semantic segmentation, instance segmentation of trunks and fruits, and instance segmentation of trees (a trunk with its fruits). This allows us to identify relevant information such as individual plants, fruits, and trunks, and capture the relationship among them, such as precisely estimate the number of fruits associated to each tree in an orchard. To efficiently evaluate our approach for hierarchical panoptic segmentation, we provide a dataset designed specifically for this task. Our dataset is recorded in Bonn, Germany, in a real apple orchard with a variety of sensors, spanning from a terrestrial laser scanner to a RGB-D camera mounted on different robots platforms. The experiments show that our approach surpasses state-of-the-art approaches in 3D panoptic segmentation in the agricultural domain, while also providing full hierarchical panoptic segmentation. Our dataset is publicly available at https://www.ipb.uni-bonn.de/data/hops/. The open-source implementation of our approach is available at https://github.com/PRBonn/hapt3D.
comment: Accepted to IROS 2025
♻ ☆ Cell Tracking according to Biological Needs -- Strong Mitosis-aware Multi-Hypothesis Tracker with Aleatoric Uncertainty
Cell tracking and segmentation assist biologists in extracting insights from large-scale microscopy time-lapse data. Driven by local accuracy metrics, current tracking approaches often suffer from a lack of long-term consistency and the ability to reconstruct lineage trees correctly. To address this issue, we introduce an uncertainty estimation technique for motion estimation frameworks and extend the multi-hypothesis tracking framework. Our uncertainty estimation lifts motion representations into probabilistic spatial densities using problem-specific test-time augmentations. Moreover, we introduce a novel mitosis-aware assignment problem formulation that allows multi-hypothesis trackers to model cell splits and to resolve false associations and mitosis detections based on long-term conflicts. In our framework, explicit biological knowledge is modeled in assignment costs. We evaluate our approach on nine competitive datasets and demonstrate that we outperform the current state-of-the-art on biologically inspired metrics substantially, achieving improvements by a factor of approximately 6 and uncover new insights into the behavior of motion estimation uncertainty.
comment: 13 pages, 4 figures, 4 tables. This work has been accepted to the IEEE for publication
♻ ☆ SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking
Text-based person retrieval aims to identify a target individual from a gallery of images based on a natural language description. It presents a significant challenge due to the complexity of real-world scenes and the ambiguity of appearance-related descriptions. Existing methods primarily emphasize appearance-based cross-modal retrieval, often neglecting the contextual information embedded within the scene, which can offer valuable complementary insights for retrieval. To address this, we introduce SCENEPERSON-13W, a large-scale dataset featuring over 100,000 scenes with rich annotations covering both pedestrian appearance and environmental cues. Based on this, we propose SA-Person, a two-stage retrieval framework. In the first stage, it performs discriminative appearance grounding by aligning textual cues with pedestrian-specific regions. In the second stage, it introduces SceneRanker, a training-free, scene-aware re-ranking method leveraging multimodal large language models to jointly reason over pedestrian appearance and the global scene context. Experiments on SCENEPERSON-13W validate the effectiveness of our framework in challenging scene-level retrieval scenarios. The code and dataset will be made publicly available.
comment: 22 pages, 7 figures. Under review
♻ ☆ Variational Supervised Contrastive Learning
Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1) Without explicit regulation of the embedding distribution, semantically related instances can inadvertently be pushed apart unless complementary signals guide pair selection, and (2) excessive reliance on large in-batch negatives and tailored augmentations hinders generalization. To address these limitations, we propose Variational Supervised Contrastive Learning (VarCon), which reformulates supervised contrastive learning as variational inference over latent class variables and maximizes a posterior-weighted evidence lower bound (ELBO) that replaces exhaustive pair-wise comparisons for efficient class-aware matching and grants fine-grained control over intra-class dispersion in the embedding space. Trained exclusively on image data, our experiments on CIFAR-10, CIFAR-100, ImageNet-100, and ImageNet-1K show that VarCon (1) achieves state-of-the-art performance for contrastive learning frameworks, reaching 79.36% Top-1 accuracy on ImageNet-1K and 78.29% on CIFAR-100 with a ResNet-50 encoder while converging in just 200 epochs; (2) yields substantially clearer decision boundaries and semantic organization in the embedding space, as evidenced by KNN classification, hierarchical clustering results, and transfer-learning assessments; and (3) demonstrates superior performance in few-shot learning than supervised baseline and superior robustness across various augmentation strategies.
♻ ☆ Structure-Preserving Patch Decoding for Efficient Neural Video Representation
Implicit neural representations (INRs) are the subject of extensive research, particularly in their application to modeling complex signals by mapping spatial and temporal coordinates to corresponding values. When handling videos, mapping compact inputs to entire frames or spatially partitioned patch images is an effective approach. This strategy better preserves spatial relationships, reduces computational overhead, and improves reconstruction quality compared to coordinate-based mapping. However, predicting entire frames often limits the reconstruction of high-frequency visual details. Additionally, conventional patch-based approaches based on uniform spatial partitioning tend to introduce boundary discontinuities that degrade spatial coherence. We propose a neural video representation method based on Structure-Preserving Patches (SPPs) to address such limitations. Our method separates each video frame into patch images of spatially aligned frames through a deterministic pixel-based splitting similar to PixelUnshuffle. This operation preserves the global spatial structure while allowing patch-level decoding. We train the decoder to reconstruct these structured patches, enabling a global-to-local decoding strategy that captures the global layout first and refines local details. This effectively reduces boundary artifacts and mitigates distortions from naive upsampling. Experiments on standard video datasets demonstrate that our method achieves higher reconstruction quality and better compression performance than existing INR-based baselines.
♻ ☆ StateSpaceDiffuser: Bringing Long Context to Diffusion World Models
World models have recently become promising tools for predicting realistic visuals based on actions in complex environments. However, their reliance on only a few recent observations leads them to lose track of the long-term context. Consequently, in just a few steps the generated scenes drift from what was previously observed, undermining the temporal coherence of the sequence. This limitation of the state-of-the-art world models, most of which rely on diffusion, comes from their lack of a lasting environment state. To address this problem, we introduce StateSpaceDiffuser, where a diffusion model is enabled to perform long-context tasks by integrating features from a state-space model, representing the entire interaction history. This design restores long-term memory while preserving the high-fidelity synthesis of diffusion models. To rigorously measure temporal consistency, we develop an evaluation protocol that probes a model's ability to reinstantiate seen content in extended rollouts. Comprehensive experiments show that StateSpaceDiffuser significantly outperforms a strong diffusion-only baseline, maintaining a coherent visual context for an order of magnitude more steps. It delivers consistent views in both a 2D maze navigation and a complex 3D environment. These results establish that bringing state-space representations into diffusion models is highly effective in demonstrating both visual details and long-term memory.
♻ ☆ Moderating the Generalization of Score-based Generative Model
Score-based Generative Models (SGMs) have demonstrated remarkable generalization abilities, e.g. generating unseen, but natural data. However, the greater the generalization power, the more likely the unintended generalization, and the more dangerous the abuse. Research on moderated generalization in SGMs remains limited. To fill this gap, we first examine the current 'gold standard' in Machine Unlearning (MU), i.e., re-training the model after removing the undesirable training data, and find it does not work in SGMs. Further analysis of score functions reveals that the MU 'gold standard' does not alter the original score function, which explains its ineffectiveness. Based on this insight, we propose the first Moderated Score-based Generative Model (MSGM), which introduces a novel score adjustment strategy that redirects the score function away from undesirable data during the continuous-time stochastic differential equation process. Extensive experimental results demonstrate that MSGM significantly reduces the likelihood of generating undesirable content while preserving high visual quality for normal image generation. Albeit designed for SGMs, MSGM is a general and flexible MU framework that is compatible with diverse diffusion architectures (SGM and DDPM) and training strategies (re-training and fine-tuning), and enables zero-shot transfer of the pre-trained models to downstream tasks, e.g. image inpainting and reconstruction. The code will be shared upon acceptance.
♻ ☆ Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
Recent advancements in large language models (LLMs) have witnessed a surge in the development of advanced reasoning paradigms, which are now being integrated into multimodal large language models (MLLMs). However, existing approaches often fall short: methods solely employing reinforcement learning (RL) can struggle with sample inefficiency and activating entirely absent reasoning capabilities, while conventional pipelines that initiate with a cold-start supervised fine-tuning (SFT) phase before RL may restrict the model's exploratory capacity and face suboptimal convergence. In this work, we introduce \textbf{Metis-RISE} (\textbf{R}L \textbf{I}ncentivizes and \textbf{S}FT \textbf{E}nhances) for multimodal reasoning model learning. Unlike conventional approaches, Metis-RISE distinctively omits an initial SFT stage, beginning instead with an RL phase (e.g., using a Group Relative Policy Optimization variant) to incentivize and activate the model's latent reasoning capacity. Subsequently, the targeted SFT stage addresses two key challenges identified during RL: (1) \textit{inefficient trajectory sampling} for tasks where the model possesses but inconsistently applies correct reasoning, which we tackle using self-distilled reasoning trajectories from the RL model itself; and (2) \textit{fundamental capability absence}, which we address by injecting expert-augmented knowledge for prompts where the model entirely fails. This strategic application of RL for incentivization followed by SFT for enhancement forms the core of Metis-RISE, leading to two versions of our MLLMs (7B and 72B parameters). Evaluations on the OpenCompass Multimodal Reasoning Leaderboard demonstrate that both models achieve state-of-the-art performance among similar-sized models, with the 72B version ranking fourth overall. Please refer to our project page for open-source information.
comment: Project Page: https://github.com/MM-Thinking/Metis-RISE
♻ ☆ Self-Regulated Neurogenesis for Online Data-Incremental Learning
Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts even in the absence of explicit cues. Online data-incremental learning seeks to emulate this capability by processing each sample only once, without having access to task or stream cues at any point in time since this is more realistic compared to offline setups, where all data from novel class(es) is assumed to be readily available. However, existing methods typically rely on storing the subsets of data in memory or expanding the initial model architecture, resulting in significant computational overhead. Drawing inspiration from 'self-regulated neurogenesis'-brain's mechanism for creating specialized regions or circuits for distinct functions-we propose a novel approach SERENA which encodes each concept in a specialized network path called 'concept cell', integrated into a single over-parameterized network. Once a concept is learned, its corresponding concept cell is frozen, effectively preventing the forgetting of previously acquired information. Furthermore, we introduce two new continual learning scenarios that more closely reflect real-world conditions, characterized by gradually changing sample sizes. Experimental results show that our method not only establishes new state-of-the-art results across ten benchmarks but also remarkably surpasses offline supervised batch learning performance. The code is available at https://github.com/muratonuryildirim/serena.
comment: Published at Conference on Lifelong Learning Agents (CoLLAs) 2025
♻ ☆ Referring Expression Instance Retrieval and A Strong End-to-End Baseline
Using natural language to query visual information is a fundamental need in real-world applications. Text-Image Retrieval (TIR) retrieves a target image from a gallery based on an image-level description, while Referring Expression Comprehension (REC) localizes a target object within a given image using an instance-level description. However, real-world applications often present more complex demands. Users typically query an instance-level description across a large gallery and expect to receive both relevant image and the corresponding instance location. In such scenarios, TIR struggles with fine-grained descriptions and object-level localization, while REC is limited in its ability to efficiently search large galleries and lacks an effective ranking mechanism. In this paper, we introduce a new task called \textbf{Referring Expression Instance Retrieval (REIR)}, which supports both instance-level retrieval and localization based on fine-grained referring expressions. First, we propose a large-scale benchmark for REIR, named REIRCOCO, constructed by prompting advanced vision-language models to generate high-quality referring expressions for instances in the MSCOCO and RefCOCO datasets. Second, we present a baseline method, Contrastive Language-Instance Alignment with Relation Experts (CLARE), which employs a dual-stream architecture to address REIR in an end-to-end manner. Given a referring expression, the textual branch encodes it into a query embedding. The visual branch detects candidate objects and extracts their instance-level visual features. The most similar candidate to the query is selected for bounding box prediction. CLARE is first trained on object detection and REC datasets to establish initial grounding capabilities, then optimized via Contrastive Language-Instance Alignment (CLIA) for improved retrieval across images. We will release our code and benchmark publicly.
♻ ☆ ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection IROS 2025
Vision-based Bird's-Eye-View (BEV) 3D object detection has recently become popular in autonomous driving. However, objects with a high similarity to the background from a camera perspective cannot be detected well by existing methods. In this paper, we propose a BEV-based 3D Object Detection Network with 2D Region-Oriented Attention (ROA-BEV), which enables the backbone to focus more on feature learning of the regions where objects exist. Moreover, our method further enhances the information feature learning ability of ROA through multi-scale structures. Each block of ROA utilizes a large kernel to ensure that the receptive field is large enough to catch information about large objects. Experiments on nuScenes show that ROA-BEV improves the performance based on BEVDepth. The source codes of this work will be available at https://github.com/DFLyan/ROA-BEV.
comment: accepted by IROS 2025
♻ ☆ Is my Data in your AI Model? Membership Inference Test with Application to Face Images
This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. Specifically, we propose two MINT architectures designed to learn the distinct activation patterns that emerge when an Audited Model is exposed to data used during its training process. These architectures are based on Multilayer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). The experimental framework focuses on the challenging task of Face Recognition, considering three state-of-the-art Face Recognition systems. Experiments are carried out using six publicly available databases, comprising over 22 million face images in total. Different experimental scenarios are considered depending on the context of the AI model to test. Our proposed MINT approach achieves promising results, with up to 90\% accuracy, indicating the potential to recognize if an AI model has been trained with specific data. The proposed MINT approach can serve to enforce privacy and fairness in several AI applications, e.g., revealing if sensitive or private data was used for training or tuning Large Language Models (LLMs).
comment: 26 pages main text and 2 pages appendix
♻ ☆ HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis
Pathology is essential for cancer diagnosis, with multiple instance learning (MIL) widely used for whole slide image (WSI) analysis. WSIs exhibit a natural hierarchy -- patches, regions, and slides -- with distinct semantic associations. While some methods attempt to leverage this hierarchy for improved representation, they predominantly rely on Euclidean embeddings, which struggle to fully capture semantic hierarchies. To address this limitation, we propose HyperPath, a novel method that integrates knowledge from textual descriptions to guide the modeling of semantic hierarchies of WSIs in hyperbolic space, thereby enhancing WSI classification. Our approach adapts both visual and textual features extracted by pathology vision-language foundation models to the hyperbolic space. We design an Angular Modality Alignment Loss to ensure robust cross-modal alignment, while a Semantic Hierarchy Consistency Loss further refines feature hierarchies through entailment and contradiction relationships and thus enhance semantic coherence. The classification is performed with geodesic distance, which measures the similarity between entities in the hyperbolic semantic hierarchy. This eliminates the need for linear classifiers and enables a geometry-aware approach to WSI analysis. Extensive experiments show that our method achieves superior performance across tasks compared to existing methods, highlighting the potential of hyperbolic embeddings for WSI analysis.
♻ ☆ HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics ICCV 2025
Long-form video understanding presents unique challenges that extend beyond traditional short-video analysis approaches, particularly in capturing long-range dependencies, processing redundant information efficiently, and extracting high-level semantic concepts. To address these challenges, we propose a novel approach that more accurately reflects human cognition. This paper introduces HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics, featuring two versatile modules that can enhance existing video-language models or operate as a standalone system. Our Episodic COmpressor (ECO) efficiently aggregates representations from micro to semi-macro levels, reducing computational overhead while preserving temporal dependencies. Our Semantics ReTRiever (SeTR) enriches these representations with semantic information by focusing on broader context, dramatically reducing feature dimensionality while preserving relevant macro-level information. We demonstrate that these modules can be seamlessly integrated into existing SOTA models, consistently improving their performance while reducing inference latency by up to 43% and memory usage by 46%. As a standalone system, HERMES achieves state-of-the-art performance across multiple long-video understanding benchmarks in both zero-shot and fully-supervised settings.
comment: Accepted for ICCV 2025. Project page: https://joslefaure.github.io/assets/html/hermes.html
♻ ☆ ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring ICCV 2025
Motion deblurring addresses the challenge of image blur caused by camera or scene movement. Event cameras provide motion information that is encoded in the asynchronous event streams. To efficiently leverage the temporal information of event streams, we employ Spiking Neural Networks (SNNs) for motion feature extraction and Artificial Neural Networks (ANNs) for color information processing. Due to the non-uniform distribution and inherent redundancy of event data, existing cross-modal feature fusion methods exhibit certain limitations. Inspired by the visual attention mechanism in the human visual system, this study introduces a bioinspired dual-drive hybrid network (BDHNet). Specifically, the Neuron Configurator Module (NCM) is designed to dynamically adjusts neuron configurations based on cross-modal features, thereby focusing the spikes in blurry regions and adapting to varying blurry scenarios dynamically. Additionally, the Region of Blurry Attention Module (RBAM) is introduced to generate a blurry mask in an unsupervised manner, effectively extracting motion clues from the event features and guiding more accurate cross-modal feature fusion. Extensive subjective and objective evaluations demonstrate that our method outperforms current state-of-the-art methods on both synthetic and real-world datasets.
comment: Accepted by ICCV 2025
♻ ☆ ToMiE: Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars
In this paper, we highlight a critical yet often overlooked factor in most 3D human tasks, namely modeling complicated 3D human with with hand-held objects or loose-fitting clothing. It is known that the parameterized formulation of SMPL is able to fit human skin; while hand-held objects and loose-fitting clothing, are difficult to get modeled within the unified framework, since their movements are usually decoupled with the human body. To enhance the capability of SMPL skeleton in response to this situation, we propose a growth strategy that enables the joint tree of the skeleton to expand adaptively. Specifically, our method, called ToMiE, consists of parent joints localization and external joints optimization. For parent joints localization, we employ a gradient-based approach guided by both LBS blending weights and motion kernels. Once the external joints are obtained, we proceed to optimize their transformations in SE(3) across different frames, enabling rendering and explicit animation. ToMiE manages to outperform other methods across various cases with hand-held objects and loose-fitting clothing, not only in rendering quality but also by offering free animation of grown joints, thereby enhancing the expressive ability of SMPL skeleton for a broader range of applications.
♻ ☆ RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS ICCV 2025
3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images. We identify that the Gaussian densification process, while enhancing scene detail capture, unintentionally contributes to these artifacts by growing additional Gaussians that model transient disturbances. To address this, we propose RobustSplat, a robust solution based on two critical designs. First, we introduce a delayed Gaussian growth strategy that prioritizes optimizing static scene structure before allowing Gaussian splitting/cloning, mitigating overfitting to transient objects in early optimization. Second, we design a scale-cascaded mask bootstrapping approach that first leverages lower-resolution feature similarity supervision for reliable initial transient mask estimation, taking advantage of its stronger semantic consistency and robustness to noise, and then progresses to high-resolution supervision to achieve more precise mask prediction. Extensive experiments on multiple challenging datasets show that our method outperforms existing methods, clearly demonstrating the robustness and effectiveness of our method. Our project page is https://fcyycf.github.io/RobustSplat/.
comment: ICCV 2025. Project page: https://fcyycf.github.io/RobustSplat/
♻ ☆ 2D Triangle Splatting for Direct Differentiable Mesh Training
Differentiable rendering with 3D Gaussian primitives has emerged as a powerful method for reconstructing high-fidelity 3D scenes from multi-view images. While it offers improvements over NeRF-based methods, this representation still encounters challenges with rendering speed and advanced rendering effects, such as relighting and shadow rendering, compared to mesh-based models. In this paper, we propose 2D Triangle Splatting (2DTS), a novel method that replaces 3D Gaussian primitives with 2D triangle facelets. This representation naturally forms a discrete mesh-like structure while retaining the benefits of continuous volumetric modeling. By incorporating a compactness parameter into the triangle primitives, we enable direct training of photorealistic meshes. Our experimental results demonstrate that our triangle-based method, in its vanilla version (without compactness tuning), achieves higher fidelity compared to state-of-the-art Gaussian-based methods. Furthermore, our approach produces reconstructed meshes with superior visual quality compared to existing mesh reconstruction methods. Please visit our project page at https://gaoderender.github.io/triangle-splatting.
comment: 13 pages, 8 figures
♻ ☆ High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous Flight CVPR2025
Semantic segmentation from RGB cameras is essential to the perception of autonomous flying vehicles. The stability of predictions through the captured videos is paramount to their reliability and, by extension, to the trustworthiness of the agents. In this paper, we propose a lightweight video semantic segmentation approach-suited to onboard real-time inference-achieving high temporal consistency on aerial data through Semantic Similarity Propagation across frames. SSP temporally propagates the predictions of an efficient image segmentation model with global registration alignment to compensate for camera movements. It combines the current estimation and the prior prediction with linear interpolation using weights computed from the features similarities of the two frames. Because data availability is a challenge in this domain, we propose a consistency-aware Knowledge Distillation training procedure for sparsely labeled datasets with few annotations. Using a large image segmentation model as a teacher to train the efficient SSP, we leverage the strong correlations between labeled and unlabeled frames in the same training videos to obtain high-quality supervision on all frames. KD-SSP obtains a significant temporal consistency increase over the base image segmentation model of 12.5% and 6.7% TC on UAVid and RuralScapes respectively, with higher accuracy and comparable inference speed. On these aerial datasets, KD-SSP provides a superior segmentation quality and inference speed trade-off than other video methods proposed for general applications and shows considerably higher consistency. Project page: https://github.com/FraunhoferIVI/SSP.
comment: Accepted by CVPR2025
♻ ☆ CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance
We introduce CREStE, a scalable learning-based mapless navigation framework to address the open-world generalization and robustness challenges of outdoor urban navigation. Key to achieving this is learning perceptual representations that generalize to open-set factors (e.g. novel semantic classes, terrains, dynamic entities) and inferring expert-aligned navigation costs from limited demonstrations. CREStE addresses both these issues, introducing 1) a visual foundation model (VFM) distillation objective for learning open-set structured bird's-eye-view perceptual representations, and 2) counterfactual inverse reinforcement learning (IRL), a novel active learning formulation that uses counterfactual trajectory demonstrations to reason about the most important cues when inferring navigation costs. We evaluate CREStE on the task of kilometer-scale mapless navigation in a variety of city, offroad, and residential environments and find that it outperforms all state-of-the-art approaches with 70% fewer human interventions, including a 2-kilometer mission in an unseen environment with just 1 intervention; showcasing its robustness and effectiveness for long-horizon mapless navigation. Videos and additional materials can be found on the project page: https://amrl.cs.utexas.edu/creste
comment: 18 pages, 10 figures, 5 tables
♻ ☆ Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling
Downscaling is essential for generating the high-resolution climate data needed for local planning, but traditional methods remain computationally demanding. Recent years have seen impressive results from AI downscaling models, particularly diffusion models, which have attracted attention due to their ability to generate ensembles and overcome the smoothing problem common in other AI methods. However, these models typically remain computationally intensive. We introduce a Hierarchical Diffusion Downscaling (HDD) model, which introduces an easily-extensible hierarchical sampling process to the diffusion framework. A coarse-to-fine hierarchy is imposed via a simple downsampling scheme. HDD achieves competitive accuracy on ERA5 reanalysis datasets and CMIP6 models, significantly reducing computational load by running on up to half as many pixels with competitive results. Additionally, a single model trained at 0.25{\deg} resolution transfers seamlessly across multiple CMIP6 models with much coarser resolution. HDD thus offers a lightweight alternative for probabilistic climate downscaling, facilitating affordable large-ensemble high-resolution climate projections. See a full code implementation at: https://github.com/HDD-Hierarchical-Diffusion-Downscaling/HDD-Hierarchical-Diffusion-Downscaling.
comment: 8 pages
♻ ☆ A Multi-Source Data Fusion-based Semantic Segmentation Model for Relic Landslide Detection
As a natural disaster, landslide often brings tremendous losses to human lives, so it urgently demands reliable detection of landslide risks. When detecting relic landslides that present important information for landslide risk warning, problems such as visual blur and small-sized dataset cause great challenges when using remote sensing images. To extract accurate semantic features, a hyper-pixel-wise contrastive learning augmented segmentation network (HPCL-Net) is proposed, which augments the local salient feature extraction from boundaries of landslides through HPCL and fuses heterogeneous information in the semantic space from high-resolution remote sensing images and digital elevation model data. For full utilization of precious samples, a global hyper-pixel-wise sample pair queues-based contrastive learning method is developed, which includes the construction of global queues that store hyper-pixel-wise samples and the updating scheme of a momentum encoder, reliably enhancing the extraction ability of semantic features. The proposed HPCL-Net is evaluated on the Loess Plateau relic landslide dataset and experimental results verify that the proposed HPCL-Net greatly outperforms existing models, where the mIoU is increased from 0.620 to 0.651, the Landslide IoU is improved from 0.334 to 0.394 and the F1score is enhanced from 0.501 to 0.565.
♻ ☆ Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion ICCV 2025
Ultra-high-definition (UHD) image restoration often faces computational bottlenecks and information loss due to its extremely high resolution. Existing studies based on Variational Autoencoders (VAE) improve efficiency by transferring the image restoration process from pixel space to latent space. However, degraded components are inherently coupled with background elements in degraded images, both information loss during compression and information gain during compensation remain uncontrollable. These lead to restored images often exhibiting image detail loss and incomplete degradation removal. To address this issue, we propose a Controlled Differential Disentangled VAE, which utilizes Hierarchical Contrastive Disentanglement Learning and an Orthogonal Gated Projection Module to guide the VAE to actively discard easily recoverable background information while encoding more difficult-to-recover degraded information into the latent space. Additionally, we design a Complex Invertible Multiscale Fusion Network to handle background features, ensuring their consistency, and utilize a latent space restoration network to transform the degraded latent features, leading to more accurate restoration results. Extensive experimental results demonstrate that our method effectively alleviates the information loss problem in VAE models while ensuring computational efficiency, significantly improving the quality of UHD image restoration, and achieves state-of-the-art results in six UHD restoration tasks with only 1M parameters.
comment: Accepted by ICCV 2025
♻ ☆ JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers ICCV
We present JointDiT, a diffusion transformer that models the joint distribution of RGB and depth. By leveraging the architectural benefit and outstanding image prior of the state-of-the-art diffusion transformer, JointDiT not only generates high-fidelity images but also produces geometrically plausible and accurate depth maps. This solid joint distribution modeling is achieved through two simple yet effective techniques that we propose, i.e., adaptive scheduling weights, which depend on the noise levels of each modality, and the unbalanced timestep sampling strategy. With these techniques, we train our model across all noise levels for each modality, enabling JointDiT to naturally handle various combinatorial generation tasks, including joint generation, depth estimation, and depth-conditioned image generation by simply controlling the timestep of each branch. JointDiT demonstrates outstanding joint generation performance. Furthermore, it achieves comparable results in depth estimation and depth-conditioned image generation, suggesting that joint distribution modeling can serve as a replaceable alternative to conditional generation. The project page is available at https://byungki-k.github.io/JointDiT/.
comment: Accepted to IEEE/CVF International Conference on Computer Vision (ICCV) 2025. Project page: https://byungki-k.github.io/JointDiT/ Code: https://github.com/ByungKi-K/JointDiT-code
♻ ☆ HUG: Hierarchical Urban Gaussian Splatting with Block-Based Reconstruction for Large-Scale Aerial Scenes ICCV
3DGS is an emerging and increasingly popular technology in the field of novel view synthesis. Its highly realistic rendering quality and real-time rendering capabilities make it promising for various applications. However, when applied to large-scale aerial urban scenes, 3DGS methods suffer from issues such as excessive memory consumption, slow training times, prolonged partitioning processes, and significant degradation in rendering quality due to the increased data volume. To tackle these challenges, we introduce \textbf{HUG}, a novel approach that enhances data partitioning and reconstruction quality by leveraging a hierarchical neural Gaussian representation. We first propose a visibility-based data partitioning method that is simple yet highly efficient, significantly outperforming existing methods in speed. Then, we introduce a novel hierarchical weighted training approach, combined with other optimization strategies, to substantially improve reconstruction quality. Our method achieves state-of-the-art results on one synthetic dataset and four real-world datasets.
comment: An improved version has recently been accepted to ICCV, manuscript, not camera-ready
♻ ☆ ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model
Speech-driven 3D facial animation aims to generate realistic lip movements and facial expressions for 3D head models from arbitrary audio clips. Although existing diffusion-based methods are capable of producing natural motions, their slow generation speed limits their application potential. In this paper, we introduce a novel autoregressive model that achieves real-time generation of highly synchronized lip movements and realistic head poses and eye blinks by learning a mapping from speech to a multi-scale motion codebook. Furthermore, our model can adapt to unseen speaking styles, enabling the creation of 3D talking avatars with unique personal styles beyond the identities seen during training. Extensive evaluations and user studies demonstrate that our method outperforms existing approaches in lip synchronization accuracy and perceived quality.
comment: More video demonstrations, code, models and data can be found on our project website: http://xg-chu.site/project_artalk/
♻ ☆ Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model MICCAI25
In ophthalmic surgery, developing an AI system capable of interpreting surgical videos and predicting subsequent operations requires numerous ophthalmic surgical videos with high-quality annotations, which are difficult to collect due to privacy concerns and labor consumption. Text-guided video generation (T2V) emerges as a promising solution to overcome this issue by generating ophthalmic surgical videos based on surgeon instructions. In this paper, we present Ophora, a pioneering model that can generate ophthalmic surgical videos following natural language instructions. To construct Ophora, we first propose a Comprehensive Data Curation pipeline to convert narrative ophthalmic surgical videos into a large-scale, high-quality dataset comprising over 160K video-instruction pairs, Ophora-160K. Then, we propose a Progressive Video-Instruction Tuning scheme to transfer rich spatial-temporal knowledge from a T2V model pre-trained on natural video-text datasets for privacy-preserved ophthalmic surgical video generation based on Ophora-160K. Experiments on video quality evaluation via quantitative analysis and ophthalmologist feedback demonstrate that Ophora can generate realistic and reliable ophthalmic surgical videos based on surgeon instructions. We also validate the capability of Ophora for empowering downstream tasks of ophthalmic surgical workflow understanding. Code is available at https://github.com/mar-cry/Ophora.
comment: Early accepted in MICCAI25
♻ ☆ Efficient Image Generation with Variadic Attention Heads CVPR
While the integration of transformers in vision models have yielded significant improvements on vision tasks they still require significant amounts of computation for both training and inference. Restricted attention mechanisms significantly reduce these computational burdens but come at the cost of losing either global or local coherence. We propose a simple, yet powerful method to reduce these trade-offs: allow the attention heads of a single transformer to attend to multiple receptive fields. We demonstrate our method utilizing Neighborhood Attention (NA) and integrate it into a StyleGAN based architecture for image generation. With this work, dubbed StyleNAT, we are able to achieve a FID of 2.05 on FFHQ, a 6% improvement over StyleGAN-XL, while utilizing 28% fewer parameters and with 4$\times$ the throughput capacity. StyleNAT achieves the Pareto Frontier on FFHQ-256 and demonstrates powerful and efficient image generation on other datasets. Our code and model checkpoints are publicly available at: https://github.com/SHI-Labs/StyleNAT
comment: Published in eLVM @ CVPR (https://openaccess.thecvf.com/content/CVPR2025W/eLVM/html/Walton_Efficient_Image_Generation_with_Variadic_Attention_Heads_CVPRW_2025_paper) | Formerly named StyleNAT: Giving Each Head a New Perspective |
Information Retrieval 17
☆ Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval ACL 2025
Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities. Traditional methods learn a single-vector embedding to represent semantics of each sample, but struggle to capture nuanced and diverse relationships that can exist across modalities. Set-based approaches, which represent each sample with multiple embeddings, offer a promising alternative, as they can capture richer and more diverse relationships. In this paper, we show that, despite their promise, these set-based representations continue to face issues including sparse supervision and set collapse, which limits their effectiveness. To address these challenges, we propose Maximal Pair Assignment Similarity to optimize one-to-one matching between embedding sets which preserve semantic diversity within the set. We also introduce two loss functions to further enhance the representations: Global Discriminative Loss to enhance distinction among embeddings, and Intra-Set Divergence Loss to prevent collapse within each set. Our method achieves state-of-the-art performance on MS-COCO and Flickr30k without relying on external data.
comment: Accepted at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025 Main)
☆ skLEP: A Slovak General Language Understanding Benchmark ACL 2025
In this work, we introduce skLEP, the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding (NLU) models. We have compiled skLEP to encompass nine diverse tasks that span token-level, sentence-pair, and document-level challenges, thereby offering a thorough assessment of model capabilities. To create this benchmark, we curated new, original datasets tailored for Slovak and meticulously translated established English NLU resources. Within this paper, we also present the first systematic and extensive evaluation of a wide array of Slovak-specific, multilingual, and English pre-trained language models using the skLEP tasks. Finally, we also release the complete benchmark data, an open-source toolkit facilitating both fine-tuning and evaluation of models, and a public leaderboard at https://github.com/slovak-nlp/sklep in the hopes of fostering reproducibility and drive future research in Slovak NLU.
comment: ACL 2025 Findings
☆ Text2Cypher Across Languages: Evaluating Foundational Models Beyond English
Recent advances in large language models have enabled natural language interfaces that translate user questions into database queries, such as Text2SQL, Text2SPARQL, and Text2Cypher. While these interfaces enhance database accessibility, most research today focuses solely on English, with limited evaluation in other languages. This paper investigates the performance of foundational LLMs on the Text2Cypher task across multiple languages. We create and release a multilingual test set by translating English questions into Spanish and Turkish while preserving the original Cypher queries, enabling fair cross-lingual comparison. We evaluate multiple foundational models using standardized prompts and metrics. Our results show a consistent performance pattern: highest on English, then Spanish, and lowest on Turkish. We attribute this to differences in training data availability and linguistic characteristics. Additionally, we explore the impact of translating task prompts into Spanish and Turkish. Results show little to no change in evaluation metrics, suggesting prompt translation has minor impact. Our findings highlight the need for more inclusive evaluation and development in multilingual query generation. Future work includes schema localization and fine-tuning across diverse languages.
☆ Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation SIGIR 2025
Real-world live retrieval-augmented generation (RAG) systems face significant challenges when processing user queries that are often noisy, ambiguous, and contain multiple intents. While RAG enhances large language models (LLMs) with external knowledge, current systems typically struggle with such complex inputs, as they are often trained or evaluated on cleaner data. This paper introduces Omni-RAG, a novel framework designed to improve the robustness and effectiveness of RAG systems in live, open-domain settings. Omni-RAG employs LLM-assisted query understanding to preprocess user inputs through three key modules: (1) Deep Query Understanding and Decomposition, which utilizes LLMs with tailored prompts to denoise queries (e.g., correcting spelling errors) and decompose multi-intent queries into structured sub-queries; (2) Intent-Aware Knowledge Retrieval, which performs retrieval for each sub-query from a corpus (i.e., FineWeb using OpenSearch) and aggregates the results; and (3) Reranking and Generation, where a reranker (i.e., BGE) refines document selection before a final response is generated by an LLM (i.e., Falcon-10B) using a chain-of-thought prompt. Omni-RAG aims to bridge the gap between current RAG capabilities and the demands of real-world applications, such as those highlighted by the SIGIR 2025 LiveRAG Challenge, by robustly handling complex and noisy queries.
comment: Accepted at SIGIR 2025 LiveRAG Workshop (Oral Presentation)
☆ Real-time and personalized product recommendations for large e-commerce platforms ICANN
We present a methodology to provide real-time and personalized product recommendations for large e-commerce platforms, specifically focusing on fashion retail. Our approach aims to achieve accurate and scalable recommendations with minimal response times, ensuring user satisfaction, leveraging Graph Neural Networks and parsimonious learning methodologies. Extensive experimentation with datasets from one of the largest e-commerce platforms demonstrates the effectiveness of our approach in forecasting purchase sequences and handling multi-interaction scenarios, achieving efficient personalized recommendations under real-world constraints.
comment: This paper has been accepted for publication at the International Conference on Artificial Neural Networks (ICANN) 2025. The final authenticated version will be available for purchase through the publisher's website. The conference proceedings will be published by Springer in the Lecture Notes in Computer Science (LNCS) series
☆ Small Encoders Can Rival Large Decoders in Detecting Groundedness
Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer queries reliably when the provided context lacks information, often resorting to ungrounded speculation or internal knowledge. Groundedness - generating responses strictly supported by the context - is essential for ensuring factual consistency and trustworthiness. This study focuses on detecting whether a given query is grounded in a document provided in context before the costly answer generation by LLMs. Such a detection mechanism can significantly reduce both inference time and resource consumption. We show that lightweight, task specific encoder models such as RoBERTa and NomicBERT, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs, such as Llama3 8B and GPT4o, in groundedness detection while reducing inference latency by orders of magnitude. The code is available at : https://github.com/chandarlab/Hallucinate-less
☆ Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various NLP tasks, their potential for ATE has scarcely been examined. We propose a retrieval-based prompting strategy that, in the few-shot setting, selects demonstrations according to \emph{syntactic} rather than semantic similarity. This syntactic retrieval method is domain-agnostic and provides more reliable guidance for capturing term boundaries. We evaluate the approach in both in-domain and cross-domain settings, analyzing how lexical overlap between the query sentence and its retrieved examples affects performance. Experiments on three specialized ATE benchmarks show that syntactic retrieval improves F1-score. These findings highlight the importance of syntactic cues when adapting LLMs to terminology-extraction tasks.
☆ PeakNetFP: Peak-based Neural Audio Fingerprinting Robust to Extreme Time Stretching
This work introduces PeakNetFP, the first neural audio fingerprinting (AFP) system designed specifically around spectral peaks. This novel system is designed to leverage the sparse spectral coordinates typically computed by traditional peak-based AFP methods. PeakNetFP performs hierarchical point feature extraction techniques similar to the computer vision model PointNet++, and is trained using contrastive learning like in the state-of-the-art deep learning AFP, NeuralFP. This combination allows PeakNetFP to outperform conventional AFP systems and achieves comparable performance to NeuralFP when handling challenging time-stretched audio data. In extensive evaluation, PeakNetFP maintains a Top-1 hit rate of over 90% for stretching factors ranging from 50% to 200%. Moreover, PeakNetFP offers significant efficiency advantages: compared to NeuralFP, it has 100 times fewer parameters and uses 11 times smaller input data. These features make PeakNetFP a lightweight and efficient solution for AFP tasks where time stretching is involved. Overall, this system represents a promising direction for future AFP technologies, as it successfully merges the lightweight nature of peak-based AFP with the adaptability and pattern recognition capabilities of neural network-based approaches, paving the way for more scalable and efficient solutions in the field.
comment: Accepted at ISMIR 2025
☆ A Semi-supervised Scalable Unified Framework for E-commerce Query Classification ACL 2025
Query classification, including multiple subtasks such as intent and category prediction, is vital to e-commerce applications. E-commerce queries are usually short and lack context, and the information between labels cannot be used, resulting in insufficient prior information for modeling. Most existing industrial query classification methods rely on users' posterior click behavior to construct training samples, resulting in a Matthew vicious cycle. Furthermore, the subtasks of query classification lack a unified framework, leading to low efficiency for algorithm optimization. In this paper, we propose a novel Semi-supervised Scalable Unified Framework (SSUF), containing multiple enhanced modules to unify the query classification tasks. The knowledge-enhanced module uses world knowledge to enhance query representations and solve the problem of insufficient query information. The label-enhanced module uses label semantics and semi-supervised signals to reduce the dependence on posterior labels. The structure-enhanced module enhances the label representation based on the complex label relations. Each module is highly pluggable, and input features can be added or removed as needed according to each subtask. We conduct extensive offline and online A/B experiments, and the results show that SSUF significantly outperforms the state-of-the-art models.
comment: Accepted by ACL 2025
☆ RecCoT: Enhancing Recommendation via Chain-of-Thought
In real-world applications, users always interact with items in multiple aspects, such as through implicit binary feedback (e.g., clicks, dislikes, long views) and explicit feedback (e.g., comments, reviews). Modern recommendation systems (RecSys) learn user-item collaborative signals from these implicit feedback signals as a large-scale binary data-streaming, subsequently recommending other highly similar items based on users' personalized historical interactions. However, from this collaborative-connection perspective, the RecSys does not focus on the actual content of the items themselves but instead prioritizes higher-probability signals of behavioral co-occurrence among items. Consequently, under this binary learning paradigm, the RecSys struggles to understand why a user likes or dislikes certain items. To alleviate it, some works attempt to utilize the content-based reviews to capture the semantic knowledge to enhance recommender models. However, most of these methods focus on predicting the ratings of reviews, but do not provide a human-understandable explanation.
comment: Work in progress
☆ Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality SIGIR 2025
Existing research on Retrieval-Augmented Generation (RAG) primarily focuses on improving overall question-answering accuracy, often overlooking the quality of sub-claims within generated responses. Recent methods that attempt to improve RAG trustworthiness, such as through auto-evaluation metrics, lack probabilistic guarantees or require ground truth answers. To address these limitations, we propose Conformal-RAG, a novel framework inspired by recent applications of conformal prediction (CP) on large language models (LLMs). Conformal-RAG leverages CP and internal information from the RAG mechanism to offer statistical guarantees on response quality. It ensures group-conditional coverage spanning multiple sub-domains without requiring manual labelling of conformal sets, making it suitable for complex RAG applications. Compared to existing RAG auto-evaluation methods, Conformal-RAG offers statistical guarantees on the quality of refined sub-claims, ensuring response reliability without the need for ground truth answers. Additionally, our experiments demonstrate that by leveraging information from the RAG system, Conformal-RAG retains up to 60\% more high-quality sub-claims from the response compared to direct applications of CP to LLMs, while maintaining the same reliability guarantee.
comment: Accepted by SIGIR 2025 short paper, 5 pages, Code is available at https://github.com/n4feng/ResponseQualityAssessment
☆ EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus. However, existing approaches typically assume a static corpus, requiring expensive full-graph reconstruction whenever new documents arrive, limiting their scalability in dynamic, evolving environments. To address these limitations, we introduce EraRAG, a novel multi-layered Graph-RAG framework that supports efficient and scalable dynamic updates. Our method leverages hyperplane-based Locality-Sensitive Hashing (LSH) to partition and organize the original corpus into hierarchical graph structures, enabling efficient and localized insertions of new data without disrupting the existing topology. The design eliminates the need for retraining or costly recomputation while preserving high retrieval accuracy and low latency. Experiments on large-scale benchmarks demonstrate that EraRag achieves up to an order of magnitude reduction in update time and token consumption compared to existing Graph-RAG systems, while providing superior accuracy performance. This work offers a practical path forward for RAG systems that must operate over continually growing corpora, bridging the gap between retrieval efficiency and adaptability. Our code and data are available at https://github.com/EverM0re/EraRAG-Official.
comment: Under review
☆ Metadata Enrichment of Long Text Documents using Large Language Models
In this project, we semantically enriched and enhanced the metadata of long text documents, theses and dissertations, retrieved from the HathiTrust Digital Library in English published from 1920 to 2020 through a combination of manual efforts and large language models. This dataset provides a valuable resource for advancing research in areas such as computational social science, digital humanities, and information science. Our paper shows that enriching metadata using LLMs is particularly beneficial for digital repositories by introducing additional metadata access points that may not have originally been foreseen to accommodate various content types. This approach is particularly effective for repositories that have significant missing data in their existing metadata fields, enhancing search results and improving the accessibility of the digital repository.
♻ ☆ From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.
♻ ☆ GATSY: Graph Attention Network for Music Artist Similarity IJCNN 2025
The artist similarity quest has become a crucial subject in social and scientific contexts, driven by the desire to enhance music discovery according to user preferences. Modern research solutions facilitate music discovery according to user tastes. However, defining similarity among artists remains challenging due to its inherently subjective nature, which can impact recommendation accuracy. This paper introduces GATSY, a novel recommendation system built upon graph attention networks and driven by a clusterized embedding of artists. The proposed framework leverages the graph topology of the input data to achieve outstanding performance results without relying heavily on hand-crafted features. This flexibility allows us to include fictitious artists within a music dataset, facilitating connections between previously unlinked artists and enabling diverse recommendations from various and heterogeneous sources. Experimental results prove the effectiveness of the proposed method with respect to state-of-the-art solutions while maintaining flexibility. The code to reproduce these experiments is available at https://github.com/difra100/GATSY-Music_Artist_Similarity.
comment: Camera-Ready version, Accepted at IJCNN 2025
♻ ☆ Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG), by integrating non-parametric knowledge from external knowledge bases into models, has emerged as a promising approach to enhancing response accuracy while mitigating factual errors and hallucinations. This method has been widely applied in tasks such as Question Answering (QA). However, existing RAG methods struggle with open-domain QA tasks because they perform independent retrieval operations and directly incorporate the retrieved information into generation without maintaining a summarizing memory or using adaptive retrieval strategies, leading to noise from redundant information and insufficient information integration. To address these challenges, we propose Adaptive memory-based optimization for enhanced RAG (Amber) for open-domain QA tasks, which comprises an Agent-based Memory Updater, an Adaptive Information Collector, and a Multi-granular Content Filter, working together within an iterative memory updating paradigm. Specifically, Amber integrates and optimizes the language model's memory through a multi-agent collaborative approach, ensuring comprehensive knowledge integration from previous retrieval steps. It dynamically adjusts retrieval queries and decides when to stop retrieval based on the accumulated knowledge, enhancing retrieval efficiency and effectiveness. Additionally, it reduces noise by filtering irrelevant content at multiple levels, retaining essential information to improve overall model performance. We conduct extensive experiments on several open-domain QA datasets, and the results demonstrate the superiority and effectiveness of our method and its components. The source code is available \footnote{https://anonymous.4open.science/r/Amber-B203/}.
comment: 8pages. arXiv admin note: text overlap with arXiv:2410.08821 by other authors
♻ ☆ Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization
This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and RAG strategy. We introduce an iterative approach where the search engine generates retrieval results for the RAG agents and gathers feedback on the quality of the retrieved documents during an offline phase. This feedback is then used to iteratively optimize the search engine using an expectation-maximization algorithm, with the goal of maximizing each agent's utility function. Additionally, we adapt this to an online setting, allowing the search engine to refine its behavior based on real-time individual agents feedback to better serve the results for each of them. Experiments on datasets from the Knowledge-Intensive Language Tasks (KILT) benchmark demonstrates that our approach significantly on average outperforms baselines across 18 RAG models. We demonstrate that our method effectively ``personalizes'' the retrieval for each RAG agent based on the collected feedback. Finally, we provide a comprehensive ablation study to explore various aspects of our method.
Multimedia 6
Whole-Body Conditioned Egocentric Video Prediction
We train models to Predict Ego-centric Video from human Actions (PEVA), given the past video and an action represented by the relative 3D body pose. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, our model learns to simulate how physical human actions shape the environment from a first-person point of view. We train an auto-regressive conditional diffusion transformer on Nymeria, a large-scale dataset of real-world egocentric video and body pose capture. We further design a hierarchical evaluation protocol with increasingly challenging tasks, enabling a comprehensive analysis of the model's embodied prediction and control abilities. Our work represents an initial attempt to tackle the challenges of modeling complex real-world environments and embodied agent behaviors with video prediction from the perspective of a human.
comment: Project Page: https://dannytran123.github.io/PEVA
☆ Exploring Adapter Design Tradeoffs for Low Resource Music Generation
Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process, often requiring updates to billions of parameters and, therefore, significant hardware resources. Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly adapter-based methods, have emerged as a promising alternative, enabling adaptation with minimal trainable parameters while preserving model performance. However, the design choices for adapters, including their architecture, placement, and size, are numerous, and it is unclear which of these combinations would produce optimal adapters and why, for a given case of low-resource music genre. In this paper, we attempt to answer this question by studying various adapter configurations for two AI music models, MusicGen and Mustango, on two genres: Hindustani Classical and Turkish Makam music. Our findings reveal distinct trade-offs: convolution-based adapters excel in capturing fine-grained local musical details such as ornamentations and short melodic phrases, while transformer-based adapters better preserve long-range dependencies crucial for structured improvisation. Additionally, we analyze computational resource requirements across different adapter scales, demonstrating how mid-sized adapters (40M parameters) achieve an optimal balance between expressivity and quality. Furthermore, we find that Mustango, a diffusion-based model, generates more diverse outputs with better adherence to the description in the input prompt while lacking in providing stability in notes, rhythm alignment, and aesthetics. Also, it is computationally intensive and requires significantly more time to train. In contrast, autoregressive models like MusicGen offer faster training and are more efficient, and can produce better quality output in comparison, but have slightly higher redundancy in their generations.
comment: 9 pages, 5 figures
☆ FairyGen: Storied Cartoon Video from a Single Child-Drawn Character
We propose FairyGen, an automatic system for generating story-driven cartoon videos from a single child's drawing, while faithfully preserving its unique artistic style. Unlike previous storytelling methods that primarily focus on character consistency and basic motion, FairyGen explicitly disentangles character modeling from stylized background generation and incorporates cinematic shot design to support expressive and coherent storytelling. Given a single character sketch, we first employ an MLLM to generate a structured storyboard with shot-level descriptions that specify environment settings, character actions, and camera perspectives. To ensure visual consistency, we introduce a style propagation adapter that captures the character's visual style and applies it to the background, faithfully retaining the character's full visual identity while synthesizing style-consistent scenes. A shot design module further enhances visual diversity and cinematic quality through frame cropping and multi-view synthesis based on the storyboard. To animate the story, we reconstruct a 3D proxy of the character to derive physically plausible motion sequences, which are then used to fine-tune an MMDiT-based image-to-video diffusion model. We further propose a two-stage motion customization adapter: the first stage learns appearance features from temporally unordered frames, disentangling identity from motion; the second stage models temporal dynamics using a timestep-shift strategy with frozen identity weights. Once trained, FairyGen directly renders diverse and coherent video scenes aligned with the storyboard. Extensive experiments demonstrate that our system produces animations that are stylistically faithful, narratively structured natural motion, highlighting its potential for personalized and engaging story animation. The code will be available at https://github.com/GVCLab/FairyGen
comment: Project Page: https://jayleejia.github.io/FairyGen/ ; Code: https://github.com/GVCLab/FairyGen
☆ Hierarchical Sub-action Tree for Continuous Sign Language Recognition
Continuous sign language recognition (CSLR) aims to transcribe untrimmed videos into glosses, which are typically textual words. Recent studies indicate that the lack of large datasets and precise annotations has become a bottleneck for CSLR due to insufficient training data. To address this, some works have developed cross-modal solutions to align visual and textual modalities. However, they typically extract textual features from glosses without fully utilizing their knowledge. In this paper, we propose the Hierarchical Sub-action Tree (HST), termed HST-CSLR, to efficiently combine gloss knowledge with visual representation learning. By incorporating gloss-specific knowledge from large language models, our approach leverages textual information more effectively. Specifically, we construct an HST for textual information representation, aligning visual and textual modalities step-by-step and benefiting from the tree structure to reduce computational complexity. Additionally, we impose a contrastive alignment enhancement to bridge the gap between the two modalities. Experiments on four datasets (PHOENIX-2014, PHOENIX-2014T, CSL-Daily, and Sign Language Gesture) demonstrate the effectiveness of our HST-CSLR.
☆ E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs AsiaCCS 2025
The rapid spread of misinformation in mobile and wireless networks presents critical security challenges. This study introduces a training-free, retrieval-based multimodal fact verification system that leverages pretrained vision-language models and large language models for credibility assessment. By dynamically retrieving and cross-referencing trusted data sources, our approach mitigates vulnerabilities of traditional training-based models, such as adversarial attacks and data poisoning. Additionally, its lightweight design enables seamless edge device integration without extensive on-device processing. Experiments on two fact-checking benchmarks achieve SOTA results, confirming its effectiveness in misinformation detection and its robustness against various attack vectors, highlighting its potential to enhance security in mobile and wireless communication environments.
comment: Accepted to AsiaCCS 2025 @ SCID
♻ ☆ Challenging Dataset and Multi-modal Gated Mixture of Experts Model for Remote Sensing Copy-Move Forgery Understanding
The Remote Sensing Copy-Move Question Answering (RSCMQA) task focuses on interpreting complex tampering scenarios and inferring the relationships between objects. Currently, publicly available datasets often use randomly generated tampered images, which lack spatial logic and do not meet the practical needs of defense security and land resource monitoring. To address this, we propose a high-quality manually annotated RSCMQA dataset, Real-RSCM, which provides more realistic evaluation metrics for the identification and understanding of remote sensing image tampering. The tampered images in the Real-RSCM dataset are subtle, authentic, and challenging, posing significant difficulties for model discrimination capabilities. To overcome these challenges, we introduce a multimodal gated mixture of experts model (CM-MMoE), which guides multi-expert models to discern tampered information in images through multi-level visual semantics and textual joint modeling. Extensive experiments demonstrate that CM-MMoE provides a stronger benchmark for the RSCMQA task compared to general VQA and CMQA models. Our dataset and code are available at https://github.com/shenyedepisa/CM-MMoE.
comment: 6 pages, 6 figures
Computer Vision and Pattern Recognition 111
☆ IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
Semantic Scene Completion (SSC) has emerged as a pivotal approach for jointly learning scene geometry and semantics, enabling downstream applications such as navigation in mobile robotics. The recent generalization to Panoptic Scene Completion (PSC) advances the SSC domain by integrating instance-level information, thereby enhancing object-level sensitivity in scene understanding. While PSC was introduced using LiDAR modality, methods based on camera images remain largely unexplored. Moreover, recent Transformer-based SSC approaches utilize a fixed set of learned queries to reconstruct objects within the scene volume. Although these queries are typically updated with image context during training, they remain static at test time, limiting their ability to dynamically adapt specifically to the observed scene. To overcome these limitations, we propose IPFormer, the first approach that leverages context-adaptive instance proposals at train and test time to address vision-based 3D Panoptic Scene Completion. Specifically, IPFormer adaptively initializes these queries as panoptic instance proposals derived from image context and further refines them through attention-based encoding and decoding to reason about semantic instance-voxel relationships. Experimental results show that our approach surpasses state-of-the-art methods in overall panoptic metrics PQ$^\dagger$ and PQ-All, matches performance in individual metrics, and achieves a runtime reduction exceeding 14$\times$. Furthermore, our ablation studies reveal that dynamically deriving instance proposals from image context, as opposed to random initialization, leads to a 3.62% increase in PQ-All and a remarkable average improvement of 18.65% in combined Thing-metrics. These results highlight our introduction of context-adaptive instance proposals as a pioneering effort in addressing vision-based 3D Panoptic Scene Completion.
☆ MMSearch-R1: Incentivizing LMMs to Search
Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented generation (RAG) and prompt engineered search agents rely on rigid pipelines, often leading to inefficient or excessive search behaviors. We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables LMMs to perform on-demand, multi-turn search in real-world Internet environments. Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty. To support training, We collect a multimodal search VQA dataset through a semi-automated pipeline that covers diverse visual and textual knowledge needs and curate a search-balanced subset with both search-required and search-free samples, which proves essential for shaping efficient and on-demand search behavior. Extensive experiments on knowledge-intensive and info-seeking VQA tasks show that our model not only outperforms RAG-based baselines of the same model size, but also matches the performance of a larger RAG-based model while reducing search calls by over 30%. We further analyze key empirical findings to offer actionable insights for advancing research in multimodal search.
comment: Code: https://github.com/EvolvingLMMs-Lab/multimodal-search-r1
☆ EditP23: 3D Editing via Propagation of Image Prompts to Multi-View
We present EditP23, a method for mask-free 3D editing that propagates 2D image edits to multi-view representations in a 3D-consistent manner. In contrast to traditional approaches that rely on text-based prompting or explicit spatial masks, EditP23 enables intuitive edits by conditioning on a pair of images: an original view and its user-edited counterpart. These image prompts are used to guide an edit-aware flow in the latent space of a pre-trained multi-view diffusion model, allowing the edit to be coherently propagated across views. Our method operates in a feed-forward manner, without optimization, and preserves the identity of the original object, in both structure and appearance. We demonstrate its effectiveness across a range of object categories and editing scenarios, achieving high fidelity to the source while requiring no manual masks.
comment: Code, supplementary videos, interactive 3D visualizations, and additional results are available at https://editp23.github.io/
☆ Disentangled representations of microscopy images IJCNN 2025
Microscopy image analysis is fundamental for different applications, from diagnosis to synthetic engineering and environmental monitoring. Modern acquisition systems have granted the possibility to acquire an escalating amount of images, requiring a consequent development of a large collection of deep learning-based automatic image analysis methods. Although deep neural networks have demonstrated great performance in this field, interpretability, an essential requirement for microscopy image analysis, remains an open challenge. This work proposes a Disentangled Representation Learning (DRL) methodology to enhance model interpretability for microscopy image classification. Exploiting benchmark datasets from three different microscopic image domains (plankton, yeast vacuoles, and human cells), we show how a DRL framework, based on transferring a representation learnt from synthetic data, can provide a good trade-off between accuracy and interpretability in this domain.
comment: Published in: International Joint Conference on Neural Networks (IJCNN 2025). Project page: https://github.com/JacopoDapueto/disentangled_microscopy
☆ Joint attitude estimation and 3D neural reconstruction of non-cooperative space objects CVPR 2025
Obtaining a better knowledge of the current state and behavior of objects orbiting Earth has proven to be essential for a range of applications such as active debris removal, in-orbit maintenance, or anomaly detection. 3D models represent a valuable source of information in the field of Space Situational Awareness (SSA). In this work, we leveraged Neural Radiance Fields (NeRF) to perform 3D reconstruction of non-cooperative space objects from simulated images. This scenario is challenging for NeRF models due to unusual camera characteristics and environmental conditions : mono-chromatic images, unknown object orientation, limited viewing angles, absence of diffuse lighting etc. In this work we focus primarly on the joint optimization of camera poses alongside the NeRF. Our experimental results show that the most accurate 3D reconstruction is achieved when training with successive images one-by-one. We estimate camera poses by optimizing an uniform rotation and use regularization to prevent successive poses from being too far apart.
comment: accepted for CVPR 2025 NFBCC workshop
☆ Shape2Animal: Creative Animal Generation from Natural Silhouettes
Humans possess a unique ability to perceive meaningful patterns in ambiguous stimuli, a cognitive phenomenon known as pareidolia. This paper introduces Shape2Animal framework to mimics this imaginative capacity by reinterpreting natural object silhouettes, such as clouds, stones, or flames, as plausible animal forms. Our automated framework first performs open-vocabulary segmentation to extract object silhouette and interprets semantically appropriate animal concepts using vision-language models. It then synthesizes an animal image that conforms to the input shape, leveraging text-to-image diffusion model and seamlessly blends it into the original scene to generate visually coherent and spatially consistent compositions. We evaluated Shape2Animal on a diverse set of real-world inputs, demonstrating its robustness and creative potential. Our Shape2Animal can offer new opportunities for visual storytelling, educational content, digital art, and interactive media design. Our project page is here: https://shape2image.github.io
☆ Weighted Mean Frequencies: a handcraft Fourier feature for 4D Flow MRI segmentation
In recent decades, the use of 4D Flow MRI images has enabled the quantification of velocity fields within a volume of interest and along the cardiac cycle. However, the lack of resolution and the presence of noise in these biomarkers are significant issues. As indicated by recent studies, it appears that biomarkers such as wall shear stress are particularly impacted by the poor resolution of vessel segmentation. The Phase Contrast Magnetic Resonance Angiography (PC-MRA) is the state-of-the-art method to facilitate segmentation. The objective of this work is to introduce a new handcraft feature that provides a novel visualisation of 4D Flow MRI images, which is useful in the segmentation task. This feature, termed Weighted Mean Frequencies (WMF), is capable of revealing the region in three dimensions where a voxel has been passed by pulsatile flow. Indeed, this feature is representative of the hull of all pulsatile velocity voxels. The value of the feature under discussion is illustrated by two experiments. The experiments involved segmenting 4D Flow MRI images using optimal thresholding and deep learning methods. The results obtained demonstrate a substantial enhancement in terms of IoU and Dice, with a respective increase of 0.12 and 0.13 in comparison with the PC-MRA feature, as evidenced by the deep learning task. This feature has the potential to yield valuable insights that could inform future segmentation processes in other vascular regions, such as the heart or the brain.
☆ Video Perception Models for 3D Scene Synthesis
Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, robotics simulation, virtual reality, and gaming. Recent approaches to 3D scene synthesis often rely on the commonsense reasoning of large language models (LLMs) or strong visual priors of modern image generation models. However, current LLMs demonstrate limited 3D spatial reasoning ability, which restricts their ability to generate realistic and coherent 3D scenes. Meanwhile, image generation-based methods often suffer from constraints in viewpoint selection and multi-view inconsistencies. In this work, we present Video Perception models for 3D Scene synthesis (VIPScene), a novel framework that exploits the encoded commonsense knowledge of the 3D physical world in video generation models to ensure coherent scene layouts and consistent object placements across views. VIPScene accepts both text and image prompts and seamlessly integrates video generation, feedforward 3D reconstruction, and open-vocabulary perception models to semantically and geometrically analyze each object in a scene. This enables flexible scene synthesis with high realism and structural consistency. For more precise analysis, we further introduce First-Person View Score (FPVScore) for coherence and plausibility evaluation, utilizing continuous first-person perspective to capitalize on the reasoning ability of multimodal large language models. Extensive experiments show that VIPScene significantly outperforms existing methods and generalizes well across diverse scenarios. The code will be released.
☆ SFNet: Fusion of Spatial and Frequency-Domain Features for Remote Sensing Image Forgery Detection
The rapid advancement of generative artificial intelligence is producing fake remote sensing imagery (RSI) that is increasingly difficult to detect, potentially leading to erroneous intelligence, fake news, and even conspiracy theories. Existing forgery detection methods typically rely on single visual features to capture predefined artifacts, such as spatial-domain cues to detect forged objects like roads or buildings in RSI, or frequency-domain features to identify artifacts from up-sampling operations in adversarial generative networks (GANs). However, the nature of artifacts can significantly differ depending on geographic terrain, land cover types, or specific features within the RSI. Moreover, these complex artifacts evolve as generative models become more sophisticated. In short, over-reliance on a single visual cue makes existing forgery detectors struggle to generalize across diverse remote sensing data. This paper proposed a novel forgery detection framework called SFNet, designed to identify fake images in diverse remote sensing data by leveraging spatial and frequency domain features. Specifically, to obtain rich and comprehensive visual information, SFNet employs two independent feature extractors to capture spatial and frequency domain features from input RSIs. To fully utilize the complementary domain features, the domain feature mapping module and the hybrid domain feature refinement module(CBAM attention) of SFNet are designed to successively align and fuse the multi-domain features while suppressing redundant information. Experiments on three datasets show that SFNet achieves an accuracy improvement of 4%-15.18% over the state-of-the-art RS forgery detection methods and exhibits robust generalization capabilities. The code is available at https://github.com/GeoX-Lab/RSTI/tree/main/SFNet.
☆ WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration
Interactive 3D scene generation from a single image has gained significant attention due to its potential to create immersive virtual worlds. However, a key challenge in current 3D generation methods is the limited explorability, which cannot render high-quality images during larger maneuvers beyond the original viewpoint, particularly when attempting to move forward into unseen areas. To address this challenge, we propose WonderFree, the first model that enables users to interactively generate 3D worlds with the freedom to explore from arbitrary angles and directions. Specifically, we decouple this challenge into two key subproblems: novel view quality, which addresses visual artifacts and floating issues in novel views, and cross-view consistency, which ensures spatial consistency across different viewpoints. To enhance rendering quality in novel views, we introduce WorldRestorer, a data-driven video restoration model designed to eliminate floaters and artifacts. In addition, a data collection pipeline is presented to automatically gather training data for WorldRestorer, ensuring it can handle scenes with varying styles needed for 3D scene generation. Furthermore, to improve cross-view consistency, we propose ConsistView, a multi-view joint restoration mechanism that simultaneously restores multiple perspectives while maintaining spatiotemporal coherence. Experimental results demonstrate that WonderFree not only enhances rendering quality across diverse viewpoints but also significantly improves global coherence and consistency. These improvements are confirmed by CLIP-based metrics and a user study showing a 77.20% preference for WonderFree over WonderWorld enabling a seamless and immersive 3D exploration experience. The code, model, and data will be publicly available.
☆ TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness
The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods depend heavily either on supervised annotations or on attention-based models, which are computationally expensive and brittle in the face of distribution shifts that hinder cross-domain applicability across datasets. We introduce a pioneering self-supervised video summarization model that captures both spatial and temporal dependencies without the overhead of attention, RNNs, or transformers. Our framework integrates a novel set of Markov process-driven loss metrics and a two-stage self supervised learning paradigm that ensures both performance and efficiency. Our approach achieves state-of-the-art performance on the SUMME and TVSUM datasets, outperforming all existing unsupervised methods. It also rivals the best supervised models, demonstrating the potential for efficient, annotation-free architectures. This paves the way for more generalizable video summarization techniques and challenges the prevailing reliance on complex architectures.
☆ Learning-Based Distance Estimation for 360° Single-Sensor Setups
Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we propose a neural network-based approach for monocular distance estimation using a single 360{\deg} fisheye lens camera. Unlike classical trigonometric techniques that rely on precise lens calibration, our method directly learns and infers the distance of objects from raw omnidirectional inputs, offering greater robustness and adaptability across diverse conditions. We evaluate our approach on three 360{\deg} datasets (LOAF, ULM360, and a newly captured dataset Boat360), each representing distinct environmental and sensor setups. Our experimental results demonstrate that the proposed learning-based model outperforms traditional geometry-based methods and other learning baselines in both accuracy and robustness. These findings highlight the potential of deep learning for real-time omnidirectional distance estimation, making our approach particularly well-suited for low-cost applications in robotics, autonomous navigation, and surveillance.
comment: Submitted to ECMR 2025
☆ Dense Video Captioning using Graph-based Sentence Summarization
Recently, dense video captioning has made attractive progress in detecting and captioning all events in a long untrimmed video. Despite promising results were achieved, most existing methods do not sufficiently explore the scene evolution within an event temporal proposal for captioning, and therefore perform less satisfactorily when the scenes and objects change over a relatively long proposal. To address this problem, we propose a graph-based partition-and-summarization (GPaS) framework for dense video captioning within two stages. For the ``partition" stage, a whole event proposal is split into short video segments for captioning at a finer level. For the ``summarization" stage, the generated sentences carrying rich description information for each segment are summarized into one sentence to describe the whole event. We particularly focus on the ``summarization" stage, and propose a framework that effectively exploits the relationship between semantic words for summarization. We achieve this goal by treating semantic words as nodes in a graph and learning their interactions by coupling Graph Convolutional Network (GCN) and Long Short Term Memory (LSTM), with the aid of visual cues. Two schemes of GCN-LSTM Interaction (GLI) modules are proposed for seamless integration of GCN and LSTM. The effectiveness of our approach is demonstrated via an extensive comparison with the state-of-the-arts methods on the two benchmarks ActivityNet Captions dataset and YouCook II dataset.
comment: 12 pages
☆ Causal Representation Learning with Observational Grouping for CXR Classification
Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustness of task-specific latent features. This work introduces the concept of grouping observations to learn identifiable representations for disease classification in chest X-rays via an end-to-end framework. Our experiments demonstrate that these causal representations improve generalisability and robustness across multiple classification tasks when grouping is used to enforce invariance w.r.t race, sex, and imaging views.
☆ Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
In this work, we propose a division-and-summarization (DaS) framework for dense video captioning. After partitioning each untrimmed long video as multiple event proposals, where each event proposal consists of a set of short video segments, we extract visual feature (e.g., C3D feature) from each segment and use the existing image/video captioning approach to generate one sentence description for this segment. Considering that the generated sentences contain rich semantic descriptions about the whole event proposal, we formulate the dense video captioning task as a visual cue aided sentence summarization problem and propose a new two stage Long Short Term Memory (LSTM) approach equipped with a new hierarchical attention mechanism to summarize all generated sentences as one descriptive sentence with the aid of visual features. Specifically, the first-stage LSTM network takes all semantic words from the generated sentences and the visual features from all segments within one event proposal as the input, and acts as the encoder to effectively summarize both semantic and visual information related to this event proposal. The second-stage LSTM network takes the output from the first-stage LSTM network and the visual features from all video segments within one event proposal as the input, and acts as the decoder to generate one descriptive sentence for this event proposal. Our comprehensive experiments on the ActivityNet Captions dataset demonstrate the effectiveness of our newly proposed DaS framework for dense video captioning.
comment: 10 pages
☆ HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction
Real-time human perception is crucial for effective human-robot interaction (HRI). Large vision-language models (VLMs) offer promising generalizable perceptual capabilities but often suffer from high latency, which negatively impacts user experience and limits VLM applicability in real-world scenarios. To systematically study VLM capabilities in human perception for HRI and performance-latency trade-offs, we introduce HRIBench, a visual question-answering (VQA) benchmark designed to evaluate VLMs across a diverse set of human perceptual tasks critical for HRI. HRIBench covers five key domains: (1) non-verbal cue understanding, (2) verbal instruction understanding, (3) human-robot object relationship understanding, (4) social navigation, and (5) person identification. To construct HRIBench, we collected data from real-world HRI environments to curate questions for non-verbal cue understanding, and leveraged publicly available datasets for the remaining four domains. We curated 200 VQA questions for each domain, resulting in a total of 1000 questions for HRIBench. We then conducted a comprehensive evaluation of both state-of-the-art closed-source and open-source VLMs (N=11) on HRIBench. Our results show that, despite their generalizability, current VLMs still struggle with core perceptual capabilities essential for HRI. Moreover, none of the models within our experiments demonstrated a satisfactory performance-latency trade-off suitable for real-time deployment, underscoring the need for future research on developing smaller, low-latency VLMs with improved human perception capabilities. HRIBench and our results can be found in this Github repository: https://github.com/interaction-lab/HRIBench.
comment: Accepted to the 19th International Symposium on Experimental Robotics (ISER 2025)
☆ AdvMIM: Adversarial Masked Image Modeling for Semi-Supervised Medical Image Segmentation MICCAI 2025
Vision Transformer has recently gained tremendous popularity in medical image segmentation task due to its superior capability in capturing long-range dependencies. However, transformer requires a large amount of labeled data to be effective, which hinders its applicability in annotation scarce semi-supervised learning scenario where only limited labeled data is available. State-of-the-art semi-supervised learning methods propose combinatorial CNN-Transformer learning to cross teach a transformer with a convolutional neural network, which achieves promising results. However, it remains a challenging task to effectively train the transformer with limited labeled data. In this paper, we propose an adversarial masked image modeling method to fully unleash the potential of transformer for semi-supervised medical image segmentation. The key challenge in semi-supervised learning with transformer lies in the lack of sufficient supervision signal. To this end, we propose to construct an auxiliary masked domain from original domain with masked image modeling and train the transformer to predict the entire segmentation mask with masked inputs to increase supervision signal. We leverage the original labels from labeled data and pseudo-labels from unlabeled data to learn the masked domain. To further benefit the original domain from masked domain, we provide a theoretical analysis of our method from a multi-domain learning perspective and devise a novel adversarial training loss to reduce the domain gap between the original and masked domain, which boosts semi-supervised learning performance. We also extend adversarial masked image modeling to CNN network. Extensive experiments on three public medical image segmentation datasets demonstrate the effectiveness of our method, where our method outperforms existing methods significantly. Our code is publicly available at https://github.com/zlheui/AdvMIM.
comment: Accepted to MICCAI 2025
☆ Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
Modern image-based object detection models, such as YOLOv7, primarily process individual frames independently, thus ignoring valuable temporal context naturally present in videos. Meanwhile, existing video-based detection methods often introduce complex temporal modules, significantly increasing model size and computational complexity. In practical applications such as surveillance and autonomous driving, transient challenges including motion blur, occlusions, and abrupt appearance changes can severely degrade single-frame detection performance. To address these issues, we propose a straightforward yet highly effective strategy: stacking multiple consecutive frames as input to a YOLO-based detector while supervising only the output corresponding to a single target frame. This approach leverages temporal information with minimal modifications to existing architectures, preserving simplicity, computational efficiency, and real-time inference capability. Extensive experiments on the challenging MOT20Det and our BOAT360 datasets demonstrate that our method improves detection robustness, especially for lightweight models, effectively narrowing the gap between compact and heavy detection networks. Additionally, we contribute the BOAT360 benchmark dataset, comprising annotated fisheye video sequences captured from a boat, to support future research in multi-frame video object detection in challenging real-world scenarios.
comment: Submitted to ECMR 2025
☆ Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.
comment: 20 pages, 10 figures
☆ AI-assisted radiographic analysis in detecting alveolar bone-loss severity and patterns
Periodontitis, a chronic inflammatory disease causing alveolar bone loss, significantly affects oral health and quality of life. Accurate assessment of bone loss severity and pattern is critical for diagnosis and treatment planning. In this study, we propose a novel AI-based deep learning framework to automatically detect and quantify alveolar bone loss and its patterns using intraoral periapical (IOPA) radiographs. Our method combines YOLOv8 for tooth detection with Keypoint R-CNN models to identify anatomical landmarks, enabling precise calculation of bone loss severity. Additionally, YOLOv8x-seg models segment bone levels and tooth masks to determine bone loss patterns (horizontal vs. angular) via geometric analysis. Evaluated on a large, expertly annotated dataset of 1000 radiographs, our approach achieved high accuracy in detecting bone loss severity (intra-class correlation coefficient up to 0.80) and bone loss pattern classification (accuracy 87%). This automated system offers a rapid, objective, and reproducible tool for periodontal assessment, reducing reliance on subjective manual evaluation. By integrating AI into dental radiographic analysis, our framework has the potential to improve early diagnosis and personalized treatment planning for periodontitis, ultimately enhancing patient care and clinical outcomes.
comment: This manuscript is 17 pages with 5 tables and 12 figures. The manuscript is under review at Nature Scientific Reports
☆ A Deep Learning Approach to Identify Rock Bolts in Complex 3D Point Clouds of Underground Mines Captured Using Mobile Laser Scanners
Rock bolts are crucial components of the subterranean support systems in underground mines that provide adequate structural reinforcement to the rock mass to prevent unforeseen hazards like rockfalls. This makes frequent assessments of such bolts critical for maintaining rock mass stability and minimising risks in underground mining operations. Where manual surveying of rock bolts is challenging due to the low light conditions in the underground mines and the time-intensive nature of the process, automated detection of rock bolts serves as a plausible solution. To that end, this study focuses on the automatic identification of rock bolts within medium to large-scale 3D point clouds obtained from underground mines using mobile laser scanners. Existing techniques for automated rock bolt identification primarily rely on feature engineering and traditional machine learning approaches. However, such techniques lack robustness as these point clouds present several challenges due to data noise, varying environments, and complex surrounding structures. Moreover, the target rock bolts are extremely small objects within large-scale point clouds and are often partially obscured due to the application of reinforcement shotcrete. Addressing these challenges, this paper proposes an approach termed DeepBolt, which employs a novel two-stage deep learning architecture specifically designed for handling severe class imbalance for the automatic and efficient identification of rock bolts in complex 3D point clouds. The proposed method surpasses state-of-the-art semantic segmentation models by up to 42.5% in Intersection over Union (IoU) for rock bolt points. Additionally, it outperforms existing rock bolt identification techniques, achieving a 96.41% precision and 96.96% recall in classifying rock bolts, demonstrating its robustness and effectiveness in complex underground environments.
☆ HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing zero-shot generation techniques for synthesizing images beyond training resolutions often produce artifacts, including object duplication and spatial incoherence. In this paper, we introduce HiWave, a training-free, zero-shot approach that substantially enhances visual fidelity and structural coherence in ultra-high-resolution image synthesis using pretrained diffusion models. Our method employs a two-stage pipeline: generating a base image from the pretrained model followed by a patch-wise DDIM inversion step and a novel wavelet-based detail enhancer module. Specifically, we first utilize inversion methods to derive initial noise vectors that preserve global coherence from the base image. Subsequently, during sampling, our wavelet-domain detail enhancer retains low-frequency components from the base image to ensure structural consistency, while selectively guiding high-frequency components to enrich fine details and textures. Extensive evaluations using Stable Diffusion XL demonstrate that HiWave effectively mitigates common visual artifacts seen in prior methods, achieving superior perceptual quality. A user study confirmed HiWave's performance, where it was preferred over the state-of-the-art alternative in more than 80% of comparisons, highlighting its effectiveness for high-quality, ultra-high-resolution image synthesis without requiring retraining or architectural modifications.
☆ Med-Art: Diffusion Transformer for 2D Medical Text-to-Image Generation
Text-to-image generative models have achieved remarkable breakthroughs in recent years. However, their application in medical image generation still faces significant challenges, including small dataset sizes, and scarcity of medical textual data. To address these challenges, we propose Med-Art, a framework specifically designed for medical image generation with limited data. Med-Art leverages vision-language models to generate visual descriptions of medical images which overcomes the scarcity of applicable medical textual data. Med-Art adapts a large-scale pre-trained text-to-image model, PixArt-$\alpha$, based on the Diffusion Transformer (DiT), achieving high performance under limited data. Furthermore, we propose an innovative Hybrid-Level Diffusion Fine-tuning (HLDF) method, which enables pixel-level losses, effectively addressing issues such as overly saturated colors. We achieve state-of-the-art performance on two medical image datasets, measured by FID, KID, and downstream classification performance.
comment: The project is available at \url{https://medart-ai.github.io}
☆ An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
Rare diseases collectively affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains a pervasive challenge. This is largely due to their clinical heterogeneity, low individual prevalence, and the limited familiarity most clinicians have with rare conditions. Here, we introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model (LLM), capable of processing heterogeneous clinical inputs. The system generates ranked diagnostic hypotheses for rare diseases, each accompanied by a transparent chain of reasoning that links intermediate analytic steps to verifiable medical evidence. DeepRare comprises three key components: a central host with a long-term memory module; specialized agent servers responsible for domain-specific analytical tasks integrating over 40 specialized tools and web-scale, up-to-date medical knowledge sources, ensuring access to the most current clinical information. This modular and scalable design enables complex diagnostic reasoning while maintaining traceability and adaptability. We evaluate DeepRare on eight datasets. The system demonstrates exceptional diagnostic performance among 2,919 diseases, achieving 100% accuracy for 1013 diseases. In HPO-based evaluations, DeepRare significantly outperforms other 15 methods, like traditional bioinformatics diagnostic tools, LLMs, and other agentic systems, achieving an average Recall@1 score of 57.18% and surpassing the second-best method (Reasoning LLM) by a substantial margin of 23.79 percentage points. For multi-modal input scenarios, DeepRare achieves 70.60% at Recall@1 compared to Exomiser's 53.20% in 109 cases. Manual verification of reasoning chains by clinical experts achieves 95.40% agreements. Furthermore, the DeepRare system has been implemented as a user-friendly web application http://raredx.cn/doctor.
☆ Fusing Radiomic Features with Deep Representations for Gestational Age Estimation in Fetal Ultrasound Images MICCAI 2025
Accurate gestational age (GA) estimation, ideally through fetal ultrasound measurement, is a crucial aspect of providing excellent antenatal care. However, deriving GA from manual fetal biometric measurements depends on the operator and is time-consuming. Hence, automatic computer-assisted methods are demanded in clinical practice. In this paper, we present a novel feature fusion framework to estimate GA using fetal ultrasound images without any measurement information. We adopt a deep learning model to extract deep representations from ultrasound images. We extract radiomic features to reveal patterns and characteristics of fetal brain growth. To harness the interpretability of radiomics in medical imaging analysis, we estimate GA by fusing radiomic features and deep representations. Our framework estimates GA with a mean absolute error of 8.0 days across three trimesters, outperforming current machine learning-based methods at these gestational ages. Experimental results demonstrate the robustness of our framework across different populations in diverse geographical regions. Our code is publicly available on \href{https://github.com/13204942/RadiomicsImageFusion_FetalUS}{GitHub}.
comment: Accepted at MICCAI 2025
☆ A Novel Large Vision Foundation Model (LVFM)-based Approach for Generating High-Resolution Canopy Height Maps in Plantations for Precision Forestry Management
Accurate, cost-effective monitoring of plantation aboveground biomass (AGB) is crucial for supporting local livelihoods and carbon sequestration initiatives like the China Certified Emission Reduction (CCER) program. High-resolution canopy height maps (CHMs) are essential for this, but standard lidar-based methods are expensive. While deep learning with RGB imagery offers an alternative, accurately extracting canopy height features remains challenging. To address this, we developed a novel model for high-resolution CHM generation using a Large Vision Foundation Model (LVFM). Our model integrates a feature extractor, a self-supervised feature enhancement module to preserve spatial details, and a height estimator. Tested in Beijing's Fangshan District using 1-meter Google Earth imagery, our model outperformed existing methods, including conventional CNNs. It achieved a mean absolute error of 0.09 m, a root mean square error of 0.24 m, and a correlation of 0.78 against lidar-based CHMs. The resulting CHMs enabled over 90% success in individual tree detection, high accuracy in AGB estimation, and effective tracking of plantation growth, demonstrating strong generalization to non-training areas. This approach presents a promising, scalable tool for evaluating carbon sequestration in both plantations and natural forests.
☆ Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking
Transformer-based visual trackers have demonstrated significant advancements due to their powerful modeling capabilities. However, their practicality is limited on resource-constrained devices because of their slow processing speeds. To address this challenge, we present HiT, a novel family of efficient tracking models that achieve high performance while maintaining fast operation across various devices. The core innovation of HiT lies in its Bridge Module, which connects lightweight transformers to the tracking framework, enhancing feature representation quality. Additionally, we introduce a dual-image position encoding approach to effectively encode spatial information. HiT achieves an impressive speed of 61 frames per second (fps) on the NVIDIA Jetson AGX platform, alongside a competitive AUC of 64.6% on the LaSOT benchmark, outperforming all previous efficient trackers.Building on HiT, we propose DyHiT, an efficient dynamic tracker that flexibly adapts to scene complexity by selecting routes with varying computational requirements. DyHiT uses search area features extracted by the backbone network and inputs them into an efficient dynamic router to classify tracking scenarios. Based on the classification, DyHiT applies a divide-and-conquer strategy, selecting appropriate routes to achieve a superior trade-off between accuracy and speed. The fastest version of DyHiT achieves 111 fps on NVIDIA Jetson AGX while maintaining an AUC of 62.4% on LaSOT.Furthermore, we introduce a training-free acceleration method based on the dynamic routing architecture of DyHiT. This method significantly improves the execution speed of various high-performance trackers without sacrificing accuracy. For instance, our acceleration method enables the state-of-the-art tracker SeqTrack-B256 to achieve a 2.68 times speedup on an NVIDIA GeForce RTX 2080 Ti GPU while maintaining the same AUC of 69.9% on the LaSOT.
comment: This paper was accepted by International Journal of Computer Vision(IJCV)
☆ InvZW: Invariant Feature Learning via Noise-Adversarial Training for Robust Image Zero-Watermarking
This paper introduces a novel deep learning framework for robust image zero-watermarking based on distortion-invariant feature learning. As a zero-watermarking scheme, our method leaves the original image unaltered and learns a reference signature through optimization in the feature space. The proposed framework consists of two key modules. In the first module, a feature extractor is trained via noise-adversarial learning to generate representations that are both invariant to distortions and semantically expressive. This is achieved by combining adversarial supervision against a distortion discriminator and a reconstruction constraint to retain image content. In the second module, we design a learning-based multibit zero-watermarking scheme where the trained invariant features are projected onto a set of trainable reference codes optimized to match a target binary message. Extensive experiments on diverse image datasets and a wide range of distortions show that our method achieves state-of-the-art robustness in both feature stability and watermark recovery. Comparative evaluations against existing self-supervised and deep watermarking techniques further highlight the superiority of our framework in generalization and robustness.
☆ DreamAnywhere: Object-Centric Panoramic 3D Scene Generation
Recent advances in text-to-3D scene generation have demonstrated significant potential to transform content creation across multiple industries. Although the research community has made impressive progress in addressing the challenges of this complex task, existing methods often generate environments that are only front-facing, lack visual fidelity, exhibit limited scene understanding, and are typically fine-tuned for either indoor or outdoor settings. In this work, we address these issues and propose DreamAnywhere, a modular system for the fast generation and prototyping of 3D scenes. Our system synthesizes a 360{\deg} panoramic image from text, decomposes it into background and objects, constructs a complete 3D representation through hybrid inpainting, and lifts object masks to detailed 3D objects that are placed in the virtual environment. DreamAnywhere supports immersive navigation and intuitive object-level editing, making it ideal for scene exploration, visual mock-ups, and rapid prototyping -- all with minimal manual modeling. These features make our system particularly suitable for low-budget movie production, enabling quick iteration on scene layout and visual tone without the overhead of traditional 3D workflows. Our modular pipeline is highly customizable as it allows components to be replaced independently. Compared to current state-of-the-art text and image-based 3D scene generation approaches, DreamAnywhere shows significant improvements in coherence in novel view synthesis and achieves competitive image quality, demonstrating its effectiveness across diverse and challenging scenarios. A comprehensive user study demonstrates a clear preference for our method over existing approaches, validating both its technical robustness and practical usefulness.
☆ Practical insights on the effect of different encodings, ansätze and measurements in quantum and hybrid convolutional neural networks
This study investigates the design choices of parameterized quantum circuits (PQCs) within quantum and hybrid convolutional neural network (HQNN and QCNN) architectures, applied to the task of satellite image classification using the EuroSAT dataset. We systematically evaluate the performance implications of data encoding techniques, variational ans\"atze, and measurement in approx. 500 distinct model configurations. Our analysis reveals a clear hierarchy of influence on model performance. For hybrid architectures, which were benchmarked against their direct classical equivalents (e.g. the same architecture with the PQCs removed), the data encoding strategy is the dominant factor, with validation accuracy varying over 30% for distinct embeddings. In contrast, the selection of variational ans\"atze and measurement basis had a comparatively marginal effect, with validation accuracy variations remaining below 5%. For purely quantum models, restricted to amplitude encoding, performance was most dependent on the measurement protocol and the data-to-amplitude mapping. The measurement strategy varied the validation accuracy by up to 30% and the encoding mapping by around 8 percentage points.
comment: 20 pages, 22 figures
☆ Feature Hallucination for Self-supervised Action Recognition
Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features. We propose a deep translational action recognition framework that enhances recognition accuracy by jointly predicting action concepts and auxiliary features from RGB video frames. At test time, hallucination streams infer missing cues, enriching feature representations without increasing computational overhead. To focus on action-relevant regions beyond raw pixels, we introduce two novel domain-specific descriptors. Object Detection Features (ODF) aggregate outputs from multiple object detectors to capture contextual cues, while Saliency Detection Features (SDF) highlight spatial and intensity patterns crucial for action recognition. Our framework seamlessly integrates these descriptors with auxiliary modalities such as optical flow, Improved Dense Trajectories, skeleton data, and audio cues. It remains compatible with state-of-the-art architectures, including I3D, AssembleNet, Video Transformer Network, FASTER, and recent models like VideoMAE V2 and InternVideo2. To handle uncertainty in auxiliary features, we incorporate aleatoric uncertainty modeling in the hallucination step and introduce a robust loss function to mitigate feature noise. Our multimodal self-supervised action recognition framework achieves state-of-the-art performance on multiple benchmarks, including Kinetics-400, Kinetics-600, and Something-Something V2, demonstrating its effectiveness in capturing fine-grained action dynamics.
comment: Accepted for publication in International Journal of Computer Vision (IJCV)
☆ EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmentation, CNNs lack global context modeling due to local receptive fields, and Transformers, though capable of capturing long-range dependencies, are computationally expensive. Recently, state space models (SSMs), such as Mamba, have gained attention for their ability to model long sequences with linear complexity. In this paper, we propose EAGLE, a U-shaped network composed of a Progressive Visual State Space (PVSS) encoder and a Hybrid Visual State Space (HVSS) decoder that work collaboratively to achieve efficient and accurate segmentation of hepatic echinococcosis (HE) lesions. The proposed Convolutional Vision State Space Block (CVSSB) module is designed to fuse local and global features, while the Haar Wavelet Transformation Block (HWTB) module compresses spatial information into the channel dimension to enable lossless downsampling. Due to the lack of publicly available HE datasets, we collected CT slices from 260 patients at a local hospital. Experimental results show that EAGLE achieves state-of-the-art performance with a Dice Similarity Coefficient (DSC) of 89.76%, surpassing MSVM-UNet by 1.61%.
☆ From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents
Robust Document Layout Analysis (DLA) is critical for the automated processing and understanding of historical documents with complex page organizations. This paper benchmarks five state-of-the-art object detection architectures on three annotated datasets representing a spectrum of codicological complexity: The e-NDP, a corpus of Parisian medieval registers (1326-1504); CATMuS, a diverse multiclass dataset derived from various medieval and modern sources (ca.12th-17th centuries) and HORAE, a corpus of decorated books of hours (ca.13th-16th centuries). We evaluate two Transformer-based models (Co-DETR, Grounding DINO) against three YOLO variants (AABB, OBB, and YOLO-World). Our findings reveal significant performance variations dependent on model architecture, data set characteristics, and bounding box representation. In the e-NDP dataset, Co-DETR achieves state-of-the-art results (0.752 mAP@.50:.95), closely followed by YOLOv11X-OBB (0.721). Conversely, on the more complex CATMuS and HORAE datasets, the CNN-based YOLOv11x-OBB significantly outperforms all other models (0.564 and 0.568, respectively). This study unequivocally demonstrates that using Oriented Bounding Boxes (OBB) is not a minor refinement but a fundamental requirement for accurately modeling the non-Cartesian nature of historical manuscripts. We conclude that a key trade-off exists between the global context awareness of Transformers, ideal for structured layouts, and the superior generalization of CNN-OBB models for visually diverse and complex documents.
☆ On the Burstiness of Faces in Set
Burstiness, a phenomenon observed in text and image retrieval, refers to that particular elements appear more times in a set than a statistically independent model assumes. We argue that in the context of set-based face recognition (SFR), burstiness exists widely and degrades the performance in two aspects: Firstly, the bursty faces, where faces with particular attributes %exist frequently in a face set, dominate the training instances and dominate the training face sets and lead to poor generalization ability to unconstrained scenarios. Secondly, the bursty faces %dominating the evaluation sets interfere with the similarity comparison in set verification and identification when evaluation. To detect the bursty faces in a set, we propose three strategies based on Quickshift++, feature self-similarity, and generalized max-pooling (GMP). We apply the burst detection results on training and evaluation stages to enhance the sampling ratios or contributions of the infrequent faces. When evaluation, we additionally propose the quality-aware GMP that enables awareness of the face quality and robustness to the low-quality faces for the original GMP. We give illustrations and extensive experiments on the SFR benchmarks to demonstrate that burstiness is widespread and suppressing burstiness considerably improves the recognition performance.
comment: 18 pages, 5 figures
☆ Radiomic fingerprints for knee MR images assessment
Accurate interpretation of knee MRI scans relies on expert clinical judgment, often with high variability and limited scalability. Existing radiomic approaches use a fixed set of radiomic features (the signature), selected at the population level and applied uniformly to all patients. While interpretable, these signatures are often too constrained to represent individual pathological variations. As a result, conventional radiomic-based approaches are found to be limited in performance, compared with recent end-to-end deep learning (DL) alternatives without using interpretable radiomic features. We argue that the individual-agnostic nature in current radiomic selection is not central to its intepretability, but is responsible for the poor generalization in our application. Here, we propose a novel radiomic fingerprint framework, in which a radiomic feature set (the fingerprint) is dynamically constructed for each patient, selected by a DL model. Unlike the existing radiomic signatures, our fingerprints are derived on a per-patient basis by predicting the feature relevance in a large radiomic feature pool, and selecting only those that are predictive of clinical conditions for individual patients. The radiomic-selecting model is trained simultaneously with a low-dimensional (considered relatively explainable) logistic regression for downstream classification. We validate our methods across multiple diagnostic tasks including general knee abnormalities, anterior cruciate ligament (ACL) tears, and meniscus tears, demonstrating comparable or superior diagnostic accuracy relative to state-of-the-art end-to-end DL models. More importantly, we show that the interpretability inherent in our approach facilitates meaningful clinical insights and potential biomarker discovery, with detailed discussion, quantitative and qualitative analysis of real-world clinical cases to evidence these advantages.
☆ Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding
The hardness of learning a function that attains a target task relates to its input-sensitivity. For example, image classification tasks are input-insensitive as minor corruptions should not affect the classification results, whereas arithmetic and symbolic computation, which have been recently attracting interest, are highly input-sensitive as each input variable connects to the computation results. This study presents the first learning-based Quick Response (QR) code decoding and investigates learning functions of medium sensitivity. Our experiments reveal that Transformers can successfully decode QR codes, even beyond the theoretical error-correction limit, by learning the structure of embedded texts. They generalize from English-rich training data to other languages and even random strings. Moreover, we observe that the Transformer-based QR decoder focuses on data bits while ignoring error-correction bits, suggesting a decoding mechanism distinct from standard QR code readers.
comment: 17 pages, 13 figures
☆ FundaQ-8: A Clinically-Inspired Scoring Framework for Automated Fundus Image Quality Assessment
Automated fundus image quality assessment (FIQA) remains a challenge due to variations in image acquisition and subjective expert evaluations. We introduce FundaQ-8, a novel expert-validated framework for systematically assessing fundus image quality using eight critical parameters, including field coverage, anatomical visibility, illumination, and image artifacts. Using FundaQ-8 as a structured scoring reference, we develop a ResNet18-based regression model to predict continuous quality scores in the 0 to 1 range. The model is trained on 1800 fundus images from real-world clinical sources and Kaggle datasets, using transfer learning, mean squared error optimization, and standardized preprocessing. Validation against the EyeQ dataset and statistical analyses confirm the framework's reliability and clinical interpretability. Incorporating FundaQ-8 into deep learning models for diabetic retinopathy grading also improves diagnostic robustness, highlighting the value of quality-aware training in real-world screening applications.
☆ TDiR: Transformer based Diffusion for Image Restoration Tasks
Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in downstream tasks such as object detection, mapping, and classification. Our transformer-based diffusion model was developed to address image restoration tasks, aiming to improve the quality of degraded images. This model was evaluated against existing deep learning methodologies across multiple quality metrics for underwater image enhancement, denoising, and deraining on publicly available datasets. Our findings demonstrate that the diffusion model, combined with transformers, surpasses current methods in performance. The results of our model highlight the efficacy of diffusion models and transformers in improving the quality of degraded images, consequently expanding their utility in downstream tasks that require high-fidelity visual data.
☆ Ctrl-Z Sampling: Diffusion Sampling with Controlled Random Zigzag Explorations
Diffusion models have shown strong performance in conditional generation by progressively denoising Gaussian noise toward a target data distribution. This denoising process can be interpreted as a form of hill climbing in a learned latent space, where the model iteratively refines the sample toward regions of higher probability. However, diffusion models often converge to local optima that are locally visually coherent yet globally inconsistent or conditionally misaligned, due to latent space complexity and suboptimal initialization. Prior efforts attempted to address this by strengthening guidance signals or manipulating the initial noise distribution. We introduce Controlled Random Zigzag Sampling (Ctrl-Z Sampling), a novel sampling strategy designed to detect and escape such local maxima during conditional generation. The method first identifies potential local maxima using a reward model. Upon detection, it injects noise and reverts to a previous, noisier state to escape the current optimization plateau. The reward model then evaluates candidate trajectories, accepting only those that offer improvement, while progressively deeper retreat enables stronger escapes when nearby alternatives fail. This controlled random zigzag process allows dynamic alternation between forward refinement and backward exploration, enhancing both alignment and visual quality in the generated outputs. The proposed Ctrl-Z Sampling is model-agnostic and compatible with existing diffusion frameworks. Experimental results show that Ctrl-Z Sampling substantially improves generation quality with only around 7.6X increase in function evaluations.
comment: 10 pages, 3 figures, 2 tables
☆ Breaking Spatial Boundaries: Spectral-Domain Registration Guided Hyperspectral and Multispectral Blind Fusion
The blind fusion of unregistered hyperspectral images (HSIs) and multispectral images (MSIs) has attracted growing attention recently. To address the registration challenge, most existing methods employ spatial transformations on the HSI to achieve alignment with the MSI. However, due to the substantial differences in spatial resolution of the images, the performance of these methods is often unsatisfactory. Moreover, the registration process tends to be time-consuming when dealing with large-sized images in remote sensing. To address these issues, we propose tackling the registration problem from the spectral domain. Initially, a lightweight Spectral Prior Learning (SPL) network is developed to extract spectral features from the HSI and enhance the spectral resolution of the MSI. Following this, the obtained image undergoes spatial downsampling to produce the registered HSI. In this process, subspace representation and cyclic training strategy are employed to improve spectral accuracy of the registered HSI obtained. Next, we propose a blind sparse fusion (BSF) method, which utilizes group sparsity regularization to equivalently promote the low-rankness of the image. This approach not only circumvents the need for rank estimation, but also reduces computational complexity. Then, we employ the Proximal Alternating Optimization (PAO) algorithm to solve the BSF model, and present its convergence analysis. Finally, extensive numerical experiments on simulated and real datasets are conducted to verify the effectiveness of our method in registration and fusion. We also demonstrate its efficacy in enhancing classification performance.
☆ Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration MICCAI 2025
Osteoporosis, characterized by reduced bone mineral density (BMD) and compromised bone microstructure, increases fracture risk in aging populations. While dual-energy X-ray absorptiometry (DXA) is the clinical standard for BMD assessment, its limited accessibility hinders diagnosis in resource-limited regions. Opportunistic computed tomography (CT) analysis has emerged as a promising alternative for osteoporosis diagnosis using existing imaging data. Current approaches, however, face three limitations: (1) underutilization of unlabeled vertebral data, (2) systematic bias from device-specific DXA discrepancies, and (3) insufficient integration of clinical knowledge such as spatial BMD distribution patterns. To address these, we propose a unified deep learning framework with three innovations. First, a self-supervised learning method using radiomic representations to leverage unlabeled CT data and preserve bone texture. Second, a Mixture of Experts (MoE) architecture with learned gating mechanisms to enhance cross-device adaptability. Third, a multi-task learning framework integrating osteoporosis diagnosis, BMD regression, and vertebra location prediction. Validated across three clinical sites and an external hospital, our approach demonstrates superior generalizability and accuracy over existing methods for opportunistic osteoporosis screening and diagnosis.
comment: Accepted by MICCAI 2025
☆ From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios
Dense prediction tasks hold significant importance of computer vision, aiming to learn pixel-wise annotated label for an input image. Despite advances in this field, existing methods primarily focus on idealized conditions, with limited generalization to real-world scenarios and facing the challenging scarcity of real-world data. To systematically study this problem, we first introduce DenseWorld, a benchmark spanning a broad set of 25 dense prediction tasks that correspond to urgent real-world applications, featuring unified evaluation across tasks. Then, we propose DenseDiT, which maximally exploits generative models' visual priors to perform diverse real-world dense prediction tasks through a unified strategy. DenseDiT combines a parameter-reuse mechanism and two lightweight branches that adaptively integrate multi-scale context, working with less than 0.1% additional parameters. Evaluations on DenseWorld reveal significant performance drops in existing general and specialized baselines, highlighting their limited real-world generalization. In contrast, DenseDiT achieves superior results using less than 0.01% training data of baselines, underscoring its practical value for real-world deployment. Our data, and checkpoints and codes are available at https://xcltql666.github.io/DenseDiTProj
☆ Forensic Study of Paintings Through the Comparison of Fabrics
The study of canvas fabrics in works of art is a crucial tool for authentication, attribution and conservation. Traditional methods are based on thread density map matching, which cannot be applied when canvases do not come from contiguous positions on a roll. This paper presents a novel approach based on deep learning to assess the similarity of textiles. We introduce an automatic tool that evaluates the similarity between canvases without relying on thread density maps. A Siamese deep learning model is designed and trained to compare pairs of images by exploiting the feature representations learned from the scans. In addition, a similarity estimation method is proposed, aggregating predictions from multiple pairs of cloth samples to provide a robust similarity score. Our approach is applied to canvases from the Museo Nacional del Prado, corroborating the hypothesis that plain weave canvases, widely used in painting, can be effectively compared even when their thread densities are similar. The results demonstrate the feasibility and accuracy of the proposed method, opening new avenues for the analysis of masterpieces.
☆ X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosis MICCAI 2025
Interpretable models are crucial for supporting clinical decision-making, driving advances in their development and application for medical images. However, the nature of 3D volumetric data makes it inherently challenging to visualize and interpret intricate and complex structures like the cerebral cortex. Cortical surface renderings, on the other hand, provide a more accessible and understandable 3D representation of brain anatomy, facilitating visualization and interactive exploration. Motivated by this advantage and the widespread use of surface data for studying neurological disorders, we present the eXplainable Surface Vision Transformer (X-SiT). This is the first inherently interpretable neural network that offers human-understandable predictions based on interpretable cortical features. As part of X-SiT, we introduce a prototypical surface patch decoder for classifying surface patch embeddings, incorporating case-based reasoning with spatially corresponding cortical prototypes. The results demonstrate state-of-the-art performance in detecting Alzheimer's disease and frontotemporal dementia while additionally providing informative prototypes that align with known disease patterns and reveal classification errors.
comment: MICCAI 2025
☆ Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification
Few-shot fine-grained image classification (FS-FGIC) presents a significant challenge, requiring models to distinguish visually similar subclasses with limited labeled examples. Existing methods have critical limitations: metric-based methods lose spatial information and misalign local features, while reconstruction-based methods fail to utilize hierarchical feature information and lack mechanisms to focus on discriminative regions. We propose the Hierarchical Mask-enhanced Dual Reconstruction Network (HMDRN), which integrates dual-layer feature reconstruction with mask-enhanced feature processing to improve fine-grained classification. HMDRN incorporates a dual-layer feature reconstruction and fusion module that leverages complementary visual information from different network hierarchies. Through learnable fusion weights, the model balances high-level semantic representations from the last layer with mid-level structural details from the penultimate layer. Additionally, we design a spatial binary mask-enhanced transformer self-reconstruction module that processes query features through adaptive thresholding while maintaining complete support features, enhancing focus on discriminative regions while filtering background noise. Extensive experiments on three challenging fine-grained datasets demonstrate that HMDRN consistently outperforms state-of-the-art methods across Conv-4 and ResNet-12 backbone architectures. Comprehensive ablation studies validate the effectiveness of each proposed component, revealing that dual-layer reconstruction enhances inter-class discrimination while mask-enhanced transformation reduces intra-class variations. Visualization results provide evidence of HMDRN's superior feature reconstruction capabilities.
☆ A Transformer Based Handwriting Recognition System Jointly Using Online and Offline Features
We posit that handwriting recognition benefits from complementary cues carried by the rasterized complex glyph and the pen's trajectory, yet most systems exploit only one modality. We introduce an end-to-end network that performs early fusion of offline images and online stroke data within a shared latent space. A patch encoder converts the grayscale crop into fixed-length visual tokens, while a lightweight transformer embeds the $(x, y, \text{pen})$ sequence. Learnable latent queries attend jointly to both token streams, yielding context-enhanced stroke embeddings that are pooled and decoded under a cross-entropy loss objective. Because integration occurs before any high-level classification, temporal cues reinforce each other during representation learning, producing stronger writer independence. Comprehensive experiments on IAMOn-DB and VNOn-DB demonstrate that our approach achieves state-of-the-art accuracy, exceeding previous bests by up to 1\%. Our study also shows adaptation of this pipeline with gesturification on the ISI-Air dataset. Our code can be found here.
comment: 15 pages, 7 figures
☆ Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement MICCAI 2025
The complexity and diversity of surgical workflows, driven by heterogeneous operating room settings, institutional protocols, and anatomical variability, present a significant challenge in developing generalizable models for cross-institutional and cross-procedural surgical understanding. While recent surgical foundation models pretrained on large-scale vision-language data offer promising transferability, their zero-shot performance remains constrained by domain shifts, limiting their utility in unseen surgical environments. To address this, we introduce Surgical Phase Anywhere (SPA), a lightweight framework for versatile surgical workflow understanding that adapts foundation models to institutional settings with minimal annotation. SPA leverages few-shot spatial adaptation to align multi-modal embeddings with institution-specific surgical scenes and phases. It also ensures temporal consistency through diffusion modeling, which encodes task-graph priors derived from institutional procedure protocols. Finally, SPA employs dynamic test-time adaptation, exploiting the mutual agreement between multi-modal phase prediction streams to adapt the model to a given test video in a self-supervised manner, enhancing the reliability under test-time distribution shifts. SPA is a lightweight adaptation framework, allowing hospitals to rapidly customize phase recognition models by defining phases in natural language text, annotating a few images with the phase labels, and providing a task graph defining phase transitions. The experimental results show that the SPA framework achieves state-of-the-art performance in few-shot surgical phase recognition across multiple institutions and procedures, even outperforming full-shot models with 32-shot labeled data. Code is available at https://github.com/CAMMA-public/SPA
comment: Accepted by MICCAI 2025
☆ FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data
Federated learning (FL) is a decentralized collaborative machine learning (ML) technique. It provides a solution to the issues of isolated data islands and data privacy leakage in industrial ML practices. One major challenge in FL is handling the non-identical and independent distributed (non-IID) data. Current solutions either focus on constructing an all-powerful global model, or customizing personalized local models. Few of them can provide both a well-generalized global model and well-performed local models at the same time. Additionally, many FL solutions to the non-IID problem are benefited from introducing public datasets. However, this will also increase the risk of data leakage. To tackle the problems, we propose a novel data-free distillation framework, Federated Bidirectional Knowledge Distillation (FedBKD). Specifically, we train Generative Adversarial Networks (GAN) for synthetic data. During the GAN training, local models serve as discriminators and their parameters are frozen. The synthetic data is then used for bidirectional distillation between global and local models to achieve knowledge interactions so that performances for both sides are improved. We conduct extensive experiments on 4 benchmarks under different non-IID settings. The results show that FedBKD achieves SOTA performances in every case.
☆ Dynamic Bandwidth Allocation for Hybrid Event-RGB Transmission
Event cameras asynchronously capture pixel-level intensity changes with extremely low latency. They are increasingly used in conjunction with RGB cameras for a wide range of vision-related applications. However, a major challenge in these hybrid systems lies in the transmission of the large volume of triggered events and RGB images. To address this, we propose a transmission scheme that retains efficient reconstruction performance of both sources while accomplishing real-time deblurring in parallel. Conventional RGB cameras and event cameras typically capture the same scene in different ways, often resulting in significant redundant information across their outputs. To address this, we develop a joint event and image (E-I) transmission framework to eliminate redundancy and thereby optimize channel bandwidth utilization. Our approach employs Bayesian modeling and the information bottleneck method to disentangle the shared and domain-specific information within the E-I inputs. This disentangled information bottleneck framework ensures both the compactness and informativeness of extracted shared and domain-specific information. Moreover, it adaptively allocates transmission bandwidth based on scene dynamics, i.e., more symbols are allocated to events for dynamic details or to images for static information. Simulation results demonstrate that the proposed scheme not only achieves superior reconstruction quality compared to conventional systems but also delivers enhanced deblurring performance.
☆ UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existing codebook-based methods either rely on small vocabularies (~16K entries) that lack fine-grained semantics or naively scale up, resulting in low token utilization and unstable training. We propose UniCode$^2$, a cascaded codebook framework enabling large-scale, semantically aligned, and stable visual tokenization. By clustering millions of SigLIP sequence embeddings, we build a 500K-entry codebook that preserves vision-language alignment while expanding capacity. Stability is ensured via a cascaded design: a frozen codebook anchors the embedding space, and a trainable codebook refines task-specific semantics. This decoupling promotes high utilization and robust learning. Moreover, the alignment of our visual tokens with textual semantics enables seamless integration with pretrained diffusion decoders, supporting high-quality visual synthesis with minimal adaptation. UniCode^2 delivers strong performance across diverse benchmarks, demonstrating the viability of scaling visual token spaces without sacrificing stability, semantics, or modularity.
comment: 19 pages, 5 figures
☆ MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment MICCAI 2025
Positron Emission Tomography / Computed Tomography (PET/CT) plays a critical role in medical imaging, combining functional and anatomical information to aid in accurate diagnosis. However, image quality degradation due to noise, compression and other factors could potentially lead to diagnostic uncertainty and increase the risk of misdiagnosis. When evaluating the quality of a PET/CT image, both low-level features like distortions and high-level features like organ anatomical structures affect the diagnostic value of the image. However, existing medical image quality assessment (IQA) methods are unable to account for both feature types simultaneously. In this work, we propose MS-IQA, a novel multi-scale feature fusion network for PET/CT IQA, which utilizes multi-scale features from various intermediate layers of ResNet and Swin Transformer, enhancing its ability of perceiving both local and global information. In addition, a multi-scale feature fusion module is also introduced to effectively combine high-level and low-level information through a dynamically weighted channel attention mechanism. Finally, to fill the blank of PET/CT IQA dataset, we construct PET-CT-IQA-DS, a dataset containing 2,700 varying-quality PET/CT images with quality scores assigned by radiologists. Experiments on our dataset and the publicly available LDCTIQAC2023 dataset demonstrate that our proposed model has achieved superior performance against existing state-of-the-art methods in various IQA metrics. This work provides an accurate and efficient IQA method for PET/CT. Our code and dataset are available at https://github.com/MS-IQA/MS-IQA/.
comment: Accepted to MICCAI 2025
☆ Progressive Alignment Degradation Learning for Pansharpening
Deep learning-based pansharpening has been shown to effectively generate high-resolution multispectral (HRMS) images. To create supervised ground-truth HRMS images, synthetic data generated using the Wald protocol is commonly employed. This protocol assumes that networks trained on artificial low-resolution data will perform equally well on high-resolution data. However, well-trained models typically exhibit a trade-off in performance between reduced-resolution and full-resolution datasets. In this paper, we delve into the Wald protocol and find that its inaccurate approximation of real-world degradation patterns limits the generalization of deep pansharpening models. To address this issue, we propose the Progressive Alignment Degradation Module (PADM), which uses mutual iteration between two sub-networks, PAlignNet and PDegradeNet, to adaptively learn accurate degradation processes without relying on predefined operators. Building on this, we introduce HFreqdiff, which embeds high-frequency details into a diffusion framework and incorporates CFB and BACM modules for frequency-selective detail extraction and precise reverse process learning. These innovations enable effective integration of high-resolution panchromatic and multispectral images, significantly enhancing spatial sharpness and quality. Experiments and ablation studies demonstrate the proposed method's superior performance compared to state-of-the-art techniques.
comment: 13 pages, 9 figures
☆ Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
Recent advancements in multimodal large language models have enhanced document understanding by integrating textual and visual information. However, existing models exhibit incompleteness within their paradigm in real-world scenarios, particularly under visual degradation. In such conditions, the current response paradigm often fails to adequately perceive visual degradation and ambiguity, leading to overreliance on linguistic priors or misaligned visual-textual reasoning. This difficulty in recognizing uncertainty frequently results in the generation of hallucinatory content, especially when a precise answer is not feasible. To better demonstrate and analyze this phenomenon and problem, we propose KIE-HVQA, the first benchmark dedicated to evaluating OCR hallucination in degraded document understanding. This dataset includes test samples spanning identity cards and invoices, with simulated real-world degradations for OCR reliability. This setup allows for evaluating models' capacity, under degraded input, to distinguish reliable visual information and answer accordingly, thereby highlighting the challenge of avoiding hallucination on uncertain data. To achieve vision-faithful reasoning and thereby avoid the aforementioned issues, we further introduce a GRPO-based framework featuring a novel reward mechanism. By incorporating a self-awareness of visual uncertainty and an analysis method that initiates refusal to answer to increase task difficulty within our supervised fine-tuning and reinforcement learning framework, we successfully mitigated hallucinations in ambiguous regions. Experiments on Qwen2.5-VL demonstrate that our 7B-parameter model achieves a 22\% absolute improvement in hallucination-free accuracy over GPT-4o on KIE-HVQA and there is no significant performance drop in standard tasks, highlighting both effectiveness and robustness.
☆ Towards Efficient Exemplar Based Image Editing with Multimodal VLMs ECCV 2024
Text-to-Image Diffusion models have enabled a wide array of image editing applications. However, capturing all types of edits through text alone can be challenging and cumbersome. The ambiguous nature of certain image edits is better expressed through an exemplar pair, i.e., a pair of images depicting an image before and after an edit respectively. In this work, we tackle exemplar-based image editing -- the task of transferring an edit from an exemplar pair to a content image(s), by leveraging pretrained text-to-image diffusion models and multimodal VLMs. Even though our end-to-end pipeline is optimization-free, our experiments demonstrate that it still outperforms baselines on multiple types of edits while being ~4x faster.
comment: Accepted at ECCV 2024 (AI4VA Workshop)
☆ Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration
Structured pruning is a well-established technique for compressing neural networks, making it suitable for deployment in resource-limited edge devices. This paper presents an efficient Loss-Aware Automatic Selection of Structured Pruning Criteria (LAASP) for slimming and accelerating deep neural networks. The majority of pruning methodologies employ a sequential process consisting of three stages: 1) training, 2) pruning, and 3) fine-tuning, whereas the proposed pruning technique adopts a pruning-while-training approach that eliminates the first stage and integrates the second and third stages into a single cycle. The automatic selection of magnitude or similarity-based filter pruning criteria from a specified pool of criteria and the specific pruning layer at each pruning iteration is guided by the network's overall loss on a small subset of the training data. To mitigate the abrupt accuracy drop due to pruning, the network is retrained briefly after each reduction of a predefined number of floating-point operations (FLOPs). The optimal pruning rates for each layer in the network are automatically determined, eliminating the need for manual allocation of fixed or variable pruning rates for each layer. Experiments on the VGGNet and ResNet models on the CIFAR-10 and ImageNet benchmark datasets demonstrate the effectiveness of the proposed method. In particular, the ResNet56 and ResNet110 models on the CIFAR-10 dataset significantly improve the top-1 accuracy compared to state-of-the-art methods while reducing the network FLOPs by 52\%. Furthermore, the ResNet50 model on the ImageNet dataset reduces FLOPs by more than 42\% with a negligible 0.33\% drop in top-5 accuracy. The source code of this paper is publicly available online - https://github.com/ghimiredhikura/laasp.
☆ EAR: Erasing Concepts from Unified Autoregressive Models
Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR models while maintaining overall generation quality remains an open challenge. In this paper, we propose Erasure Autoregressive Model (EAR), a fine-tuning method for effective and utility-preserving concept erasure in AR models. Specifically, we introduce Windowed Gradient Accumulation (WGA) strategy to align patch-level decoding with erasure objectives, and Thresholded Loss Masking (TLM) strategy to protect content unrelated to the target concept during fine-tuning. Furthermore, we propose a novel benchmark, Erase Concept Generator and Visual Filter (ECGVF), aim at provide a more rigorous and comprehensive foundation for evaluating concept erasure in AR models. Specifically, we first employ structured templates across diverse large language models (LLMs) to pre-generate a large-scale corpus of target-replacement concept prompt pairs. Subsequently, we generate images from these prompts and subject them to rigorous filtering via a visual classifier to ensure concept fidelity and alignment. Extensive experimental results conducted on the ECGVF benchmark with the AR model Janus-Pro demonstrate that EAR achieves marked improvements in both erasure effectiveness and model utility preservation. Code is available at: https://github.com/immc-lab/ear/
comment: 11 pages, 7 figures, 1 tables
☆ From 2D to 3D Cognition: A Brief Survey of General World Models
World models have garnered increasing attention in the development of artificial general intelligence (AGI), serving as computational frameworks for learning representations of the external world and forecasting future states. While early efforts focused on 2D visual perception and simulation, recent 3D-aware generative world models have demonstrated the ability to synthesize geometrically consistent, interactive 3D environments, marking a shift toward 3D spatial cognition. Despite rapid progress, the field lacks systematic analysis to categorize emerging techniques and clarify their roles in advancing 3D cognitive world models. This survey addresses this need by introducing a conceptual framework, providing a structured and forward-looking review of world models transitioning from 2D perception to 3D cognition. Within this framework, we highlight two key technological drivers, particularly advances in 3D representations and the incorporation of world knowledge, as fundamental pillars. Building on these, we dissect three core cognitive capabilities that underpin 3D world modeling: 3D physical scene generation, 3D spatial reasoning, and 3D spatial interaction. We further examine the deployment of these capabilities in real-world applications, including embodied AI, autonomous driving, digital twin, and gaming/VR. Finally, we identify challenges across data, modeling, and deployment, and outline future directions for advancing more robust and generalizable 3D world models.
☆ BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos
Recent advances in deep generative models have led to significant progress in video generation, yet the fidelity of AI-generated videos remains limited. Synthesized content often exhibits visual artifacts such as temporally inconsistent motion, physically implausible trajectories, unnatural object deformations, and local blurring that undermine realism and user trust. Accurate detection and spatial localization of these artifacts are crucial for both automated quality control and for guiding the development of improved generative models. However, the research community currently lacks a comprehensive benchmark specifically designed for artifact localization in AI generated videos. Existing datasets either restrict themselves to video or frame level detection or lack the fine-grained spatial annotations necessary for evaluating localization methods. To address this gap, we introduce BrokenVideos, a benchmark dataset of 3,254 AI-generated videos with meticulously annotated, pixel-level masks highlighting regions of visual corruption. Each annotation is validated through detailed human inspection to ensure high quality ground truth. Our experiments show that training state of the art artifact detection models and multi modal large language models (MLLMs) on BrokenVideos significantly improves their ability to localize corrupted regions. Through extensive evaluation, we demonstrate that BrokenVideos establishes a critical foundation for benchmarking and advancing research on artifact localization in generative video models. The dataset is available at: https://broken-video-detection-datetsets.github.io/Broken-Video-Detection-Datasets.github.io/.
comment: 7 page,4 figures,2 tables
☆ MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the agriculture domain, MIRAGE captures the full complexity of expert consultations by combining natural user queries, expert-authored responses, and image-based context, offering a high-fidelity benchmark for evaluating models on grounded reasoning, clarification strategies, and long-form generation in a real-world, knowledge-intensive domain. Grounded in over 35,000 real user-expert interactions and curated through a carefully designed multi-step pipeline, MIRAGE spans diverse crop health, pest diagnosis, and crop management scenarios. The benchmark includes more than 7,000 unique biological entities, covering plant species, pests, and diseases, making it one of the most taxonomically diverse benchmarks available for vision-language models, grounded in the real world. Unlike existing benchmarks that rely on well-specified user inputs and closed-set taxonomies, MIRAGE features underspecified, context-rich scenarios with open-world settings, requiring models to infer latent knowledge gaps, handle rare entities, and either proactively guide the interaction or respond. Project Page: https://mirage-benchmark.github.io
comment: 66 pages, 32 figures, 23 tables
♻ ☆ One Prototype Is Enough: Single-Prototype Activation for Interpretable Image Classification
In this paper, we propose ProtoSolo, a novel deep neural architecture for interpretable image classification inspired by prototypical networks such as ProtoPNet. Existing prototype networks usually rely on the collaborative decision-making of multiple prototypes to achieve the classification and interpretation of a single category. In contrast, ProtoSolo only requires the activation of a single prototype to complete the classification. This allows the network to explain each category decision by only providing the features that are most similar to the prototype of that category, significantly reducing the cognitive complexity of the explanation. Secondly, we propose a feature-based comparison method, which uses feature map instead of full-channel feature vector as the object of similarity comparison and prototype learning. This design enables ProtoSolo to utilize richer global information for classification while relying on a single prototype activation. In addition, we propose a non-prototype projection learning strategy, which preserves the information association between the prototype and the training image patches while avoiding the sharp change of the network structure caused by the projection operation, thus avoiding its negative impact on the classification performance. Experiments on the CUB-200-2011 and Stanford Cars datasets show that ProtoSolo achieves superior performance in classification tasks and reaches the best level in terms of cognitive complexity of explanations compared to state-of-the-art interpretable methods. The code is available at https://github.com/pyt19/ProtoSolo.
♻ ☆ ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
Advancements in 3D scene reconstruction have transformed 2D images from the real world into 3D models, producing realistic 3D results from hundreds of input photos. Despite great success in dense-view reconstruction scenarios, rendering a detailed scene from insufficient captured views is still an ill-posed optimization problem, often resulting in artifacts and distortions in unseen areas. In this paper, we propose ReconX, a novel 3D scene reconstruction paradigm that reframes the ambiguous reconstruction challenge as a temporal generation task. The key insight is to unleash the strong generative prior of large pre-trained video diffusion models for sparse-view reconstruction. However, 3D view consistency struggles to be accurately preserved in directly generated video frames from pre-trained models. To address this, given limited input views, the proposed ReconX first constructs a global point cloud and encodes it into a contextual space as the 3D structure condition. Guided by the condition, the video diffusion model then synthesizes video frames that are both detail-preserved and exhibit a high degree of 3D consistency, ensuring the coherence of the scene from various perspectives. Finally, we recover the 3D scene from the generated video through a confidence-aware 3D Gaussian Splatting optimization scheme. Extensive experiments on various real-world datasets show the superiority of our ReconX over state-of-the-art methods in terms of quality and generalizability.
comment: Project page: https://liuff19.github.io/ReconX
♻ ☆ Self-Supervised Multimodal NeRF for Autonomous Driving
In this paper, we propose a Neural Radiance Fields (NeRF) based framework, referred to as Novel View Synthesis Framework (NVSF). It jointly learns the implicit neural representation of space and time-varying scene for both LiDAR and Camera. We test this on a real-world autonomous driving scenario containing both static and dynamic scenes. Compared to existing multimodal dynamic NeRFs, our framework is self-supervised, thus eliminating the need for 3D labels. For efficient training and faster convergence, we introduce heuristic-based image pixel sampling to focus on pixels with rich information. To preserve the local features of LiDAR points, a Double Gradient based mask is employed. Extensive experiments on the KITTI-360 dataset show that, compared to the baseline models, our framework has reported best performance on both LiDAR and Camera domain. Code of the model is available at https://github.com/gaurav00700/Selfsupervised-NVSF
♻ ☆ Sampling Matters in Explanations: Towards Trustworthy Attribution Analysis Building Block in Visual Models through Maximizing Explanation Certainty
Image attribution analysis seeks to highlight the feature representations learned by visual models such that the highlighted feature maps can reflect the pixel-wise importance of inputs. Gradient integration is a building block in the attribution analysis by integrating the gradients from multiple derived samples to highlight the semantic features relevant to inferences. Such a building block often combines with other information from visual models such as activation or attention maps to form ultimate explanations. Yet, our theoretical analysis demonstrates that the extent to the alignment of the sample distribution in gradient integration with respect to natural image distribution gives a lower bound of explanation certainty. Prior works add noise into images as samples and the noise distributions can lead to low explanation certainty. Counter-intuitively, our experiment shows that extra information can saturate neural networks. To this end, building trustworthy attribution analysis needs to settle the sample distribution misalignment problem. Instead of adding extra information into input images, we present a semi-optimal sampling approach by suppressing features from inputs. The sample distribution by suppressing features is approximately identical to the distribution of natural images. Our extensive quantitative evaluation on large scale dataset ImageNet affirms that our approach is effective and able to yield more satisfactory explanations against state-of-the-art baselines throughout all experimental models.
comment: Code: https://anonymous.4open.science/r/sampling_matters_reproducibility-BB60/
♻ ☆ EvDetMAV: Generalized MAV Detection from Moving Event Cameras
Existing micro aerial vehicle (MAV) detection methods mainly rely on the target's appearance features in RGB images, whose diversity makes it difficult to achieve generalized MAV detection. We notice that different types of MAVs share the same distinctive features in event streams due to their high-speed rotating propellers, which are hard to see in RGB images. This paper studies how to detect different types of MAVs from an event camera by fully exploiting the features of propellers in the original event stream. The proposed method consists of three modules to extract the salient and spatio-temporal features of the propellers while filtering out noise from background objects and camera motion. Since there are no existing event-based MAV datasets, we introduce a novel MAV dataset for the community. This is the first event-based MAV dataset comprising multiple scenarios and different types of MAVs. Without training, our method significantly outperforms state-of-the-art methods and can deal with challenging scenarios, achieving a precision rate of 83.0\% (+30.3\%) and a recall rate of 81.5\% (+36.4\%) on the proposed testing dataset. The dataset and code are available at: https://github.com/WindyLab/EvDetMAV.
comment: 8 pages, 7 figures. This paper is accepted by IEEE Robotics and Automation Letters
♻ ☆ OmniGen2: Exploration to Advanced Multimodal Generation
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2
♻ ☆ Diffusion Models Through a Global Lens: Are They Culturally Inclusive?
Text-to-image diffusion models have recently enabled the creation of visually compelling, detailed images from textual prompts. However, their ability to accurately represent various cultural nuances remains an open question. In our work, we introduce CultDiff benchmark, evaluating state-of-the-art diffusion models whether they can generate culturally specific images spanning ten countries. We show that these models often fail to generate cultural artifacts in architecture, clothing, and food, especially for underrepresented country regions, by conducting a fine-grained analysis of different similarity aspects, revealing significant disparities in cultural relevance, description fidelity, and realism compared to real-world reference images. With the collected human evaluations, we develop a neural-based image-image similarity metric, namely, CultDiff-S, to predict human judgment on real and generated images with cultural artifacts. Our work highlights the need for more inclusive generative AI systems and equitable dataset representation over a wide range of cultures.
comment: 17 pages, 17 figures, 3 tables
♻ ☆ From $\mathcal{O}(n^{2})$ to $\mathcal{O}(n)$ Parameters: Quantum Self-Attention in Vision Transformers for Biomedical Image Classification MICCAI 2025
We demonstrate that quantum vision transformers (QViTs), vision transformers (ViTs) with self-attention (SA) mechanisms replaced by quantum self-attention (QSA) mechanisms, can match state-of-the-art (SOTA) biomedical image classifiers while using 99.99% fewer parameters. QSAs are produced by replacing linear SA layers with parameterised quantum neural networks (QNNs), producing a QSA mechanism and reducing parameter scaling from $\mathcal{O}(n^2)$ to $\mathcal{O}(n)$. On RetinaMNIST, our ultra parameter-efficient QViT outperforms 13/14 SOTA methods including CNNs and ViTs, achieving 56.5% accuracy, just 0.88% below the top MedMamba model while using 99.99% fewer parameters (1K vs 14.5M) and 89% fewer GFLOPs. We present the first investigation of knowledge distillation (KD) from classical to quantum vision transformers in biomedical image classification, showing that QViTs maintain comparable performance to classical ViTs across eight diverse datasets spanning multiple modalities, with improved QSA parameter-efficiency. Our higher-qubit architecture benefitted more from KD pre-training, suggesting a scaling relationship between QSA parameters and KD effectiveness. These findings establish QSA as a practical architectural choice toward parameter-efficient biomedical image analysis.
comment: Submitted for EMA4MICCAI 2025
♻ ☆ Time-Aware Auto White Balance in Mobile Photography
Cameras rely on auto white balance (AWB) to correct undesirable color casts caused by scene illumination and the camera's spectral sensitivity. This is typically achieved using an illuminant estimator that determines the global color cast solely from the color information in the camera's raw sensor image. Mobile devices provide valuable additional metadata-such as capture timestamp and geolocation-that offers strong contextual clues to help narrow down the possible illumination solutions. This paper proposes a lightweight illuminant estimation method that incorporates such contextual metadata, along with additional capture information and image colors, into a compact model (~5K parameters), achieving promising results, matching or surpassing larger models. To validate our method, we introduce a dataset of 3,224 smartphone images with contextual metadata collected at various times of day and under diverse lighting conditions. The dataset includes ground-truth illuminant colors, determined using a color chart, and user-preferred illuminants validated through a user study, providing a comprehensive benchmark for AWB evaluation.
♻ ☆ FluoroSAM: A Language-promptable Foundation Model for Flexible X-ray Image Segmentation
Language promptable X-ray image segmentation would enable greater flexibility for human-in-the-loop workflows in diagnostic and interventional precision medicine. Prior efforts have contributed task-specific models capable of solving problems within a narrow scope, but expanding to broader use requires additional data, annotations, and training time. Recently, language-aligned foundation models (LFMs) -- machine learning models trained on large amounts of highly variable image and text data thus enabling broad applicability -- have emerged as promising tools for automated image analysis. Existing foundation models for medical image analysis focus on scenarios and modalities where large, richly annotated datasets are available. However, the X-ray imaging modality features highly variable image appearance and applications, from diagnostic chest X-rays to interventional fluoroscopy, with varying availability of data. To pave the way toward an LFM for comprehensive and language-aligned analysis of arbitrary medical X-ray images, we introduce FluoroSAM, a language-promptable variant of the Segment Anything Model, trained from scratch on 3M synthetic X-ray images from a wide variety of human anatomies, imaging geometries, and viewing angles. These include pseudo-ground truth masks for 128 organ types and 464 tools with associated text descriptions. FluoroSAM is capable of segmenting myriad anatomical structures and tools based on natural language prompts, thanks to the novel incorporation of vector quantization (VQ) of text embeddings in the training process. We demonstrate FluoroSAM's performance quantitatively on real X-ray images and showcase on several applications how FluoroSAM is a key enabler for rich human-machine interaction in the X-ray image acquisition and analysis context. Code is available at https://github.com/arcadelab/fluorosam.
♻ ☆ Dark Channel-Assisted Depth-from-Defocus from a Single Image
We estimate scene depth from a single defocus-blurred image using the dark channel as a complementary cue, leveraging its ability to capture local statistics and scene structure. Traditional depth-from-defocus (DFD) methods use multiple images with varying apertures or focus. Single-image DFD is underexplored due to its inherent challenges. Few attempts have focused on depth-from-defocus (DFD) from a single defocused image because the problem is underconstrained. Our method uses the relationship between local defocus blur and contrast variations as depth cues to improve scene structure estimation. The pipeline is trained end-to-end with adversarial learning. Experiments on real data demonstrate that incorporating the dark channel prior into single-image DFD provides meaningful depth estimation, validating our approach.
♻ ☆ Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models
Fine-tuning Video Diffusion Models (VDMs) at the user level to generate videos that reflect specific attributes of training data presents notable challenges, yet remains underexplored despite its practical importance. Meanwhile, recent work such as Representation Alignment (REPA) has shown promise in improving the convergence and quality of DiT-based image diffusion models by aligning, or assimilating, its internal hidden states with external pretrained visual features, suggesting its potential for VDM fine-tuning. In this work, we first propose a straightforward adaptation of REPA for VDMs and empirically show that, while effective for convergence, it is suboptimal in preserving semantic consistency across frames. To address this limitation, we introduce Cross-frame Representation Alignment (CREPA), a novel regularization technique that aligns hidden states of a frame with external features from neighboring frames. Empirical evaluations on large-scale VDMs, including CogVideoX-5B and Hunyuan Video, demonstrate that CREPA improves both visual fidelity and cross-frame semantic coherence when fine-tuned with parameter-efficient methods such as LoRA. We further validate CREPA across diverse datasets with varying attributes, confirming its broad applicability.
comment: Project page: https://crepavideo.github.io
♻ ☆ PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms
Panoramic video generation enables immersive 360{\deg} content creation, valuable in applications that demand scene-consistent world exploration. However, existing panoramic video generation models struggle to leverage pre-trained generative priors from conventional text-to-video models for high-quality and diverse panoramic videos generation, due to limited dataset scale and the gap in spatial feature representations. In this paper, we introduce PanoWan to effectively lift pre-trained text-to-video models to the panoramic domain, equipped with minimal modules. PanoWan employs latitude-aware sampling to avoid latitudinal distortion, while its rotated semantic denoising and padded pixel-wise decoding ensure seamless transitions at longitude boundaries. To provide sufficient panoramic videos for learning these lifted representations, we contribute PanoVid, a high-quality panoramic video dataset with captions and diverse scenarios. Consequently, PanoWan achieves state-of-the-art performance in panoramic video generation and demonstrates robustness for zero-shot downstream tasks. Our project page is available at https://panowan.variantconst.com.
♻ ☆ ViStoryBench: Comprehensive Benchmark Suite for Story Visualization
Story visualization, which aims to generate a sequence of visually coherent images aligning with a given narrative and reference images, has seen significant progress with recent advancements in generative models. To further enhance the performance of story visualization frameworks in real-world scenarios, we introduce a comprehensive evaluation benchmark, ViStoryBench. We collect a diverse dataset encompassing various story types and artistic styles, ensuring models are evaluated across multiple dimensions such as different plots (e.g., comedy, horror) and visual aesthetics (e.g., anime, 3D renderings). ViStoryBench is carefully curated to balance narrative structures and visual elements, featuring stories with single and multiple protagonists to test models' ability to maintain character consistency. Additionally, it includes complex plots and intricate world-building to challenge models in generating accurate visuals. To ensure comprehensive comparisons, our benchmark incorporates a wide range of evaluation metrics assessing critical aspects. This structured and multifaceted framework enables researchers to thoroughly identify both the strengths and weaknesses of different models, fostering targeted improvements.
comment: 33 Pages, Project Page: https://vistorybench.github.io/, Code: https://github.com/vistorybench/vistorybench
♻ ☆ LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs through label propagation, which jointly optimizes predictions by incorporating patch-to-patch relationships. Since VLMs are primarily optimized for cross-modal alignment and not for intra-modal similarity, we use a Vision Model (VM) that is observed to better capture these relationships. We address resolution limitations inherent to patch-based encoders by applying label propagation at the pixel level as a refinement step, significantly improving segmentation accuracy near class boundaries. Our method, called LPOSS+, performs inference over the entire image, avoiding window-based processing and thereby capturing contextual interactions across the full image. LPOSS+ achieves state-of-the-art performance among training-free methods, across a diverse set of datasets. Code: https://github.com/vladan-stojnic/LPOSS
♻ ☆ MatSwap: Light-aware material transfers in images
We present MatSwap, a method to transfer materials to designated surfaces in an image photorealistically. Such a task is non-trivial due to the large entanglement of material appearance, geometry, and lighting in a photograph. In the literature, material editing methods typically rely on either cumbersome text engineering or extensive manual annotations requiring artist knowledge and 3D scene properties that are impractical to obtain. In contrast, we propose to directly learn the relationship between the input material -- as observed on a flat surface -- and its appearance within the scene, without the need for explicit UV mapping. To achieve this, we rely on a custom light- and geometry-aware diffusion model. We fine-tune a large-scale pre-trained text-to-image model for material transfer using our synthetic dataset, preserving its strong priors to ensure effective generalization to real images. As a result, our method seamlessly integrates a desired material into the target location in the photograph while retaining the identity of the scene. We evaluate our method on synthetic and real images and show that it compares favorably to recent work both qualitatively and quantitatively. We release our code and data on https://github.com/astra-vision/MatSwap
comment: Accepted to EGSR, journal track to appear in Computer Graphics Forum
♻ ☆ MagicPose4D: Crafting Articulated Models with Appearance and Motion Control
With the success of 2D and 3D visual generative models, there is growing interest in generating 4D content. Existing methods primarily rely on text prompts to produce 4D content, but they often fall short of accurately defining complex or rare motions. To address this limitation, we propose MagicPose4D, a novel framework for refined control over both appearance and motion in 4D generation. Unlike current 4D generation methods, MagicPose4D accepts monocular videos or mesh sequences as motion prompts, enabling precise and customizable motion control. MagicPose4D comprises two key modules: (i) Dual-Phase 4D Reconstruction Module, which operates in two phases. The first phase focuses on capturing the model's shape using accurate 2D supervision and less accurate but geometrically informative 3D pseudo-supervision without imposing skeleton constraints. The second phase extracts the 3D motion (skeleton poses) using more accurate pseudo-3D supervision, obtained in the first phase and introduces kinematic chain-based skeleton constraints to ensure physical plausibility. Additionally, we propose a Global-local Chamfer loss that aligns the overall distribution of predicted mesh vertices with the supervision while maintaining part-level alignment without extra annotations. (ii) Cross-category Motion Transfer Module, which leverages the extracted motion from the 4D reconstruction module and uses a kinematic-chain-based skeleton to achieve cross-category motion transfer. It ensures smooth transitions between frames through dynamic rigidity, facilitating robust generalization without additional training. Through extensive experiments, we demonstrate that MagicPose4D significantly improves the accuracy and consistency of 4D content generation, outperforming existing methods in various benchmarks.
comment: Project Page: https://magicpose4d.github.io/
♻ ☆ CLAIM: Clinically-Guided LGE Augmentation for Realistic and Diverse Myocardial Scar Synthesis and Segmentation
Deep learning-based myocardial scar segmentation from late gadolinium enhancement (LGE) cardiac MRI has shown great potential for accurate and timely diagnosis and treatment planning for structural cardiac diseases. However, the limited availability and variability of LGE images with high-quality scar labels restrict the development of robust segmentation models. To address this, we introduce CLAIM: \textbf{C}linically-Guided \textbf{L}GE \textbf{A}ugmentation for Real\textbf{i}stic and Diverse \textbf{M}yocardial Scar Synthesis and Segmentation framework, a framework for anatomically grounded scar generation and segmentation. At its core is the SMILE module (Scar Mask generation guided by cLinical knowledgE), which conditions a diffusion-based generator on the clinically adopted AHA 17-segment model to synthesize images with anatomically consistent and spatially diverse scar patterns. In addition, CLAIM employs a joint training strategy in which the scar segmentation network is optimized alongside the generator, aiming to enhance both the realism of synthesized scars and the accuracy of the scar segmentation performance. Experimental results show that CLAIM produces anatomically coherent scar patterns and achieves higher Dice similarity with real scar distributions compared to baseline models. Our approach enables controllable and realistic myocardial scar synthesis and has demonstrated utility for downstream medical imaging task. Code is available at https://github.com/farheenjabeen/CLAIM-Scar-Synthesis.
comment: 14 Pages
♻ ☆ LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical Images MICCAI 2025
Autoregressive Initial Bits is a framework that integrates sub-image autoregression and latent variable modeling, demonstrating its advantages in lossless medical image compression. However, in existing methods, the image segmentation process leads to an even distribution of latent variable information across each sub-image, which in turn causes posterior collapse and inefficient utilization of latent variables. To deal with these issues, we propose a prediction-based end-to-end lossless medical image compression method named LVPNet, leveraging global latent variables to predict pixel values and encoding predicted probabilities for lossless compression. Specifically, we introduce the Global Multi-scale Sensing Module (GMSM), which extracts compact and informative latent representations from the entire image, effectively capturing spatial dependencies within the latent space. Furthermore, to mitigate the information loss introduced during quantization, we propose the Quantization Compensation Module (QCM), which learns the distribution of quantization errors and refines the quantized features to compensate for quantization loss. Extensive experiments on challenging benchmarks demonstrate that our method achieves superior compression efficiency compared to state-of-the-art lossless image compression approaches, while maintaining competitive inference speed. The code is at https://github.com/scy-Jackel/LVPNet.
comment: Accepted to MICCAI 2025
♻ ☆ Image Super-Resolution with Guarantees via Conformalized Generative Models
The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We address this need by presenting a novel approach based on conformal prediction techniques to create a 'confidence mask' capable of reliably and intuitively communicating where the generated image can be trusted. Our method is adaptable to any black-box generative model, including those locked behind an opaque API, requires only easily attainable data for calibration, and is highly customizable via the choice of a local image similarity metric. We prove strong theoretical guarantees for our method that span fidelity error control (according to our local image similarity metric), reconstruction quality, and robustness in the face of data leakage. Finally, we empirically evaluate these results and establish our method's solid performance.
comment: 17 pages, 7 figures
♻ ☆ Learning Adaptive Lighting via Channel-Aware Guidance
Learning lighting adaptation is a crucial step in achieving good visual perception and supporting downstream vision tasks. Current research often addresses individual light-related challenges, such as high dynamic range imaging and exposure correction, in isolation. However, we identify shared fundamental properties across these tasks: i) different color channels have different light properties, and ii) the channel differences reflected in the spatial and frequency domains are different. Leveraging these insights, we introduce the channel-aware Learning Adaptive Lighting Network (LALNet), a multi-task framework designed to handle multiple light-related tasks efficiently. Specifically, LALNet incorporates color-separated features that highlight the unique light properties of each color channel, integrated with traditional color-mixed features by Light Guided Attention (LGA). The LGA utilizes color-separated features to guide color-mixed features focusing on channel differences and ensuring visual consistency across all channels. Additionally, LALNet employs dual domain channel modulation for generating color-separated features and a mixed channel modulation and light state space module for producing color-mixed features. Extensive experiments on four representative light-related tasks demonstrate that LALNet significantly outperforms state-of-the-art methods on benchmark tests and requires fewer computational resources. We provide an anonymous online demo at https://xxxxxx2025.github.io/LALNet/.
♻ ☆ It's not you, it's me -- Global urban visual perception varies across demographics and personalities
Understanding people's preferences and needs is crucial for urban planning decisions, yet current approaches often combine them from multi-cultural and multi-city populations, obscuring important demographic differences and risking amplifying biases. We conducted a large-scale urban visual perception survey of streetscapes worldwide using street view imagery, examining how demographics -- including gender, age, income, education, race and ethnicity, and, for the first time, personality traits -- shape perceptions among 1,000 participants, with balanced demographics, from five countries and 45 nationalities. This dataset, introduced as Street Perception Evaluation Considering Socioeconomics (SPECS), exhibits statistically significant differences in perception scores in six traditionally used indicators (safe, lively, wealthy, beautiful, boring, and depressing) and four new ones we propose (live nearby, walk, cycle, green) among demographics and personalities. We revealed that location-based sentiments are carried over in people's preferences when comparing urban streetscapes with other cities. Further, we compared the perception scores based on where participants and streetscapes are from. We found that an off-the-shelf machine learning model trained on an existing global perception dataset tends to overestimate positive indicators and underestimate negative ones compared to human responses, suggesting that targeted intervention should consider locals' perception. Our study aspires to rectify the myopic treatment of street perception, which rarely considers demographics or personality traits.
comment: Under review
♻ ☆ MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration
Capturing voxel-wise spatial correspondence across distinct modalities is crucial for medical image analysis. However, current registration approaches are not practical enough in terms of registration accuracy and clinical applicability. In this paper, we introduce MambaMorph, a novel multi-modality deformable registration framework. Specifically, MambaMorph utilizes a Mamba-based registration module and a fine-grained, yet simple, feature extractor for efficient long-range correspondence modeling and high-dimensional feature learning, respectively. Additionally, we develop a well-annotated brain MR-CT registration dataset, SR-Reg, to address the scarcity of data in multi-modality registration. To validate MambaMorph's multi-modality registration capabilities, we conduct quantitative experiments on both our SR-Reg dataset and a public T1-T2 dataset. The experimental results on both datasets demonstrate that MambaMorph significantly outperforms the current state-of-the-art learning-based registration methods in terms of registration accuracy. Further study underscores the efficiency of the Mamba-based registration module and the lightweight feature extractor, which achieve notable registration quality while maintaining reasonable computational costs and speeds. We believe that MambaMorph holds significant potential for practical applications in medical image registration. The code for MambaMorph is available at: https://github.com/Guo-Stone/MambaMorph.
♻ ☆ VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human Feedback
As artificial intelligence (AI) becomes increasingly central to healthcare, the demand for explainable and trustworthy models is paramount. Current report generation systems for chest X-rays (CXR) often lack mechanisms for validating outputs without expert oversight, raising concerns about reliability and interpretability. To address these challenges, we propose a novel multimodal framework designed to enhance the semantic alignment and localization accuracy of AI-generated medical reports. Our framework integrates two key modules: a Phrase Grounding Model, which identifies and localizes pathologies in CXR images based on textual prompts, and a Text-to-Image Diffusion Module, which generates synthetic CXR images from prompts while preserving anatomical fidelity. By comparing features between the original and generated images, we introduce a dual-scoring system: one score quantifies localization accuracy, while the other evaluates semantic consistency. This approach significantly outperforms existing methods, achieving state-of-the-art results in pathology localization and text-to-image alignment. The integration of phrase grounding with diffusion models, coupled with the dual-scoring evaluation system, provides a robust mechanism for validating report quality, paving the way for more trustworthy and transparent AI in medical imaging.
♻ ☆ Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors ECML-PKDD2025
Deep neural networks (DNNs) deployed in a cloud often allow users to query models via the APIs. However, these APIs expose the models to model extraction attacks (MEAs). In this attack, the attacker attempts to duplicate the target model by abusing the responses from the API. Backdoor-based DNN watermarking is known as a promising defense against MEAs, wherein the defender injects a backdoor into extracted models via API responses. The backdoor is used as a watermark of the model; if a suspicious model has the watermark (i.e., backdoor), it is verified as an extracted model. This work focuses on object detection (OD) models. Existing backdoor attacks on OD models are not applicable for model watermarking as the defense against MEAs on a realistic threat model. Our proposed approach involves inserting a backdoor into extracted models via APIs by stealthily modifying the bounding-boxes (BBs) of objects detected in queries while keeping the OD capability. In our experiments on three OD datasets, the proposed approach succeeded in identifying the extracted models with 100% accuracy in a wide variety of experimental scenarios.
comment: Accepted at ECML-PKDD2025. Please refer to the conference proceedings for the final version. Source codes: https://zenodo.org/records/15641464
♻ ☆ Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration WACV 2025
Neural field-based SLAM methods typically employ a single, monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a novel RGB-D neural mapping framework in which the scene is represented by a collection of lightweight neural fields which are dynamically anchored to the pose graph of a sparse visual SLAM system. Our approach shows the ability to integrate large-scale loop closures, while requiring only minimal reintegration. Furthermore, we verify the scalability of our approach by demonstrating successful building-scale mapping taking multiple loop closures into account during the optimization, and show that our method outperforms existing state-of-the-art approaches on large scenes in terms of quality and runtime. Our code is available open-source at https://github.com/KTH-RPL/neural_graph_mapping.
comment: WACV 2025, Project page: https://kth-rpl.github.io/neural_graph_mapping/
♻ ☆ ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistency
While Gaussian Splatting (GS) demonstrates efficient and high-quality scene rendering and small area surface extraction ability, it falls short in handling large-scale aerial image surface extraction tasks. To overcome this, we present ULSR-GS, a framework dedicated to high-fidelity surface extraction in ultra-large-scale scenes, addressing the limitations of existing GS-based mesh extraction methods. Specifically, we propose a point-to-photo partitioning approach combined with a multi-view optimal view matching principle to select the best training images for each sub-region. Additionally, during training, ULSR-GS employs a densification strategy based on multi-view geometric consistency to enhance surface extraction details. Experimental results demonstrate that ULSR-GS outperforms other state-of-the-art GS-based works on large-scale aerial photogrammetry benchmark datasets, significantly improving surface extraction accuracy in complex urban environments. Project page: https://ulsrgs.github.io.
comment: Project page: https://ulsrgs.github.io
♻ ☆ World-Consistent Data Generation for Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency, aimed at enhancing the generalization of agents to novel environments. Roughly, our framework consists of two stages, the trajectory stage which leverages a point-cloud based technique to ensure spatial coherency among viewpoints, and the viewpoint stage which adopts a novel angle synthesis method to guarantee spatial and wraparound consistency within the entire observation. By accurately predicting viewpoint changes with 3D knowledge, our approach maintains the world-consistency during the generation procedure. Experiments on a wide range of datasets verify the effectiveness of our method, demonstrating that our data augmentation strategy enables agents to achieve new state-of-the-art results on all navigation tasks, and is capable of enhancing the VLN agents' generalization ability to unseen environments.
♻ ☆ Provably Improving Generalization of Few-Shot Models with Synthetic Data ICML 2025
Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often face performance degradation due to the inherent gap between real and synthetic distributions. To address this limitation, we develop a theoretical framework that quantifies the impact of such distribution discrepancies on supervised learning, specifically in the context of image classification. More importantly, our framework suggests practical ways to generate good synthetic samples and to train a predictor with high generalization ability. Building upon this framework, we propose a novel theoretical-based algorithm that integrates prototype learning to optimize both data partitioning and model training, effectively bridging the gap between real few-shot data and synthetic data. Extensive experiments results show that our approach demonstrates superior performance compared to state-of-the-art methods, outperforming them across multiple datasets.
comment: ICML 2025. Our code is released at https://github.com/Fsoft-AIC/ProtoAug
♻ ☆ Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models IROS 2025
Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing for precise prediction of action trajectories. However, diffusion models typically rely on large parameter UNet backbones as policy networks, which can be challenging to deploy on resource-constrained devices. Recently, the Mamba model has emerged as a promising solution for efficient modeling, offering low computational complexity and strong performance in sequence modeling. In this work, we propose the Mamba Policy, a lighter but stronger policy that reduces the parameter count by over 80% compared to the original policy network while achieving superior performance. Specifically, we introduce the XMamba Block, which effectively integrates input information with conditional features and leverages a combination of Mamba and Attention mechanisms for deep feature extraction. Extensive experiments demonstrate that the Mamba Policy excels on the Adroit, Dexart, and MetaWorld datasets, requiring significantly fewer computational resources. Additionally, we highlight the Mamba Policy's enhanced robustness in long-horizon scenarios compared to baseline methods and explore the performance of various Mamba variants within the Mamba Policy framework. Real-world experiments are also conducted to further validate its effectiveness. Our open-source project page can be found at https://andycao1125.github.io/mamba_policy/.
comment: Accepted to IROS 2025
♻ ☆ WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care ECML
Chronic wounds affect a large population, particularly the elderly and diabetic patients, who often exhibit limited mobility and co-existing health conditions. Automated wound monitoring via mobile image capture can reduce in-person physician visits by enabling remote tracking of wound size. Semantic segmentation is key to this process, yet wound segmentation remains underrepresented in medical imaging research. To address this, we benchmark state-of-the-art deep learning models from general-purpose vision, medical imaging, and top methods from public wound challenges. For a fair comparison, we standardize training, data augmentation, and evaluation, conducting cross-validation to minimize partitioning bias. We also assess real-world deployment aspects, including generalization to an out-of-distribution wound dataset, computational efficiency, and interpretability. Additionally, we propose a reference object-based approach to convert AI-generated masks into clinically relevant wound size estimates and evaluate this, along with mask quality, for the five best architectures based on physician assessments. Overall, the transformer-based TransNeXt showed the highest levels of generalizability. Despite variations in inference times, all models processed at least one image per second on the CPU, which is deemed adequate for the intended application. Interpretability analysis typically revealed prominent activations in wound regions, emphasizing focus on clinically relevant features. Expert evaluation showed high mask approval for all analyzed models, with VWFormer and ConvNeXtS backbone performing the best. Size retrieval accuracy was similar across models, and predictions closely matched expert annotations. Finally, we demonstrate how our AI-driven wound size estimation framework, WoundAmbit, is integrated into a custom telehealth system.
comment: Main paper: 18 pages; supplementary material: 15 pages; the paper has been accepted for publication at the Applied Data Science (ADS) track of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2025)
♻ ☆ Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning
Toddlers learn to recognize objects from different viewpoints with almost no supervision. During this learning, they execute frequent eye and head movements that shape their visual experience. It is presently unclear if and how these behaviors contribute to toddlers' emerging object recognition abilities. To answer this question, we here combine head-mounted eye tracking during dyadic play with unsupervised machine learning. We approximate toddlers' central visual field experience by cropping image regions from a head-mounted camera centered on the current gaze location estimated via eye tracking. This visual stream feeds an unsupervised computational model of toddlers' learning, which constructs visual representations that slowly change over time. Our experiments demonstrate that toddlers' gaze strategy supports the learning of invariant object representations. Our analysis also shows that the limited size of the central visual field where acuity is high is crucial for this. Overall, our work reveals how toddlers' gaze behavior may support their development of view-invariant object recognition.
comment: 27 pages, 16 figures
♻ ☆ ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing PointMamba-based methods depend on complex token ordering and random masking, which disrupt spatial continuity and local semantic correlations. We propose ZigzagPointMamba to tackle these challenges. The core of our approach is a simple zigzag scan path that globally sequences point cloud tokens, enhancing spatial continuity by preserving the proximity of spatially adjacent point tokens. Nevertheless, random masking undermines local semantic modeling in self-supervised learning. To address this, we introduce a Semantic-Siamese Masking Strategy (SMS), which masks semantically similar tokens to facilitate reconstruction by integrating local features of original and similar tokens. This overcomes the dependence on isolated local features and enables robust global semantic modeling. Our pre-trained ZigzagPointMamba weights significantly improve downstream tasks, achieving a 1.59% mIoU gain on ShapeNetPart for part segmentation, a 0.4% higher accuracy on ModelNet40 for classification, and 0.19%, 1.22%, and 0.72% higher accuracies respectively for the classification tasks on the OBJ-BG, OBJ-ONLY, and PB-T50-RS subsets of ScanObjectNN.
comment: The format of the document has an error and needs to be revised
♻ ☆ KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling CVPR 2024
DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up. In this paper, we focus on the compression of DETR with knowledge distillation. While knowledge distillation has been well-studied in classic detectors, there is a lack of researches on how to make it work effectively on DETR. We first provide experimental and theoretical analysis to point out that the main challenge in DETR distillation is the lack of consistent distillation points. Distillation points refer to the corresponding inputs of the predictions for student to mimic, which have different formulations in CNN detector and DETR, and reliable distillation requires sufficient distillation points which are consistent between teacher and student. Based on this observation, we propose the first general knowledge distillation paradigm for DETR (KD-DETR) with consistent distillation points sampling, for both homogeneous and heterogeneous distillation. Specifically, we decouple detection and distillation tasks by introducing a set of specialized object queries to construct distillation points for DETR. We further propose a general-to-specific distillation points sampling strategy to explore the extensibility of KD-DETR. Extensive experiments validate the effectiveness and generalization of KD-DETR. For both single-scale DAB-DETR and multis-scale Deformable DETR and DINO, KD-DETR boost the performance of student model with improvements of $2.6\%-5.2\%$. We further extend KD-DETR to heterogeneous distillation, and achieves $2.1\%$ improvement by distilling the knowledge from DINO to Faster R-CNN with ResNet-50, which is comparable with homogeneous distillation methods.The code is available at https://github.com/wennyuhey/KD-DETR.
comment: Accepted to CVPR 2024
♻ ☆ FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion
3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling real-time positioning and the construction of high-fidelity maps. However, the uncertainty in gaussian position and initialization parameters introduces challenges, often requiring extensive iterative convergence and resulting in redundant or insufficient gaussian representations. To address this, we introduce a novel adaptive densification method based on Fourier frequency domain analysis to establish gaussian priors for rapid convergence. Additionally, we propose constructing independent and unified sparse and dense maps, where a sparse map supports efficient tracking via Generalized Iterative Closest Point (GICP) and a dense map creates high-fidelity visual representations. This is the first SLAM system leveraging frequency domain analysis to achieve high-quality gaussian mapping in real-time. Experimental results demonstrate an average frame rate of 36 FPS on Replica and TUM RGB-D datasets, achieving competitive accuracy in both localization and mapping.
♻ ☆ TT3D: Table Tennis 3D Reconstruction
Sports analysis requires processing large amounts of data, which is time-consuming and costly. Advancements in neural networks have significantly alleviated this burden, enabling highly accurate ball tracking in sports broadcasts. However, relying solely on 2D ball tracking is limiting, as it depends on the camera's viewpoint and falls short of supporting comprehensive game analysis. To address this limitation, we propose a novel approach for reconstructing precise 3D ball trajectories from online table tennis match recordings. Our method leverages the underlying physics of the ball's motion to identify the bounce state that minimizes the reprojection error of the ball's flying trajectory, hence ensuring an accurate and reliable 3D reconstruction. A key advantage of our approach is its ability to infer ball spin without relying on human pose estimation or racket tracking, which are often unreliable or unavailable in broadcast footage. We developed an automated camera calibration method capable of reliably tracking camera movements. Additionally, we adapted an existing 3D pose estimation model, which lacks depth motion capture, to accurately track player movements. Together, these contributions enable the full 3D reconstruction of a table tennis rally.
comment: Accepted to CVSport 2025
♻ ☆ Matching-Free Depth Recovery from Structured Light
We introduce a novel approach for depth estimation using images obtained from monocular structured light systems. In contrast to many existing methods that depend on image matching, our technique employs a density voxel grid to represent scene geometry. This grid is trained through self-supervised differentiable volume rendering. Our method leverages color fields derived from the projected patterns in structured light systems during the rendering process, facilitating the isolated optimization of the geometry field. This innovative approach leads to faster convergence and high-quality results. Additionally, we integrate normalized device coordinates (NDC), a distortion loss, and a distinctive surface-based color loss to enhance geometric fidelity. Experimental results demonstrate that our method outperforms current matching-based techniques in terms of geometric performance in few-shot scenarios, achieving an approximately 30% reduction in average estimated depth errors for both synthetic scenes and real-world captured scenes. Moreover, our approach allows for rapid training, being approximately three times faster than previous matching-free methods that utilize implicit representations.
comment: 13 pages, 10 figures
♻ ☆ VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental aspect of human intelligence, remains a persistent challenge due to the complex logic, temporal and causal structures inherent in video data. To fill this gap, we propose VIDEORFT, a novel approach that extends the RFT paradigm to cultivate human-like video reasoning capabilities in MLLMs. VIDEORFT follows the standard two-stage scheme in RFT: supervised fine-tuning (SFT) with chain-of-thought (CoT) annotations, followed by reinforcement learning (RL) to improve generalization. A central challenge to achieve this in the video domain lies in the scarcity of large-scale, high-quality video CoT datasets. We address this by building a fully automatic CoT curation pipeline. First, we devise a cognitioninspired prompting strategy to elicit a reasoning LLM to generate preliminary CoTs based solely on rich, structured, and literal representations of video content. Subsequently, these CoTs are revised by a visual-language model conditioned on the actual video, ensuring visual consistency and reducing visual hallucinations. This pipeline results in two new datasets - VideoRFT-CoT-102K for SFT and VideoRFT-RL-310K for RL. To further strengthen the RL phase, we introduce a novel semantic-consistency reward that explicitly promotes the alignment between textual reasoning and visual evidence. This reward encourages the model to produce coherent, context-aware reasoning outputs grounded in visual input. Extensive experiments show that VIDEORFT achieves state-of-the-art performance on six video reasoning benchmarks.
comment: Code: https://github.com/QiWang98/VideoRFT
♻ ☆ Skin Color Measurement from Dermatoscopic Images: An Evaluation on a Synthetic Dataset
This paper presents a comprehensive evaluation of skin color measurement methods from dermatoscopic images using a synthetic dataset (S-SYNTH) with controlled ground-truth melanin content, lesion shapes, hair models, and 18 distinct lighting conditions. This allows for rigorous assessment of the robustness and invariance to lighting conditions. We assess four classes of image colorimetry approaches: segmentation-based, patch-based, color quantization, and neural networks. We use these methods to estimate the Individual Typology Angle (ITA) and Fitzpatrick types from dermatoscopic images. Our results show that segmentation-based and color quantization methods yield robust, lighting-invariant estimates, whereas patch-based approaches exhibit significant lighting-dependent biases that require calibration. Furthermore, neural network models, particularly when combined with heavy blurring to reduce overfitting, can provide light-invariant Fitzpatrick predictions, although their generalization to real-world images remains unverified. We conclude with practical recommendations for designing fair and reliable skin color estimation methods.
♻ ☆ A Siamese Network to Detect If Two Iris Images Are Monozygotic
This study presents the first automated classifier designed to determine whether a pair of iris images originates from monozygotic individuals, addressing a previously untackled problem in biometric recognition. In Daugman-style iris recognition, the textures of the left and right irises of the same person are traditionally considered as being as different as the irises of two unrelated persons. However, previous research indicates that humans can detect that two iris images are from different eyes of the same person, or eyes of monozygotic twins, with an accuracy of about 80%. In this work, we employ a Siamese network architecture and contrastive learning to categorize a pair of iris images as coming from monozygotic or non-monozygotic irises. This could potentially be applied, for example, as a fast, noninvasive test to determine if twins are monozygotic or non-monozygotic. We construct a dataset comprising both synthetic monozygotic pairs (images of different irises of the same individual) and natural monozygotic pairs (images of different images from persons who are identical twins), in addition to non-monozygotic pairs from unrelated individuals, ensuring a comprehensive evaluation of the model's capabilities. To gain deeper insights into the learned representations, we train and analyze three variants of the model using (1) the original input images, (2) iris-only images (masking everything but the iris region), and (3) non-iris-only images (masking the iris region). This comparison reveals that both iris texture and surrounding ocular structure contain information useful for the model to classify the image pairs as monozygotic or non-monozygotic. Our approach achieves accuracy levels using the full iris image that exceed those previously reported for human classification of monozygotic iris pairs.
♻ ☆ TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
The rapid advancements of Text-to-Image (T2I) models have ushered in a new phase of AI-generated content, marked by their growing ability to interpret and follow user instructions. However, existing T2I model evaluation benchmarks fall short in limited prompt diversity and complexity, as well as coarse evaluation metrics, making it difficult to evaluate the fine-grained alignment performance between textual instructions and generated images. In this paper, we present TIIF-Bench (Text-to-Image Instruction Following Benchmark), aiming to systematically assess T2I models' ability in interpreting and following intricate textual instructions. TIIF-Bench comprises a set of 5000 prompts organized along multiple dimensions, which are categorized into three levels of difficulties and complexities. To rigorously evaluate model robustness to varying prompt lengths, we provide a short and a long version for each prompt with identical core semantics. Two critical attributes, i.e., text rendering and style control, are introduced to evaluate the precision of text synthesis and the aesthetic coherence of T2I models. In addition, we collect 100 high-quality designer level prompts that encompass various scenarios to comprehensively assess model performance. Leveraging the world knowledge encoded in large vision language models, we propose a novel computable framework to discern subtle variations in T2I model outputs. Through meticulous benchmarking of mainstream T2I models on TIIF-Bench, we analyze the pros and cons of current T2I models and reveal the limitations of current T2I benchmarks. Project Page: https://a113n-w3i.github.io/TIIF_Bench/.
comment: 23 pages, 12 figures, 11 tables
♻ ☆ USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
Spike cameras, as an innovative neuromorphic camera that captures scenes with the 0-1 bit stream at 40 kHz, are increasingly employed for the 3D reconstruction task via Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS). Previous spike-based 3D reconstruction approaches often employ a casecased pipeline: starting with high-quality image reconstruction from spike streams based on established spike-to-image reconstruction algorithms, then progressing to camera pose estimation and 3D reconstruction. However, this cascaded approach suffers from substantial cumulative errors, where quality limitations of initial image reconstructions negatively impact pose estimation, ultimately degrading the fidelity of the 3D reconstruction. To address these issues, we propose a synergistic optimization framework, \textbf{USP-Gaussian}, that unifies spike-based image reconstruction, pose correction, and Gaussian splatting into an end-to-end framework. Leveraging the multi-view consistency afforded by 3DGS and the motion capture capability of the spike camera, our framework enables a joint iterative optimization that seamlessly integrates information between the spike-to-image network and 3DGS. Experiments on synthetic datasets with accurate poses demonstrate that our method surpasses previous approaches by effectively eliminating cascading errors. Moreover, we integrate pose optimization to achieve robust 3D reconstruction in real-world scenarios with inaccurate initial poses, outperforming alternative methods by effectively reducing noise and preserving fine texture details. Our code, data and trained models will be available at https://github.com/chenkang455/USP-Gaussian.
♻ ☆ VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning
Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions. Current language model-based navigation systems operate on discrete topological graphs, limiting path planning to predefined node connections. We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions, adopting GRPO-based training inspired by DeepSeek-R1. To enable effective training, we first construct the VLN-Ego dataset using a 3D simulator, Habitat, and propose Long-Short Memory Sampling to balance historical and current observations. While large language models can supervise complete textual instructions, they lack fine-grained action-level control. Our framework employs a two-stage training approach: a) Supervised fine-tuning (SFT) to align the model's action sequence text predictions with expert demonstrations, followed by b) Reinforcement fine-tuning (RFT) enhanced with a Time-Decayed Reward (TDR) mechanism that strategically weights multi-step future actions. Experimental results show VLN-R1 achieves strong performance on VLN-CE benchmark. VLN-R1 proves LVLMs can drive embodied navigation and enhance task-specific reasoning through data-efficient, reward-driven post-training.
comment: project page: vlnr1.github.io
♻ ☆ C3S3: Complementary Competition and Contrastive Selection for Semi-Supervised Medical Image Segmentation ICME 2025
For the immanent challenge of insufficiently annotated samples in the medical field, semi-supervised medical image segmentation (SSMIS) offers a promising solution. Despite achieving impressive results in delineating primary target areas, most current methodologies struggle to precisely capture the subtle details of boundaries. This deficiency often leads to significant diagnostic inaccuracies. To tackle this issue, we introduce C3S3, a novel semi-supervised segmentation model that synergistically integrates complementary competition and contrastive selection. This design significantly sharpens boundary delineation and enhances overall precision. Specifically, we develop an Outcome-Driven Contrastive Learning module dedicated to refining boundary localization. Additionally, we incorporate a Dynamic Complementary Competition module that leverages two high-performing sub-networks to generate pseudo-labels, thereby further improving segmentation quality. The proposed C3S3 undergoes rigorous validation on two publicly accessible datasets, encompassing the practices of both MRI and CT scans. The results demonstrate that our method achieves superior performance compared to previous cutting-edge competitors. Especially, on the 95HD and ASD metrics, our approach achieves a notable improvement of at least 6%, highlighting the significant advancements. The code is available at https://github.com/Y-TARL/C3S3.
comment: Accepted to ICME 2025
♻ ☆ Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation
This paper discusses how ophthalmologists often rely on multimodal data to improve diagnostic accuracy. However, complete multimodal data is rare in real-world applications due to a lack of medical equipment and concerns about data privacy. Traditional deep learning methods typically address these issues by learning representations in latent space. However, the paper highlights two key limitations of these approaches: (i) Task-irrelevant redundant information (e.g., numerous slices) in complex modalities leads to significant redundancy in latent space representations. (ii) Overlapping multimodal representations make it difficult to extract unique features for each modality. To overcome these challenges, the authors propose the Essence-Point and Disentangle Representation Learning (EDRL) strategy, which integrates a self-distillation mechanism into an end-to-end framework to enhance feature selection and disentanglement for more robust multimodal learning. Specifically, the Essence-Point Representation Learning module selects discriminative features that improve disease grading performance. The Disentangled Representation Learning module separates multimodal data into modality-common and modality-unique representations, reducing feature entanglement and enhancing both robustness and interpretability in ophthalmic disease diagnosis. Experiments on multimodal ophthalmology datasets show that the proposed EDRL strategy significantly outperforms current state-of-the-art methods.
comment: 10pages
♻ ☆ Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models ICML 2025
In this paper, we present Morse, a simple dual-sampling framework for accelerating diffusion models losslessly. The key insight of Morse is to reformulate the iterative generation (from noise to data) process via taking advantage of fast jump sampling and adaptive residual feedback strategies. Specifically, Morse involves two models called Dash and Dot that interact with each other. The Dash model is just the pre-trained diffusion model of any type, but operates in a jump sampling regime, creating sufficient space for sampling efficiency improvement. The Dot model is significantly faster than the Dash model, which is learnt to generate residual feedback conditioned on the observations at the current jump sampling point on the trajectory of the Dash model, lifting the noise estimate to easily match the next-step estimate of the Dash model without jump sampling. By chaining the outputs of the Dash and Dot models run in a time-interleaved fashion, Morse exhibits the merit of flexibly attaining desired image generation performance while improving overall runtime efficiency. With our proposed weight sharing strategy between the Dash and Dot models, Morse is efficient for training and inference. Our method shows a lossless speedup of 1.78X to 3.31X on average over a wide range of sampling step budgets relative to 9 baseline diffusion models on 6 image generation tasks. Furthermore, we show that our method can be also generalized to improve the Latent Consistency Model (LCM-SDXL, which is already accelerated with consistency distillation technique) tailored for few-step text-to-image synthesis. The code and models are available at https://github.com/deep-optimization/Morse.
comment: Fixed a prompt typo in Figure 18 of the Appendix. This work is accepted to ICML 2025. The project page: https://github.com/deep-optimization/Morse
♻ ☆ Predictive Modeling, Pattern Recognition, and Spatiotemporal Representations of Plant Growth in Simulated and Controlled Environments: A Comprehensive Review
Accurate predictions and representations of plant growth patterns in simulated and controlled environments are important for addressing various challenges in plant phenomics research. This review explores various works on state-of-the-art predictive pattern recognition techniques, focusing on the spatiotemporal modeling of plant traits and the integration of dynamic environmental interactions. We provide a comprehensive examination of deterministic, probabilistic, and generative modeling approaches, emphasizing their applications in high-throughput phenotyping and simulation-based plant growth forecasting. Key topics include regressions and neural network-based representation models for the task of forecasting, limitations of existing experiment-based deterministic approaches, and the need for dynamic frameworks that incorporate uncertainty and evolving environmental feedback. This review surveys advances in 2D and 3D structured data representations through functional-structural plant models and conditional generative models. We offer a perspective on opportunities for future works, emphasizing the integration of domain-specific knowledge to data-driven methods, improvements to available datasets, and the implementation of these techniques toward real-world applications.
♻ ☆ Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition
Vision Large Language Models (VLLMs) exhibit promising potential for multi-modal understanding, yet their application to video-based emotion recognition remains limited by insufficient spatial and contextual awareness. Traditional approaches, which prioritize isolated facial features, often neglect critical non-verbal cues such as body language, environmental context, and social interactions, leading to reduced robustness in real-world scenarios. To address this gap, we propose Set-of-Vision-Text Prompting (SoVTP), a novel framework that enhances zero-shot emotion recognition by integrating spatial annotations (e.g., bounding boxes, facial landmarks), physiological signals (facial action units), and contextual cues (body posture, scene dynamics, others' emotions) into a unified prompting strategy. SoVTP preserves holistic scene information while enabling fine-grained analysis of facial muscle movements and interpersonal dynamics. Extensive experiments show that SoVTP achieves substantial improvements over existing visual prompting methods, demonstrating its effectiveness in enhancing VLLMs' video emotion recognition capabilities.
comment: 14 pages, 14 figures
♻ ☆ BeltCrack: the First Sequential-image Industrial Conveyor Belt Crack Detection Dataset and Its Baseline with Triple-domain Feature Learning
Conveyor belts are important equipment in modern industry, widely applied in production and manufacturing. Their health is much critical to operational efficiency and safety. Cracks are a major threat to belt health. Currently, considering safety, how to intelligently detect belt cracks is catching an increasing attention. To implement the intelligent detection with machine learning, real crack samples are believed to be necessary. However, existing crack datasets primarily focus on pavement scenarios or synthetic data, no real-world industrial belt crack datasets at all. Cracks are a major threat to belt health. Furthermore, to validate usability and effectiveness, we propose a special baseline method with triple-domain ($i.e.$, time-space-frequency) feature hierarchical fusion learning for the two whole-new datasets. Experimental results demonstrate the availability and effectiveness of our dataset. Besides, they also show that our baseline is obviously superior to other similar detection methods. Our datasets and source codes are available at https://github.com/UESTC-nnLab/BeltCrack.
comment: 14 pages, 10 figures
♻ ☆ PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding
This report introduces PP-DocBee2, an advanced version of the PP-DocBee, designed to enhance multimodal document understanding. Built on a large multimodal model architecture, PP-DocBee2 addresses the limitations of its predecessor through key technological improvements, including enhanced synthetic data quality, improved visual feature fusion strategy, and optimized inference methodologies. These enhancements yield an $11.4\%$ performance boost on internal benchmarks for Chinese business documents, and reduce inference latency by $73.0\%$ to the vanilla version. A key innovation of our work is a data quality optimization strategy for multimodal document tasks. By employing a large-scale multimodal pre-trained model to evaluate data, we apply a novel statistical criterion to filter outliers, ensuring high-quality training data. Inspired by insights into underutilized intermediate features in multimodal models, we enhance the ViT representational capacity by decomposing it into layers and applying a novel feature fusion strategy to improve complex reasoning. The source code and pre-trained model are available at \href{https://github.com/PaddlePaddle/PaddleMIX}{https://github.com/PaddlePaddle/PaddleMIX}.
♻ ☆ Fine-Grained Perturbation Guidance via Attention Head Selection
Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong empirical performance in unconditional scenarios where classifier-free guidance is not applicable. However, existing attention perturbation methods lack principled approaches for determining where perturbations should be applied, particularly in Diffusion Transformer (DiT) architectures where quality-relevant computations are distributed across layers. In this paper, we investigate the granularity of attention perturbations, ranging from the layer level down to individual attention heads, and discover that specific heads govern distinct visual concepts such as structure, style, and texture quality. Building on this insight, we propose "HeadHunter", a systematic framework for iteratively selecting attention heads that align with user-centric objectives, enabling fine-grained control over generation quality and visual attributes. In addition, we introduce SoftPAG, which linearly interpolates each selected head's attention map toward an identity matrix, providing a continuous knob to tune perturbation strength and suppress artifacts. Our approach not only mitigates the oversmoothing issues of existing layer-level perturbation but also enables targeted manipulation of specific visual styles through compositional head selection. We validate our method on modern large-scale DiT-based text-to-image models including Stable Diffusion 3 and FLUX.1, demonstrating superior performance in both general quality enhancement and style-specific guidance. Our work provides the first head-level analysis of attention perturbation in diffusion models, uncovering interpretable specialization within attention layers and enabling practical design of effective perturbation strategies.
comment: Project page: https://cvlab-kaist.github.io/HeadHunter/
♻ ☆ Low-light Pedestrian Detection in Visible and Infrared Image Feeds: Issues and Challenges
Pedestrian detection has become a cornerstone for several high-level tasks, including autonomous driving, intelligent transportation, and traffic surveillance. There are several works focussed on pedestrian detection using visible images, mainly in the daytime. However, this task is very intriguing when the environmental conditions change to poor lighting or nighttime. Recently, new ideas have been spurred to use alternative sources, such as Far InfraRed (FIR) temperature sensor feeds for detecting pedestrians in low-light conditions. This study reviews recent developments in low-light pedestrian detection approaches. It systematically categorizes and analyses various algorithms from region-based to non-region-based and graph-based learning methodologies by highlighting their methodologies, implementation issues, and challenges. It also outlines the key benchmark datasets that can be used for research and development of advanced pedestrian detection algorithms, particularly in low-light situations.
comment: 29 pages, 4 tables, 21 figures
Information Retrieval 19
☆ Unidentified and Confounded? Understanding Two-Tower Models for Unbiased Learning to Rank
Additive two-tower models are popular learning-to-rank methods for handling biased user feedback in industry settings. Recent studies, however, report a concerning phenomenon: training two-tower models on clicks collected by well-performing production systems leads to decreased ranking performance. This paper investigates two recent explanations for this observation: confounding effects from logging policies and model identifiability issues. We theoretically analyze the identifiability conditions of two-tower models, showing that either document swaps across positions or overlapping feature distributions are required to recover model parameters from clicks. We also investigate the effect of logging policies on two-tower models, finding that they introduce no bias when models perfectly capture user behavior. However, logging policies can amplify biases when models imperfectly capture user behavior, particularly when prediction errors correlate with document placement across positions. We propose a sample weighting technique to mitigate these effects and provide actionable insights for researchers and practitioners using two-tower models.
☆ ReCode: Updating Code API Knowledge with Reinforcement Learning
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their training data, even with access to current documentation, impedes reliable code generation in dynamic environments. To tackle this issue, we propose ReCode (rule-based Reinforcement learning for Code Update), a novel framework that mimics human programmer adaptation to API changes. Specifically, we construct a dataset of approximately 2,000 data entries to train the LLMs to perform version migration based on updated information. Then, we introduce a modified string similarity metric for code evaluation as the reward for reinforcement learning. Our experiments demonstrate that ReCode substantially boosts LLMs' code generation performance in dynamic API scenarios, especially on the unseen CodeUpdateArena task. Crucially, compared to supervised fine-tuning, ReCode has less impact on LLMs' general code generation abilities. We apply ReCode on various LLMs and reinforcement learning algorithms (GRPO and DAPO), all achieving consistent improvements. Notably, after training, Qwen2.5-Coder-7B outperforms that of the 32B parameter code instruction-tuned model and the reasoning model with the same architecture. Code is available at https://github.com/zjunlp/ReCode.
comment: Work in progress
☆ Knowledge-Aware Diverse Reranking for Cross-Source Question Answering
This paper presents Team Marikarp's solution for the SIGIR 2025 LiveRAG competition. The competition's evaluation set, automatically generated by DataMorgana from internet corpora, encompassed a wide range of target topics, question types, question formulations, audience types, and knowledge organization methods. It offered a fair evaluation of retrieving question-relevant supporting documents from a 15M documents subset of the FineWeb corpus. Our proposed knowledge-aware diverse reranking RAG pipeline achieved first place in the competition.
☆ Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search
Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the visual information (e.g, image) of item is leveraged as supplementary of textual information to enrich item representation and further improve retrieval performance. Though learning from cross-modality data has been studied extensively in tasks such as visual question answering or media summarization, multimodal retrieval remains a non-trivial and unsolved problem especially in the asymmetric scenario where the query is unimodal while the item is multimodal. In this paper, we propose a novel model named SMAR, which stands for Semantic-enhanced Modality-Asymmetric Retrieval, to tackle the problem of modality fusion and alignment in this kind of asymmetric scenario. Extensive experimental results on an industrial dataset show that the proposed model outperforms baseline models significantly in retrieval accuracy. We have open sourced our industrial dataset for the sake of reproducibility and future research works.
comment: published in sigir2023
☆ A Literature Review on Simulation in Conversational Recommender Systems
Conversational Recommender Systems (CRSs) have garnered attention as a novel approach to delivering personalized recommendations through multi-turn dialogues. This review developed a taxonomy framework to systematically categorize relevant publications into four groups: dataset construction, algorithm design, system evaluation, and empirical studies, providing a comprehensive analysis of simulation methods in CRSs research. Our analysis reveals that simulation methods play a key role in tackling CRSs' main challenges. For example, LLM-based simulation methods have been used to create conversational recommendation data, enhance CRSs algorithms, and evaluate CRSs. Despite several challenges, such as dataset bias, the limited output flexibility of LLM-based simulations, and the gap between text semantic space and behavioral semantics, persist due to the complexity in Human-Computer Interaction (HCI) of CRSs, simulation methods hold significant potential for advancing CRS research. This review offers a thorough summary of the current research landscape in this domain and identifies promising directions for future inquiry.
comment: 6 pages, 1 figures, accepted as a poster for CSWIM 2025
☆ Irec: A Metacognitive Scaffolding for Self-Regulated Learning through Just-in-Time Insight Recall: A Conceptual Framework and System Prototype
The core challenge in learning has shifted from knowledge acquisition to effective Self-Regulated Learning (SRL): planning, monitoring, and reflecting on one's learning. Existing digital tools, however, inadequately support metacognitive reflection. Spaced Repetition Systems (SRS) use de-contextualized review, overlooking the role of context, while Personal Knowledge Management (PKM) tools require high manual maintenance. To address these challenges, this paper introduces "Insight Recall," a novel paradigm that conceptualizes the context-triggered retrieval of personal past insights as a metacognitive scaffold to promote SRL. We formalize this paradigm using the Just-in-Time Adaptive Intervention (JITAI) framework and implement a prototype system, Irec, to demonstrate its feasibility. At its core, Irec uses a dynamic knowledge graph of the user's learning history. When a user faces a new problem, a hybrid retrieval engine recalls relevant personal "insights." Subsequently, a large language model (LLM) performs a deep similarity assessment to filter and present the most relevant scaffold in a just-in-time manner. To reduce cognitive load, Irec features a human-in-the-loop pipeline for LLM-based knowledge graph construction. We also propose an optional "Guided Inquiry" module, where users can engage in a Socratic dialogue with an expert LLM, using the current problem and recalled insights as context. The contribution of this paper is a solid theoretical framework and a usable system platform for designing next-generation intelligent learning systems that enhance metacognition and self-regulation.
comment: Version 1 of a work in progress. Finalized system flowcharts, a public GitHub repository with the source code, and a full reproducibility package detailing the prompts, models, and testing guidelines will be provided in v2
☆ Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision ICDE'24
Existing multi-media retrieval models either rely on creating a common subspace with modality-specific representation models or require schema mapping among modalities to measure similarities among multi-media data. Our goal is to avoid the annotation overhead incurred from considering retrieval as a supervised classification task and re-use the pretrained encoders in large language models and vision tasks. We propose "FemmIR", a framework to retrieve multimodal results relevant to information needs expressed with multimodal queries by example without any similarity label. Such identification is necessary for real-world applications where data annotations are scarce and satisfactory performance is required without fine-tuning with a common framework across applications. We curate a new dataset called MuQNOL for benchmarking progress on this task. Our technique is based on weak supervision introduced through edit distance between samples: graph edit distance can be modified to consider the cost of replacing a data sample in terms of its properties, and relevance can be measured through the implicit signal from the amount of edit cost among the objects. Unlike metric learning or encoding networks, FemmIR re-uses the high-level properties and maintains the property value and relationship constraints with a multi-level interaction score between data samples and the query example provided by the user. We empirically evaluate FemmIR on a missing person use case with MuQNOL. FemmIR performs comparably to similar retrieval systems in delivering on-demand retrieval results with exact and approximate similarities while using the existing property identifiers in the system.
comment: Submitted to ICDE'24. An earlier version of this paper appeared on TechRxiv: https://www.techrxiv.org/doi/full/10.36227/techrxiv.21990284.v1, uploaded on February 05, 2023
☆ Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
Retrieval-Augmented Generation (RAG) systems are emerging as a key approach for grounding Large Language Models (LLMs) in external knowledge, addressing limitations in factual accuracy and contextual relevance. However, there is a lack of empirical studies that report on the development of RAG-based implementations grounded in real-world use cases, evaluated through general user involvement, and accompanied by systematic documentation of lessons learned. This paper presents five domain-specific RAG applications developed for real-world scenarios across governance, cybersecurity, agriculture, industrial research, and medical diagnostics. Each system incorporates multilingual OCR, semantic retrieval via vector embeddings, and domain-adapted LLMs, deployed through local servers or cloud APIs to meet distinct user needs. A web-based evaluation involving a total of 100 participants assessed the systems across six dimensions: (i) Ease of Use, (ii) Relevance, (iii) Transparency, (iv) Responsiveness, (v) Accuracy, and (vi) Likelihood of Recommendation. Based on user feedback and our development experience, we documented twelve key lessons learned, highlighting technical, operational, and ethical challenges affecting the reliability and usability of RAG systems in practice.
comment: Accepted as a full paper to the 51st Euromicro Conference on Software Engineering and Advanced Applications (SEAA 2025). 9 pages, 4 figures. This is the preprint version and not the final camera ready version
☆ Towards Two-Stage Counterfactual Learning to Rank ICTIR 2025
Counterfactual learning to rank (CLTR) aims to learn a ranking policy from user interactions while correcting for the inherent biases in interaction data, such as position bias. Existing CLTR methods assume a single ranking policy that selects top-K ranking from the entire document candidate set. In real-world applications, the candidate document set is on the order of millions, making a single-stage ranking policy impractical. In order to scale to millions of documents, real-world ranking systems are designed in a two-stage fashion, with a candidate generator followed by a ranker. The existing CLTR method for a two-stage offline ranking system only considers the top-1 ranking set-up and only focuses on training the candidate generator, with the ranker fixed. A CLTR method for training both the ranker and candidate generator jointly is missing from the existing literature. In this paper, we propose a two-stage CLTR estimator that considers the interaction between the two stages and estimates the joint value of the two policies offline. In addition, we propose a novel joint optimization method to train the candidate and ranker policies, respectively. To the best of our knowledge, we are the first to propose a CLTR estimator and learning method for two-stage ranking. Experimental results on a semi-synthetic benchmark demonstrate the effectiveness of the proposed joint CLTR method over baselines.
comment: Accepted at ICTIR 2025 (co-located with SIGIR 2025)
☆ The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers SIGIR
Scientific fact-checking aims to determine the veracity of scientific claims by retrieving and analysing evidence from research literature. The problem is inherently more complex than general fact-checking since it must accommodate the evolving nature of scientific knowledge, the structural complexity of academic literature and the challenges posed by long-form, multimodal scientific expression. However, existing approaches focus on simplified versions of the problem based on small-scale datasets consisting of abstracts rather than full papers, thereby avoiding the distinct challenges associated with processing complete documents. This paper examines the limitations of current scientific fact-checking systems and reveals the many potential features and resources that could be exploited to advance their performance. It identifies key research challenges within evidence retrieval, including (1) evidence-driven retrieval that addresses semantic limitations and topic imbalance (2) time-aware evidence retrieval with citation tracking to mitigate outdated information, (3) structured document parsing to leverage long-range context, (4) handling complex scientific expressions, including tables, figures, and domain-specific terminology and (5) assessing the credibility of scientific literature. Preliminary experiments were conducted to substantiate these challenges and identify potential solutions. This perspective paper aims to advance scientific fact-checking with a specialised IR system tailored for real-world applications.
comment: Accepted for ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR'25)
☆ RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation
This paper addresses the challenge of developing multimodal recommender systems for the movie domain, where limited metadata (e.g., title, genre) often hinders the generation of robust recommendations. We introduce a resource that combines LLM-generated plot descriptions with trailer-derived visual embeddings in a unified pipeline supporting both Retrieval-Augmented Generation (RAG) and collaborative filtering. Central to our approach is a data augmentation step that transforms sparse metadata into richer textual signals, alongside fusion strategies (e.g., PCA, CCA) that integrate visual cues. Experimental evaluations demonstrate that CCA-based fusion significantly boosts recall compared to unimodal baselines, while an LLM-driven re-ranking step further improves NDCG, particularly in scenarios with limited textual data. By releasing this framework, we invite further exploration of multi-modal recommendation techniques tailored to cold-start, novelty-focused, and domain-specific settings. All code, data, and detailed documentation are publicly available at: https://github.com/RecSys-lab/RAG-VisualRec
comment: 20 pages, 6 figures, 5 tables
☆ Producer-Fairness in Sequential Bundle Recommendation
We address fairness in the context of sequential bundle recommendation, where users are served in turn with sets of relevant and compatible items. Motivated by real-world scenarios, we formalize producer-fairness, that seeks to achieve desired exposure of different item groups across users in a recommendation session. Our formulation combines naturally with building high quality bundles. Our problem is solved in real time as users arrive. We propose an exact solution that caters to small instances of our problem. We then examine two heuristics, quality-first and fairness-first, and an adaptive variant that determines on-the-fly the right balance between bundle fairness and quality. Our experiments on three real-world datasets underscore the strengths and limitations of each solution and demonstrate their efficacy in providing fair bundle recommendations without compromising bundle quality.
☆ Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data
The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e.g., CVPR, ICCV, KDD, AAAI, IJCAI, WSDM) to enforce strict per-author submission limits and to desk-reject any excess papers by simple ID order. While this policy helps reduce reviewer workload, it may unintentionally discard valuable papers and penalize authors' efforts. In this paper, we ask an essential research question on whether it is possible to follow submission limits while minimizing needless rejections. We first formalize the current desk-rejection policies as an optimization problem, and then develop a practical algorithm based on linear programming relaxation and a rounding scheme. Under extensive evaluation on 11 years of real-world ICLR (International Conference on Learning Representations) data, our method preserves up to $19.23\%$ more papers without violating any author limits. Moreover, our algorithm is highly efficient in practice, with all results on ICLR data computed within at most 53.64 seconds. Our work provides a simple and practical desk-rejection strategy that significantly reduces unnecessary rejections, demonstrating strong potential to improve current CS conference submission policies.
♻ ☆ Mapping the Evolution of Research Contributions using KnoVo
This paper presents KnoVo (Knowledge Evolution), an intelligent framework designed for quantifying and analyzing the evolution of research novelty in the scientific literature. Moving beyond traditional citation analysis, which primarily measures impact, KnoVo determines a paper's novelty relative to both prior and subsequent work within its multilayered citation network. Given a target paper's abstract, KnoVo utilizes Large Language Models (LLMs) to dynamically extract dimensions of comparison (e.g., methodology, application, dataset). The target paper is then compared to related publications along these same extracted dimensions. This comparative analysis, inspired by tournament selection, yields quantitative novelty scores reflecting the relative improvement, equivalence, or inferiority of the target paper in specific aspects. By aggregating these scores and visualizing their progression, for instance, through dynamic evolution graphs and comparative radar charts, KnoVo facilitates researchers not only to assess originality and identify similar work, but also to track knowledge evolution along specific research dimensions, uncover research gaps, and explore cross-disciplinary connections. We demonstrate these capabilities through a detailed analysis of 20 diverse papers from multiple scientific fields and report on the performance of various open-source LLMs within the KnoVo framework.
♻ ☆ Forgetful by Design? A Critical Audit of YouTube's Search API for Academic Research
This paper critically audits the search endpoint of YouTube's Data API (v3), a common tool for academic research. Through systematic weekly searches over six months using eleven queries, we identify major limitations regarding completeness, representativeness, consistency, and bias. Our findings reveal substantial differences between ranking parameters like relevance and date in terms of video recall and precision, with relevance often retrieving numerous off-topic videos. We also find severe temporal decay, as the number of findable videos for a specific period dramatically decreases after just 20-60 days from the publication date, potentially hampering many different research designs. Furthermore, search results lack consistency, with identical queries yielding different video sets over time, compromising replicability. A case study on the European Parliament elections highlights how these issues impact research outcomes. While the paper offers several mitigation strategies, it concludes that the API's search function, potentially prioritizing "freshness" over comprehensive retrieval, is not adequate for robust academic research, especially concerning Digital Services Act requirements.
comment: 15 pages, 2 tables and 4 figures
♻ ☆ Diffusion Recommender Model SIGIR'23
Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic limitations such as the instability of GANs and the restricted representation ability of VAEs. Such limitations hinder the accurate modeling of the complex user interaction generation procedure, such as noisy interactions caused by various interference factors. In light of the impressive advantages of Diffusion Models (DMs) over traditional generative models in image synthesis, we propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner. To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis. In addition, we extend traditional DMs to tackle the unique challenges in practical recommender systems: high resource costs for large-scale item prediction and temporal shifts of user preference. To this end, we propose two extensions of DiffRec: L-DiffRec clusters items for dimension compression and conducts the diffusion processes in the latent space; and T-DiffRec reweights user interactions based on the interaction timestamps to encode temporal information. We conduct extensive experiments on three datasets under multiple settings (e.g. clean training, noisy training, and temporal training). The empirical results and in-depth analysis validate the superiority of DiffRec with two extensions over competitive baselines.
comment: 10 pages, 7 figures, accepted for publication in SIGIR'23
♻ ☆ Dual-Channel Multiplex Graph Neural Networks for Recommendation
Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our DCMGNN surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10, respectively.
♻ ☆ AI-Driven Sentiment Analytics: Unlocking Business Value in the E-Commerce Landscape
The rapid growth of e-commerce has led to an overwhelming volume of customer feedback, from product reviews to service interactions. Extracting meaningful insights from this data is crucial for businesses aiming to improve customer satisfaction and optimize decision-making. This paper presents an AI-driven sentiment analysis system designed specifically for e-commerce applications, balancing accuracy with interpretability. Our approach integrates traditional machine learning techniques with modern deep learning models, allowing for a more nuanced understanding of customer sentiment while ensuring transparency in decision-making. Experimental results show that our system outperforms standard sentiment analysis methods, achieving an accuracy of 89.7% on diverse, large-scale datasets. Beyond technical performance, real-world implementation across multiple e-commerce platforms demonstrates tangible improvements in customer engagement and operational efficiency. This study highlights both the potential and the challenges of applying AI to sentiment analysis in a commercial setting, offering insights into practical deployment strategies and areas for future refinement.
comment: 7 pages
♻ ☆ InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset.
comment: 11 pages, 6 figures
Multimedia 8
☆ Deciphering GunType Hierarchy through Acoustic Analysis of Gunshot Recordings
The escalating rates of gun-related violence and mass shootings represent a significant threat to public safety. Timely and accurate information for law enforcement agencies is crucial in mitigating these incidents. Current commercial gunshot detection systems, while effective, often come with prohibitive costs. This research explores a cost-effective alternative by leveraging acoustic analysis of gunshot recordings, potentially obtainable from ubiquitous devices like cell phones, to not only detect gunshots but also classify the type of firearm used. This paper details a study on deciphering gun type hierarchies using a curated dataset of 3459 recordings. We investigate the fundamental acoustic characteristics of gunshots, including muzzle blasts and shockwaves, which vary based on firearm type, ammunition, and shooting direction. We propose and evaluate machine learning frameworks, including Support Vector Machines (SVMs) as a baseline and a more advanced Convolutional Neural Network (CNN) architecture for joint gunshot detection and gun type classification. Results indicate that our deep learning approach achieves a mean average precision (mAP) of 0.58 on clean labeled data, outperforming the SVM baseline (mAP 0.39). Challenges related to data quality, environmental noise, and the generalization capabilities when using noisy web-sourced data (mAP 0.35) are also discussed. The long-term vision is to develop a highly accurate, real-time system deployable on common recording devices, significantly reducing detection costs and providing critical intelligence to first responders.
comment: 4 pages + 1 References
☆ Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.
comment: 20 pages, 10 figures
☆ Multimodal Representation Learning and Fusion
Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each modality, multi-modal learning allows AI systems to build stronger and richer internal representations. These help machines better interpretation, reasoning, and making decisions in real-life situations. This field includes core techniques such as representation learning (to get shared features from different data types), alignment methods (to match information across modalities), and fusion strategies (to combine them by deep learning models). Although there has been good progress, some major problems still remain. Like dealing with different data formats, missing or incomplete inputs, and defending against adversarial attacks. Researchers now are exploring new methods, such as unsupervised or semi-supervised learning, AutoML tools, to make models more efficient and easier to scale. And also more attention on designing better evaluation metrics or building shared benchmarks, make it easier to compare model performance across tasks and domains. As the field continues to grow, multi-modal learning is expected to improve many areas: computer vision, natural language processing, speech recognition, and healthcare. In the future, it may help to build AI systems that can understand the world in a way more like humans, flexible, context aware, and able to deal with real-world complexity.
☆ InvZW: Invariant Feature Learning via Noise-Adversarial Training for Robust Image Zero-Watermarking
This paper introduces a novel deep learning framework for robust image zero-watermarking based on distortion-invariant feature learning. As a zero-watermarking scheme, our method leaves the original image unaltered and learns a reference signature through optimization in the feature space. The proposed framework consists of two key modules. In the first module, a feature extractor is trained via noise-adversarial learning to generate representations that are both invariant to distortions and semantically expressive. This is achieved by combining adversarial supervision against a distortion discriminator and a reconstruction constraint to retain image content. In the second module, we design a learning-based multibit zero-watermarking scheme where the trained invariant features are projected onto a set of trainable reference codes optimized to match a target binary message. Extensive experiments on diverse image datasets and a wide range of distortions show that our method achieves state-of-the-art robustness in both feature stability and watermark recovery. Comparative evaluations against existing self-supervised and deep watermarking techniques further highlight the superiority of our framework in generalization and robustness.
☆ UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existing codebook-based methods either rely on small vocabularies (~16K entries) that lack fine-grained semantics or naively scale up, resulting in low token utilization and unstable training. We propose UniCode$^2$, a cascaded codebook framework enabling large-scale, semantically aligned, and stable visual tokenization. By clustering millions of SigLIP sequence embeddings, we build a 500K-entry codebook that preserves vision-language alignment while expanding capacity. Stability is ensured via a cascaded design: a frozen codebook anchors the embedding space, and a trainable codebook refines task-specific semantics. This decoupling promotes high utilization and robust learning. Moreover, the alignment of our visual tokens with textual semantics enables seamless integration with pretrained diffusion decoders, supporting high-quality visual synthesis with minimal adaptation. UniCode^2 delivers strong performance across diverse benchmarks, demonstrating the viability of scaling visual token spaces without sacrificing stability, semantics, or modularity.
comment: 19 pages, 5 figures
☆ Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision ICDE'24
Existing multi-media retrieval models either rely on creating a common subspace with modality-specific representation models or require schema mapping among modalities to measure similarities among multi-media data. Our goal is to avoid the annotation overhead incurred from considering retrieval as a supervised classification task and re-use the pretrained encoders in large language models and vision tasks. We propose "FemmIR", a framework to retrieve multimodal results relevant to information needs expressed with multimodal queries by example without any similarity label. Such identification is necessary for real-world applications where data annotations are scarce and satisfactory performance is required without fine-tuning with a common framework across applications. We curate a new dataset called MuQNOL for benchmarking progress on this task. Our technique is based on weak supervision introduced through edit distance between samples: graph edit distance can be modified to consider the cost of replacing a data sample in terms of its properties, and relevance can be measured through the implicit signal from the amount of edit cost among the objects. Unlike metric learning or encoding networks, FemmIR re-uses the high-level properties and maintains the property value and relationship constraints with a multi-level interaction score between data samples and the query example provided by the user. We empirically evaluate FemmIR on a missing person use case with MuQNOL. FemmIR performs comparably to similar retrieval systems in delivering on-demand retrieval results with exact and approximate similarities while using the existing property identifiers in the system.
comment: Submitted to ICDE'24. An earlier version of this paper appeared on TechRxiv: https://www.techrxiv.org/doi/full/10.36227/techrxiv.21990284.v1, uploaded on February 05, 2023
☆ RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation
This paper addresses the challenge of developing multimodal recommender systems for the movie domain, where limited metadata (e.g., title, genre) often hinders the generation of robust recommendations. We introduce a resource that combines LLM-generated plot descriptions with trailer-derived visual embeddings in a unified pipeline supporting both Retrieval-Augmented Generation (RAG) and collaborative filtering. Central to our approach is a data augmentation step that transforms sparse metadata into richer textual signals, alongside fusion strategies (e.g., PCA, CCA) that integrate visual cues. Experimental evaluations demonstrate that CCA-based fusion significantly boosts recall compared to unimodal baselines, while an LLM-driven re-ranking step further improves NDCG, particularly in scenarios with limited textual data. By releasing this framework, we invite further exploration of multi-modal recommendation techniques tailored to cold-start, novelty-focused, and domain-specific settings. All code, data, and detailed documentation are publicly available at: https://github.com/RecSys-lab/RAG-VisualRec
comment: 20 pages, 6 figures, 5 tables
♻ ☆ EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations
In recent years, emotion recognition plays a critical role in applications such as human-computer interaction, mental health monitoring, and sentiment analysis. While datasets for emotion analysis in languages such as English have proliferated, there remains a pressing need for high-quality, comprehensive datasets tailored to the unique linguistic, cultural, and multimodal characteristics of Chinese. In this work, we propose \textbf{EmotionTalk}, an interactive Chinese multimodal emotion dataset with rich annotations. This dataset provides multimodal information from 19 actors participating in dyadic conversational settings, incorporating acoustic, visual, and textual modalities. It includes 23.6 hours of speech (19,250 utterances), annotations for 7 utterance-level emotion categories (happy, surprise, sad, disgust, anger, fear, and neutral), 5-dimensional sentiment labels (negative, weakly negative, neutral, weakly positive, and positive) and 4-dimensional speech captions (speaker, speaking style, emotion and overall). The dataset is well-suited for research on unimodal and multimodal emotion recognition, missing modality challenges, and speech captioning tasks. To our knowledge, it represents the first high-quality and versatile Chinese dialogue multimodal emotion dataset, which is a valuable contribution to research on cross-cultural emotion analysis and recognition. Additionally, we conduct experiments on EmotionTalk to demonstrate the effectiveness and quality of the dataset. It will be open-source and freely available for all academic purposes. The dataset and codes will be made available at: https://github.com/NKU-HLT/EmotionTalk.
Information Retrieval 14
☆ KnowML: Improving Generalization of ML-NIDS with Attack Knowledge Graphs
Despite extensive research on Machine Learning-based Network Intrusion Detection Systems (ML-NIDS), their capability to detect diverse attack variants remains uncertain. Prior studies have largely relied on homogeneous datasets, which artificially inflate performance scores and offer a false sense of security. Designing systems that can effectively detect a wide range of attack variants remains a significant challenge. The progress of ML-NIDS continues to depend heavily on human expertise, which can embed subjective judgments of system designers into the model, potentially hindering its ability to generalize across diverse attack types. To address this gap, we propose KnowML, a framework for knowledge-guided machine learning that integrates attack knowledge into ML-NIDS. KnowML systematically explores the threat landscape by leveraging Large Language Models (LLMs) to perform automated analysis of attack implementations. It constructs a unified Knowledge Graph (KG) of attack strategies, on which it applies symbolic reasoning to generate KG-Augmented Input, embedding domain knowledge directly into the design process of ML-NIDS. We evaluate KnowML on 28 realistic attack variants, of which 10 are newly collected for this study. Our findings reveal that baseline ML-NIDS models fail to detect several variants entirely, achieving F1 scores as low as 0 %. In contrast, our knowledge-guided approach achieves up to 99 % F1 score while maintaining a False Positive Rate below 0.1 %.
☆ Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study
Large Language Models (LLMs) hold promise in automating data analysis tasks, yet open-source models face significant limitations in these kinds of reasoning-intensive scenarios. In this work, we investigate strategies to enhance the data analysis capabilities of open-source LLMs. By curating a seed dataset of diverse, realistic scenarios, we evaluate models across three dimensions: data understanding, code generation, and strategic planning. Our analysis reveals three key findings: (1) Strategic planning quality serves as the primary determinant of model performance; (2) Interaction design and task complexity significantly influence reasoning capabilities; (3) Data quality demonstrates a greater impact than diversity in achieving optimal performance. We leverage these insights to develop a data synthesis methodology, demonstrating significant improvements in open-source LLMs' analytical reasoning capabilities.
comment: Work in progress
☆ Alleviating User-Sensitive bias with Fair Generative Sequential Recommendation Model
Recommendation fairness has recently attracted much attention. In the real world, recommendation systems are driven by user behavior, and since users with the same sensitive feature (e.g., gender and age) tend to have the same patterns, recommendation models can easily capture the strong correlation preference of sensitive features and thus cause recommendation unfairness. Diffusion model (DM) as a new generative model paradigm has achieved great success in recommendation systems. DM's ability to model uncertainty and represent diversity, and its modeling mechanism has a high degree of adaptability with the real-world recommendation process with bias. Therefore, we use DM to effectively model the fairness of recommendation and enhance the diversity. This paper proposes a FairGENerative sequential Recommendation model based on DM, FairGENRec. In the training phase, we inject random noise into the original distribution under the guidance of the sensitive feature recognition model, and a sequential denoise model is designed for the reverse reconstruction of items. Simultaneously, recommendation fairness modeling is completed by injecting multi-interests representational information that eliminates the bias of sensitive user features into the generated results. In the inference phase, the model obtains the noise in the form of noise addition by using the history interactions which is followed by reverse iteration to reconstruct the target item representation. Finally, our extensive experiments on three datasets demonstrate the dual enhancement effect of FairGENRec on accuracy and fairness, while the statistical analysis of the cases visualizes the degree of improvement on the fairness of the recommendation.
☆ NEAR$^2$: A Nested Embedding Approach to Efficient Product Retrieval and Ranking SIGIR
E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast product catalogs. The dual challenge lies in precisely matching user intent with relevant products while managing the computational demands of real-time search across massive inventories. In this paper, we propose a Nested Embedding Approach to product Retrieval and Ranking, called NEAR$^2$, which can achieve up to $12$ times efficiency in embedding size at inference time while introducing no extra cost in training and improving performance in accuracy for various encoder-based Transformer models. We validate our approach using different loss functions for the retrieval and ranking task, including multiple negative ranking loss and online contrastive loss, on four different test sets with various IR challenges such as short and implicit queries. Our approach achieves an improved performance over a smaller embedding dimension, compared to any existing models.
comment: This paper is accepted to the 2025 SIGIR Workshop on eCommerce
☆ Higher-Order Graph Databases
Recent advances in graph databases (GDBs) have been driving interest in large-scale analytics, yet current systems fail to support higher-order (HO) interactions beyond first-order (one-hop) relations, which are crucial for tasks such as subgraph counting, polyadic modeling, and HO graph learning. We address this by introducing a new class of systems, higher-order graph databases (HO-GDBs) that use lifting and lowering paradigms to seamlessly extend traditional GDBs with HO. We provide a theoretical analysis of OLTP and OLAP queries, ensuring correctness, scalability, and ACID compliance. We implement a lightweight, modular, and parallelizable HO-GDB prototype that offers native support for hypergraphs, node-tuples, subgraphs, and other HO structures under a unified API. The prototype scales to large HO OLTP & OLAP workloads and shows how HO improves analytical tasks, for example enhancing accuracy of graph neural networks within a GDB by 44%. Our work ensures low latency and high query throughput, and generalizes both ACID-compliant and eventually consistent systems.
☆ Health Sentinel: An AI Pipeline For Real-time Disease Outbreak Detection
Early detection of disease outbreaks is crucial to ensure timely intervention by the health authorities. Due to the challenges associated with traditional indicator-based surveillance, monitoring informal sources such as online media has become increasingly popular. However, owing to the number of online articles getting published everyday, manual screening of the articles is impractical. To address this, we propose Health Sentinel. It is a multi-stage information extraction pipeline that uses a combination of ML and non-ML methods to extract events-structured information concerning disease outbreaks or other unusual health events-from online articles. The extracted events are made available to the Media Scanning and Verification Cell (MSVC) at the National Centre for Disease Control (NCDC), Delhi for analysis, interpretation and further dissemination to local agencies for timely intervention. From April 2022 till date, Health Sentinel has processed over 300 million news articles and identified over 95,000 unique health events across India of which over 3,500 events were shortlisted by the public health experts at NCDC as potential outbreaks.
☆ Controlled Retrieval-augmented Context Evaluation for Long-form RAG
Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking metrics, such metrics may be insufficient to reflect the retrieval's impact on the final RAG result, especially in long-form generation scenarios. We argue that providing a comprehensive retrieval-augmented context is important for long-form RAG tasks like report generation and propose metrics for assessing the context independent of generation. We introduce CRUX, a \textbf{C}ontrolled \textbf{R}etrieval-a\textbf{U}gmented conte\textbf{X}t evaluation framework designed to directly assess retrieval-augmented contexts. This framework uses human-written summaries to control the information scope of knowledge, enabling us to measure how well the context covers information essential for long-form generation. CRUX uses question-based evaluation to assess RAG's retrieval in a fine-grained manner. Empirical results show that CRUX offers more reflective and diagnostic evaluation. Our findings also reveal substantial room for improvement in current retrieval methods, pointing to promising directions for advancing RAG's retrieval. Our data and code are publicly available to support and advance future research on retrieval.
☆ LSH-DynED: A Dynamic Ensemble Framework with LSH-Based Undersampling for Evolving Multi-Class Imbalanced Classification
The classification of imbalanced data streams, which have unequal class distributions, is a key difficulty in machine learning, especially when dealing with multiple classes. While binary imbalanced data stream classification tasks have received considerable attention, only a few studies have focused on multi-class imbalanced data streams. Effectively managing the dynamic imbalance ratio is a key challenge in this domain. This study introduces a novel, robust, and resilient approach to address these challenges by integrating Locality Sensitive Hashing with Random Hyperplane Projections (LSH-RHP) into the Dynamic Ensemble Diversification (DynED) framework. To the best of our knowledge, we present the first application of LSH-RHP for undersampling in the context of imbalanced non-stationary data streams. The proposed method undersamples the majority classes by utilizing LSH-RHP, provides a balanced training set, and improves the ensemble's prediction performance. We conduct comprehensive experiments on 23 real-world and ten semi-synthetic datasets and compare LSH-DynED with 15 state-of-the-art methods. The results reveal that LSH-DynED outperforms other approaches in terms of both Kappa and mG-Mean effectiveness measures, demonstrating its capability in dealing with multi-class imbalanced non-stationary data streams. Notably, LSH-DynED performs well in large-scale, high-dimensional datasets with considerable class imbalances and demonstrates adaptation and robustness in real-world circumstances. To motivate our design, we review existing methods for imbalanced data streams, outline key challenges, and offer guidance for future work. For the reproducibility of our results, we have made our implementation available on GitHub.
☆ CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems ACL 2025
Recommender systems play a pivotal role in providing relevant content to users. With the rapid development of large language models (LLMs), researchers have begun utilizing LLMs to build more powerful recommender systems. However, existing approaches that focus on aligning LLMs with recommendation tasks do not fully leverage their sequential information processing capabilities, leading to suboptimal performance. In this paper, we propose a novel system called compressed vocabulary expansion (CoVE). In CoVE, each item is assigned a unique ID within the expanded vocabulary. Our framework effectively capitalizes on sequence understanding abilities of LLMs, significantly enhancing their performance on recommendation tasks. Additionally, we compress the embedding layer, making CoVE practical for large-scale industrial applications. The effectiveness and performance of CoVE are demonstrated through comprehensive experiments on multiple recommendation datasets and comparisons with prior works. Our code can be found at https://github.com/HaochenZhang717/CoVE-official-Repo.
comment: Accepted by ACL 2025 Findings
♻ ☆ jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-vector and multi-vector embeddings in the late interaction style. The model incorporates task-specific Low-Rank Adaptation (LoRA) adapters to optimize performance across diverse retrieval scenarios, including query-document retrieval, semantic text similarity, and code search. Comprehensive evaluations demonstrate that jina-embeddings-v4 achieves state-of-the-art performance on both single-modal and cross-modal retrieval tasks, with particular strength in processing visually rich content such as tables, charts, diagrams, and mixed-media formats. To facilitate evaluation of this capability, we also introduce Jina-VDR, a novel benchmark specifically designed for visually rich image retrieval.
comment: 22 pages, 1-10 main, 14-22 experimental results, benchmark tables
♻ ☆ Talking to GDELT Through Knowledge Graphs
In this work we study various Retrieval Augmented Regeneration (RAG) approaches to gain an understanding of the strengths and weaknesses of each approach in a question-answering analysis. To gain this understanding we use a case-study subset of the Global Database of Events, Language, and Tone (GDELT) dataset as well as a corpus of raw text scraped from the online news articles. To retrieve information from the text corpus we implement a traditional vector store RAG as well as state-of-the-art large language model (LLM) based approaches for automatically constructing KGs and retrieving the relevant subgraphs. In addition to these corpus approaches, we develop a novel ontology-based framework for constructing knowledge graphs (KGs) from GDELT directly which leverages the underlying schema of GDELT to create structured representations of global events. For retrieving relevant information from the ontology-based KGs we implement both direct graph queries and state-of-the-art graph retrieval approaches. We compare the performance of each method in a question-answering task. We find that while our ontology-based KGs are valuable for question-answering, automated extraction of the relevant subgraphs is challenging. Conversely, LLM-generated KGs, while capturing event summaries, often lack consistency and interpretability. Our findings suggest benefits of a synergistic approach between ontology and LLM-based KG construction, with proposed avenues toward that end.
♻ ☆ Answering Multimodal Exclusion Queries with Lightweight Sparse Disentangled Representations SIGIR
Multimodal representations that enable cross-modal retrieval are widely used. However, these often lack interpretability making it difficult to explain the retrieved results. Solutions such as learning sparse disentangled representations are typically guided by the text tokens in the data, making the dimensionality of the resulting embeddings very high. We propose an approach that generates smaller dimensionality fixed-size embeddings that are not only disentangled but also offer better control for retrieval tasks. We demonstrate their utility using challenging exclusion queries over MSCOCO and Conceptual Captions benchmarks. Our experiments show that our approach is superior to traditional dense models such as CLIP, BLIP and VISTA (gains up to 11% in AP@10), as well as sparse disentangled models like VDR (gains up to 21% in AP@10). We also present qualitative results to further underline the interpretability of disentangled representations.
comment: In Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)
♻ ☆ Entropy and type-token ratio in gigaword corpora
There are different ways of measuring diversity in complex systems. In particular, in language, lexical diversity is characterized in terms of the type-token ratio and the word entropy. We here investigate both diversity metrics in six massive linguistic datasets in English, Spanish, and Turkish, consisting of books, news articles, and tweets. These gigaword corpora correspond to languages with distinct morphological features and differ in registers and genres, thus constituting a varied testbed for a quantitative approach to lexical diversity. We unveil an empirical functional relation between entropy and type-token ratio of texts of a given corpus and language, which is a consequence of the statistical laws observed in natural language. Further, in the limit of large text lengths we find an analytical expression for this relation relying on both Zipf and Heaps laws that agrees with our empirical findings.
comment: 15 pages, 10 figures, 8 tables
♻ ☆ Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation
Embedding-Based Retrieval (EBR) is an important technique in modern search engines, enabling semantic match between search queries and relevant results. However, search logging data on platforms like Facebook Marketplace lacks the diversity and details needed for effective EBR model training, limiting the models' ability to capture nuanced search patterns. To address this challenge, we propose Aug2Search, an EBR-based framework leveraging synthetic data generated by Generative AI (GenAI) models, in a multimodal and multitask approach to optimize query-product relevance. This paper investigates the capabilities of GenAI, particularly Large Language Models (LLMs), in generating high-quality synthetic data, and analyzing its impact on enhancing EBR models. We conducted experiments using eight Llama models and 100 million data points from Facebook Marketplace logs. Our synthetic data generation follows three strategies: (1) generate queries, (2) enhance product listings, and (3) generate queries from enhanced listings. We train EBR models on three different datasets: sampled engagement data or original data ((e.g., "Click" and "Listing Interactions")), synthetic data, and a mixture of both engagement and synthetic data to assess their performance across various training sets. Our findings underscore the robustness of Llama models in producing synthetic queries and listings with high coherence, relevance, and diversity, while maintaining low levels of hallucination. Aug2Search achieves an improvement of up to 4% in ROC_AUC with 100 million synthetic data samples, demonstrating the effectiveness of our approach. Moreover, our experiments reveal that with the same volume of training data, models trained exclusively on synthetic data often outperform those trained on original data only or a mixture of original and synthetic data.
Computer Vision and Pattern Recognition 159
☆ Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Energy Decay in video diffusion models: post-softmax attention scores diminish as spatial and temporal distance between tokens increase, akin to the physical decay of signal or waves over space and time in nature. Motivated by this, we propose Radial Attention, a scalable sparse attention mechanism with $O(n \log n)$ complexity that translates energy decay into exponentially decaying compute density, which is significantly more efficient than standard $O(n^2)$ dense attention and more expressive than linear attention. Specifically, Radial Attention employs a simple, static attention mask where each token attends to spatially nearby tokens, with the attention window size shrinking with temporal distance. Moreover, it allows pre-trained video diffusion models to extend their generation length with efficient LoRA-based fine-tuning. Extensive experiments show that Radial Attention maintains video quality across Wan2.1-14B, HunyuanVideo, and Mochi 1, achieving up to a 1.9$\times$ speedup over the original dense attention. With minimal tuning, it enables video generation up to 4$\times$ longer while reducing training costs by up to 4.4$\times$ compared to direct fine-tuning and accelerating inference by up to 3.7$\times$ compared to dense attention inference.
comment: Code: https://github.com/mit-han-lab/radial-attention
☆ AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowledge to the 3D domain, supporting diverse articulated meshes with arbitrary skeletons. Our method represents 3D motion as multi-view, multi-frame 2D pose maps, and enables joint video-pose diffusion conditioned on template renderings and a textual motion prompt. We introduce shared positional encodings and modality-aware embeddings to ensure spatial-temporal alignment between video and pose sequences, effectively transferring video priors to motion generation task. The resulting multi-view pose sequences are triangulated into 3D joint positions and converted into mesh animation via inverse kinematics. Trained on a newly curated dataset of 160,000 rigged sequences, AnimaX achieves state-of-the-art results on VBench in generalization, motion fidelity, and efficiency, offering a scalable solution for category-agnostic 3D animation. Project page: \href{https://anima-x.github.io/}{https://anima-x.github.io/}.
comment: Project page: https://anima-x.github.io/
☆ Unified Vision-Language-Action Model
Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to generate action signals, often overlooking the rich temporal and causal structure embedded in visual observations. In this paper, we present UniVLA, a unified and native multimodal VLA model that autoregressively models vision, language, and action signals as discrete token sequences. This formulation enables flexible multimodal tasks learning, particularly from large-scale video data. By incorporating world modeling during post-training, UniVLA captures causal dynamics from videos, facilitating effective transfer to downstream policy learning--especially for long-horizon tasks. Our approach sets new state-of-the-art results across several widely used simulation benchmarks, including CALVIN, LIBERO, and Simplenv-Bridge, significantly surpassing previous methods. For example, UniVLA achieves 95.5% average success rate on LIBERO benchmark, surpassing pi0-FAST's 85.5%. We further demonstrate its broad applicability on real-world ALOHA manipulation and autonomous driving.
comment: technical report
☆ ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality image captioning lie in the inherent biases of LVLMs: multimodal bias resulting in imbalanced descriptive granularity, offering detailed accounts of some elements while merely skimming over others; linguistic bias leading to hallucinated descriptions of non-existent objects. To address these issues, we propose a scalable debiased captioning strategy, which continuously enriches and calibrates the caption with increased inference budget. Specifically, we propose two novel components: heuristic question answering and contrastive sentence rating. The former generates content-specific questions based on the image and answers them to progressively inject relevant information into the caption. The latter employs sentence-level offline contrastive decoding to effectively identify and eliminate hallucinations caused by linguistic biases. With increased inference cost, more heuristic questions are raised by ScaleCap to progressively capture additional visual details, generating captions that are more accurate, balanced, and informative. Extensive modality alignment experiments demonstrate the effectiveness of ScaleCap. Annotating 450K images with ScaleCap and using them for LVLM pretraining leads to consistent performance gains across 11 widely used benchmarks. Furthermore, ScaleCap showcases superb richness and fidelity of generated captions with two additional tasks: replacing images with captions in VQA task, and reconstructing images from captions to assess semantic coverage. Code is available at https://github.com/Cooperx521/ScaleCap.
comment: Code is available at https://github.com/Cooperx521/ScaleCap
☆ Orthogonal Finetuning Made Scalable
Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment. We identify the core computational bottleneck in OFT as its weight-centric implementation, which relies on costly matrix-matrix multiplications with cubic complexity. To overcome this, we propose OFTv2, an input-centric reformulation that instead uses matrix-vector multiplications (i.e., matrix-free computation), reducing the computational cost to quadratic. We further introduce the Cayley-Neumann parameterization, an efficient orthogonal parameterization that approximates the matrix inversion in Cayley transform via a truncated Neumann series. These modifications allow OFTv2 to achieve up to 10x faster training and 3x lower GPU memory usage without compromising performance. In addition, we extend OFTv2 to support finetuning quantized foundation models and show that it outperforms the popular QLoRA in training stability, efficiency, and memory usage.
comment: Technical report (17 pages, 7 figures, project page: https://spherelab.ai/oftv2/)
☆ A Comparative Study of NAFNet Baselines for Image Restoration
We study NAFNet (Nonlinear Activation Free Network), a simple and efficient deep learning baseline for image restoration. By using CIFAR10 images corrupted with noise and blur, we conduct an ablation study of NAFNet's core components. Our baseline model implements SimpleGate activation, Simplified Channel Activation (SCA), and LayerNormalization. We compare this baseline to different variants that replace or remove components. Quantitative results (PSNR, SSIM) and examples illustrate how each modification affects restoration performance. Our findings support the NAFNet design: the SimpleGate and simplified attention mechanisms yield better results than conventional activations and attention, while LayerNorm proves to be important for stable training. We conclude with recommendations for model design, discuss potential improvements, and future work.
☆ Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment
We tackle active view selection in novel view synthesis and 3D reconstruction. Existing methods like FisheRF and ActiveNeRF select the next best view by minimizing uncertainty or maximizing information gain in 3D, but they require specialized designs for different 3D representations and involve complex modelling in 3D space. Instead, we reframe this as a 2D image quality assessment (IQA) task, selecting views where current renderings have the lowest quality. Since ground-truth images for candidate views are unavailable, full-reference metrics like PSNR and SSIM are inapplicable, while no-reference metrics, such as MUSIQ and MANIQA, lack the essential multi-view context. Inspired by a recent cross-referencing quality framework CrossScore, we train a model to predict SSIM within a multi-view setup and use it to guide view selection. Our cross-reference IQA framework achieves substantial quantitative and qualitative improvements across standard benchmarks, while being agnostic to 3D representations, and runs 14-33 times faster than previous methods.
comment: Project page: https://avs.active.vision/
☆ GenHSI: Controllable Generation of Human-Scene Interaction Videos
Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in using these models to generate long movie-like videos with rich human-object interactions that include unrealistic human-scene interaction, lack of subject identity preservation, and require expensive training. We propose GenHSI, a training-free method for controllable generation of long human-scene interaction videos (HSI). Taking inspiration from movie animation, our key insight is to overcome the limitations of previous work by subdividing the long video generation task into three stages: (1) script writing, (2) pre-visualization, and (3) animation. Given an image of a scene, a user description, and multiple images of a person, we use these three stages to generate long-videos that preserve human-identity and provide rich human-scene interactions. Script writing converts complex human tasks into simple atomic tasks that are used in the pre-visualization stage to generate 3D keyframes (storyboards). These 3D keyframes are rendered and animated by off-the-shelf video diffusion models for consistent long video generation with rich contacts in a 3D-aware manner. A key advantage of our work is that we alleviate the need for scanned, accurate scenes and create 3D keyframes from single-view images. We are the first to generate a long video sequence with a consistent camera pose that contains arbitrary numbers of character actions without training. Experiments demonstrate that our method can generate long videos that effectively preserve scene content and character identity with plausible human-scene interaction from a single image scene. Visit our project homepage https://kunkun0w0.github.io/project/GenHSI/ for more information.
☆ Improving Progressive Generation with Decomposable Flow Matching
Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models benefit from the coarse-to-fine nature of denoising, explicit multi-stage architectures are rarely adopted. These architectures have increased the complexity of the overall approach, introducing the need for a custom diffusion formulation, decomposition-dependent stage transitions, add-hoc samplers, or a model cascade. Our contribution, Decomposable Flow Matching (DFM), is a simple and effective framework for the progressive generation of visual media. DFM applies Flow Matching independently at each level of a user-defined multi-scale representation (such as Laplacian pyramid). As shown by our experiments, our approach improves visual quality for both images and videos, featuring superior results compared to prior multistage frameworks. On Imagenet-1k 512px, DFM achieves 35.2% improvements in FDD scores over the base architecture and 26.4% over the best-performing baseline, under the same training compute. When applied to finetuning of large models, such as FLUX, DFM shows faster convergence speed to the training distribution. Crucially, all these advantages are achieved with a single model, architectural simplicity, and minimal modifications to existing training pipelines.
comment: Project Webpage: https://snap-research.github.io/dfm/
☆ SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution
Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on latent computation becomes inadequate. A promising approach involves decoupling the process into two stages: semantic content generation and detail synthesis. The former employs a computationally intensive base model at lower resolutions, while the latter leverages a lightweight cascaded video super-resolution (VSR) model to achieve high-resolution output. In this work, we focus on studying key design principles for latter cascaded VSR models, which are underexplored currently. First, we propose two degradation strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator. Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs. These findings directly inform our architectural and training innovations. Finally, we introduce interleaving temporal unit and sparse local attention to achieve efficient training and inference, drastically reducing computational overhead. Extensive experiments demonstrate the superiority of our framework over existing methods, with ablation studies confirming the efficacy of each design choice. Our work establishes a simple yet effective baseline for cascaded video super-resolution generation, offering practical insights to guide future advancements in efficient cascaded synthesis systems.
comment: Project webpage available at https://simplegvr.github.io/
☆ Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router
Recent years have witnessed remarkable advances in audio-driven talking head generation. However, existing approaches predominantly focus on single-character scenarios. While some methods can create separate conversation videos between two individuals, the critical challenge of generating unified conversation videos with multiple physically co-present characters sharing the same spatial environment remains largely unaddressed. This setting presents two key challenges: audio-to-character correspondence control and the lack of suitable datasets featuring multi-character talking videos within the same scene. To address these challenges, we introduce Bind-Your-Avatar, an MM-DiT-based model specifically designed for multi-talking-character video generation in the same scene. Specifically, we propose (1) A novel framework incorporating a fine-grained Embedding Router that binds `who' and `speak what' together to address the audio-to-character correspondence control. (2) Two methods for implementing a 3D-mask embedding router that enables frame-wise, fine-grained control of individual characters, with distinct loss functions based on observed geometric priors and a mask refinement strategy to enhance the accuracy and temporal smoothness of the predicted masks. (3) The first dataset, to the best of our knowledge, specifically constructed for multi-talking-character video generation, and accompanied by an open-source data processing pipeline, and (4) A benchmark for the dual-talking-characters video generation, with extensive experiments demonstrating superior performance over multiple state-of-the-art methods.
☆ Look to Locate: Vision-Based Multisensory Navigation with 3-D Digital Maps for GNSS-Challenged Environments
In Global Navigation Satellite System (GNSS)-denied environments such as indoor parking structures or dense urban canyons, achieving accurate and robust vehicle positioning remains a significant challenge. This paper proposes a cost-effective, vision-based multi-sensor navigation system that integrates monocular depth estimation, semantic filtering, and visual map registration (VMR) with 3-D digital maps. Extensive testing in real-world indoor and outdoor driving scenarios demonstrates the effectiveness of the proposed system, achieving sub-meter accuracy of 92% indoors and more than 80% outdoors, with consistent horizontal positioning and heading average root mean-square errors of approximately 0.98 m and 1.25 {\deg}, respectively. Compared to the baselines examined, the proposed solution significantly reduced drift and improved robustness under various conditions, achieving positioning accuracy improvements of approximately 88% on average. This work highlights the potential of cost-effective monocular vision systems combined with 3D maps for scalable, GNSS-independent navigation in land vehicles.
☆ CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation
Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong generalization across manipulation tasks. However, they remain constrained by a single-frame observation paradigm and cannot fully benefit from the motion information offered by aggregated multi-frame historical observations, as the large vision-language backbone introduces substantial computational cost and inference latency. We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm through an efficient post-training stage. CronusVLA comprises three key components: (1) single-frame pretraining on large-scale embodied datasets with autoregressive action tokens prediction, which establishes an embodied vision-language foundation; (2) multi-frame encoding, adapting the prediction of vision-language backbones from discrete action tokens to motion features during post-training, and aggregating motion features from historical frames into a feature chunking; (3) cross-frame decoding, which maps the feature chunking to accurate actions via a shared decoder with cross-attention. By reducing redundant token computation and caching past motion features, CronusVLA achieves efficient inference. As an application of motion features, we further propose an action adaptation mechanism based on feature-action retrieval to improve model performance during finetuning. CronusVLA achieves state-of-the-art performance on SimplerEnv with 70.9% success rate, and 12.7% improvement over OpenVLA on LIBERO. Real-world Franka experiments also show the strong performance and robustness.
comment: 36 pages, 21 figures
☆ KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
Large Language Models (LLMs), particularly slow-thinking models, often exhibit severe hallucination, outputting incorrect content due to an inability to accurately recognize knowledge boundaries during reasoning. While Reinforcement Learning (RL) can enhance complex reasoning abilities, its outcome-oriented reward mechanism often lacks factual supervision over the thinking process, further exacerbating the hallucination problem. To address the high hallucination in slow-thinking models, we propose Knowledge-enhanced RL, KnowRL. KnowRL guides models to perform fact-based slow thinking by integrating a factuality reward, based on knowledge verification, into the RL training process, helping them recognize their knowledge boundaries. KnowRL guides models to perform fact-based slow thinking by integrating a factuality reward, based on knowledge verification, into the RL training process, helping them recognize their knowledge boundaries. This targeted factual input during RL training enables the model to learn and internalize fact-based reasoning strategies. By directly rewarding adherence to facts within the reasoning steps, KnowRL fosters a more reliable thinking process. Experimental results on three hallucination evaluation datasets and two reasoning evaluation datasets demonstrate that KnowRL effectively mitigates hallucinations in slow-thinking models while maintaining their original strong reasoning capabilities. Our code is available at https://github.com/zjunlp/KnowRL.
comment: Work in progress
☆ CoCo4D: Comprehensive and Complex 4D Scene Generation
Existing 4D synthesis methods primarily focus on object-level generation or dynamic scene synthesis with limited novel views, restricting their ability to generate multi-view consistent and immersive dynamic 4D scenes. To address these constraints, we propose a framework (dubbed as CoCo4D) for generating detailed dynamic 4D scenes from text prompts, with the option to include images. Our method leverages the crucial observation that articulated motion typically characterizes foreground objects, whereas background alterations are less pronounced. Consequently, CoCo4D divides 4D scene synthesis into two responsibilities: modeling the dynamic foreground and creating the evolving background, both directed by a reference motion sequence. Given a text prompt and an optional reference image, CoCo4D first generates an initial motion sequence utilizing video diffusion models. This motion sequence then guides the synthesis of both the dynamic foreground object and the background using a novel progressive outpainting scheme. To ensure seamless integration of the moving foreground object within the dynamic background, CoCo4D optimizes a parametric trajectory for the foreground, resulting in realistic and coherent blending. Extensive experiments show that CoCo4D achieves comparable or superior performance in 4D scene generation compared to existing methods, demonstrating its effectiveness and efficiency. More results are presented on our website https://colezwhy.github.io/coco4d/.
comment: 16 pages,10 figures
☆ Systematic Review of Pituitary Gland and Pituitary Adenoma Automatic Segmentation Techniques in Magnetic Resonance Imaging
Purpose: Accurate segmentation of both the pituitary gland and adenomas from magnetic resonance imaging (MRI) is essential for diagnosis and treatment of pituitary adenomas. This systematic review evaluates automatic segmentation methods for improving the accuracy and efficiency of MRI-based segmentation of pituitary adenomas and the gland itself. Methods: We reviewed 34 studies that employed automatic and semi-automatic segmentation methods. We extracted and synthesized data on segmentation techniques and performance metrics (such as Dice overlap scores). Results: The majority of reviewed studies utilized deep learning approaches, with U-Net-based models being the most prevalent. Automatic methods yielded Dice scores of 0.19--89.00\% for pituitary gland and 4.60--96.41\% for adenoma segmentation. Semi-automatic methods reported 80.00--92.10\% for pituitary gland and 75.90--88.36\% for adenoma segmentation. Conclusion: Most studies did not report important metrics such as MR field strength, age and adenoma size. Automated segmentation techniques such as U-Net-based models show promise, especially for adenoma segmentation, but further improvements are needed to achieve consistently good performance in small structures like the normal pituitary gland. Continued innovation and larger, diverse datasets are likely critical to enhancing clinical applicability.
☆ Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images
Fisheye cameras offer robots the ability to capture human movements across a wider field of view (FOV) than standard pinhole cameras, making them particularly useful for applications in human-robot interaction and automotive contexts. However, accurately detecting human poses in fisheye images is challenging due to the curved distortions inherent to fisheye optics. While various methods for undistorting fisheye images have been proposed, their effectiveness and limitations for poses that cover a wide FOV has not been systematically evaluated in the context of absolute human pose estimation from monocular fisheye images. To address this gap, we evaluate the impact of pinhole, equidistant and double sphere camera models, as well as cylindrical projection methods, on 3D human pose estimation accuracy. We find that in close-up scenarios, pinhole projection is inadequate, and the optimal projection method varies with the FOV covered by the human pose. The usage of advanced fisheye models like the double sphere model significantly enhances 3D human pose estimation accuracy. We propose a heuristic for selecting the appropriate projection model based on the detection bounding box to enhance prediction quality. Additionally, we introduce and evaluate on our novel dataset FISHnCHIPS, which features 3D human skeleton annotations in fisheye images, including images from unconventional angles, such as extreme close-ups, ground-mounted cameras, and wide-FOV poses, available at: https://www.vision.rwth-aachen.de/fishnchips
comment: Presented at IEEE International Conference on Robotics and Automation 2025
☆ NeRF-based CBCT Reconstruction needs Normalization and Initialization
Cone Beam Computed Tomography (CBCT) is widely used in medical imaging. However, the limited number and intensity of X-ray projections make reconstruction an ill-posed problem with severe artifacts. NeRF-based methods have achieved great success in this task. However, they suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network. Specifically, in each training step, only a subset of the hash encoder's parameters is used (local sparse), whereas all parameters in the neural network participate (global dense). Consequently, hash features generated in each step are highly misaligned, as they come from different subsets of the hash encoder. These misalignments from different training steps are then fed into the neural network, causing repeated inconsistent global updates in training, which leads to unstable training, slower convergence, and degraded reconstruction quality. Aiming to alleviate the impact of this local-global optimization mismatch, we introduce a Normalized Hash Encoder, which enhances feature consistency and mitigates the mismatch. Additionally, we propose a Mapping Consistency Initialization(MCI) strategy that initializes the neural network before training by leveraging the global mapping property from a well-trained model. The initialized neural network exhibits improved stability during early training, enabling faster convergence and enhanced reconstruction performance. Our method is simple yet effective, requiring only a few lines of code while substantially improving training efficiency on 128 CT cases collected from 4 different datasets, covering 7 distinct anatomical regions.
☆ Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls
The pursuit of efficient and controllable high-quality content generation remains a central challenge in artificial intelligence-generated content (AIGC). While one-step generators, enabled by diffusion distillation techniques, offer excellent generation quality and computational efficiency, adapting them to new control conditions--such as structural constraints, semantic guidelines, or external inputs--poses a significant challenge. Conventional approaches often necessitate computationally expensive modifications to the base model and subsequent diffusion distillation. This paper introduces Noise Consistency Training (NCT), a novel and lightweight approach to directly integrate new control signals into pre-trained one-step generators without requiring access to original training images or retraining the base diffusion model. NCT operates by introducing an adapter module and employs a noise consistency loss in the noise space of the generator. This loss aligns the adapted model's generation behavior across noises that are conditionally dependent to varying degrees, implicitly guiding it to adhere to the new control. Theoretically, this training objective can be understood as minimizing the distributional distance between the adapted generator and the conditional distribution induced by the new conditions. NCT is modular, data-efficient, and easily deployable, relying only on the pre-trained one-step generator and a control signal model. Extensive experiments demonstrate that NCT achieves state-of-the-art controllable generation in a single forward pass, surpassing existing multi-step and distillation-based methods in both generation quality and computational efficiency. Code is available at https://github.com/Luo-Yihong/NCT
☆ Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders
Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands or objects appearing in groups of four -- that are reasonably expected to appear in the training data. These failure modes have largely been documented anecdotally, leaving open the question of whether they reflect idiosyncratic anomalies or more structural limitations of these models. To address this, we introduce a systematic approach for identifying and characterizing "conceptual blindspots" -- concepts present in the training data but absent or misrepresented in a model's generations. Our method leverages sparse autoencoders (SAEs) to extract interpretable concept embeddings, enabling a quantitative comparison of concept prevalence between real and generated images. We train an archetypal SAE (RA-SAE) on DINOv2 features with 32,000 concepts -- the largest such SAE to date -- enabling fine-grained analysis of conceptual disparities. Applied to four popular generative models (Stable Diffusion 1.5/2.1, PixArt, and Kandinsky), our approach reveals specific suppressed blindspots (e.g., bird feeders, DVD discs, and whitespaces on documents) and exaggerated blindspots (e.g., wood background texture and palm trees). At the individual datapoint level, we further isolate memorization artifacts -- instances where models reproduce highly specific visual templates seen during training. Overall, we propose a theoretically grounded framework for systematically identifying conceptual blindspots in generative models by assessing their conceptual fidelity with respect to the underlying data-generating process.
☆ UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation
Precise anomaly detection in medical images is critical for clinical decision-making. While recent unsupervised or semi-supervised anomaly detection methods trained on large-scale normal data show promising results, they lack fine-grained differentiation, such as benign vs. malignant tumors. Additionally, ultrasound (US) imaging is highly sensitive to devices and acquisition parameter variations, creating significant domain gaps in the resulting US images. To address these challenges, we propose UltraAD, a vision-language model (VLM)-based approach that leverages few-shot US examples for generalized anomaly localization and fine-grained classification. To enhance localization performance, the image-level token of query visual prototypes is first fused with learnable text embeddings. This image-informed prompt feature is then further integrated with patch-level tokens, refining local representations for improved accuracy. For fine-grained classification, a memory bank is constructed from few-shot image samples and corresponding text descriptions that capture anatomical and abnormality-specific features. During training, the stored text embeddings remain frozen, while image features are adapted to better align with medical data. UltraAD has been extensively evaluated on three breast US datasets, outperforming state-of-the-art methods in both lesion localization and fine-grained medical classification. The code will be released upon acceptance.
☆ ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
Prostate gland segmentation from T2-weighted MRI is a critical yet challenging task in clinical prostate cancer assessment. While deep learning-based methods have significantly advanced automated segmentation, most conventional approaches-particularly 2D convolutional neural networks (CNNs)-fail to leverage inter-slice anatomical continuity, limiting their accuracy and robustness. Fully 3D models offer improved spatial coherence but require large amounts of annotated data, which is often impractical in clinical settings. To address these limitations, we propose a hybrid architecture that models MRI sequences as spatiotemporal data. Our method uses a deep, pretrained DeepLabV3 backbone to extract high-level semantic features from each MRI slice and a recurrent convolutional head, built with ConvLSTM layers, to integrate information across slices while preserving spatial structure. This combination enables context-aware segmentation with improved consistency, particularly in data-limited and noisy imaging conditions. We evaluate our method on the PROMISE12 benchmark under both clean and contrast-degraded test settings. Compared to state-of-the-art 2D and 3D segmentation models, our approach demonstrates superior performance in terms of precision, recall, Intersection over Union (IoU), and Dice Similarity Coefficient (DSC), highlighting its potential for robust clinical deployment.
☆ Semantic Scene Graph for Ultrasound Image Explanation and Scanning Guidance
Understanding medical ultrasound imaging remains a long-standing challenge due to significant visual variability caused by differences in imaging and acquisition parameters. Recent advancements in large language models (LLMs) have been used to automatically generate terminology-rich summaries orientated to clinicians with sufficient physiological knowledge. Nevertheless, the increasing demand for improved ultrasound interpretability and basic scanning guidance among non-expert users, e.g., in point-of-care settings, has not yet been explored. In this study, we first introduce the scene graph (SG) for ultrasound images to explain image content to ordinary and provide guidance for ultrasound scanning. The ultrasound SG is first computed using a transformer-based one-stage method, eliminating the need for explicit object detection. To generate a graspable image explanation for ordinary, the user query is then used to further refine the abstract SG representation through LLMs. Additionally, the predicted SG is explored for its potential in guiding ultrasound scanning toward missing anatomies within the current imaging view, assisting ordinary users in achieving more standardized and complete anatomical exploration. The effectiveness of this SG-based image explanation and scanning guidance has been validated on images from the left and right neck regions, including the carotid and thyroid, across five volunteers. The results demonstrate the potential of the method to maximally democratize ultrasound by enhancing its interpretability and usability for ordinaries.
☆ Genome-Anchored Foundation Model Embeddings Improve Molecular Prediction from Histology Images
Precision oncology requires accurate molecular insights, yet obtaining these directly from genomics is costly and time-consuming for broad clinical use. Predicting complex molecular features and patient prognosis directly from routine whole-slide images (WSI) remains a major challenge for current deep learning methods. Here we introduce PathLUPI, which uses transcriptomic privileged information during training to extract genome-anchored histological embeddings, enabling effective molecular prediction using only WSIs at inference. Through extensive evaluation across 49 molecular oncology tasks using 11,257 cases among 20 cohorts, PathLUPI demonstrated superior performance compared to conventional methods trained solely on WSIs. Crucially, it achieves AUC $\geq$ 0.80 in 14 of the biomarker prediction and molecular subtyping tasks and C-index $\geq$ 0.70 in survival cohorts of 5 major cancer types. Moreover, PathLUPI embeddings reveal distinct cellular morphological signatures associated with specific genotypes and related biological pathways within WSIs. By effectively encoding molecular context to refine WSI representations, PathLUPI overcomes a key limitation of existing models and offers a novel strategy to bridge molecular insights with routine pathology workflows for wider clinical application.
comment: Under Review
☆ Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation
Generating reports for computed tomography (CT) images is a challenging task, while similar to existing studies for medical image report generation, yet has its unique characteristics, such as spatial encoding of multiple images, alignment between image volume and texts, etc. Existing solutions typically use general 2D or 3D image processing techniques to extract features from a CT volume, where they firstly compress the volume and then divide the compressed CT slices into patches for visual encoding. These approaches do not explicitly account for the transformations among CT slices, nor do they effectively integrate multi-level image features, particularly those containing specific organ lesions, to instruct CT report generation (CTRG). In considering the strong correlation among consecutive slices in CT scans, in this paper, we propose a large language model (LLM) based CTRG method with recurrent visual feature extraction and stereo attentions for hierarchical feature modeling. Specifically, we use a vision Transformer to recurrently process each slice in a CT volume, and employ a set of attentions over the encoded slices from different perspectives to selectively obtain important visual information and align them with textual features, so as to better instruct an LLM for CTRG. Experiment results and further analysis on the benchmark M3D-Cap dataset show that our method outperforms strong baseline models and achieves state-of-the-art results, demonstrating its validity and effectiveness.
comment: 7 pages, 3 figures
☆ SAM2-SGP: Enhancing SAM2 for Medical Image Segmentation via Support-Set Guided Prompting
Although new vision foundation models such as Segment Anything Model 2 (SAM2) have significantly enhanced zero-shot image segmentation capabilities, reliance on human-provided prompts poses significant challenges in adapting SAM2 to medical image segmentation tasks. Moreover, SAM2's performance in medical image segmentation was limited by the domain shift issue, since it was originally trained on natural images and videos. To address these challenges, we proposed SAM2 with support-set guided prompting (SAM2-SGP), a framework that eliminated the need for manual prompts. The proposed model leveraged the memory mechanism of SAM2 to generate pseudo-masks using image-mask pairs from a support set via a Pseudo-mask Generation (PMG) module. We further introduced a novel Pseudo-mask Attention (PMA) module, which used these pseudo-masks to automatically generate bounding boxes and enhance localized feature extraction by guiding attention to relevant areas. Furthermore, a low-rank adaptation (LoRA) strategy was adopted to mitigate the domain shift issue. The proposed framework was evaluated on both 2D and 3D datasets across multiple medical imaging modalities, including fundus photography, X-ray, computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), and ultrasound. The results demonstrated a significant performance improvement over state-of-the-art models, such as nnUNet and SwinUNet, as well as foundation models, such as SAM2 and MedSAM2, underscoring the effectiveness of the proposed approach. Our code is publicly available at https://github.com/astlian9/SAM_Support.
☆ Video Compression for Spatiotemporal Earth System Data
Large-scale Earth system datasets, from high-resolution remote sensing imagery to spatiotemporal climate model outputs, exhibit characteristics analogous to those of standard videos. Their inherent spatial, temporal, and spectral redundancies can thus be readily exploited by established video compression techniques. Here, we present xarrayvideo, a Python library for compressing multichannel spatiotemporal datasets by encoding them as videos. Our approach achieves compression ratios of up to 250x while maintaining high fidelity by leveraging standard, well-optimized video codecs through ffmpeg. We demonstrate the library's effectiveness on four real-world multichannel spatiotemporal datasets: DynamicEarthNet (very high resolution Planet images), DeepExtremeCubes (high resolution Sentinel-2 images), ERA5 (weather reanalysis data), and the SimpleS2 dataset (high resolution multichannel Sentinel-2 images), achieving Peak Signal-to-Noise Ratios (PSNRs) of 55.86, 40.60, 46.58, and 43.23 dB at 0.1 bits per pixel per band (bpppb) and 65.91, 54.28, 62.90, and 55.04 dB at 1 bpppb. We are redistributing two of these datasets, DeepExtremeCubes (2.3 Tb) and DynamicEarthNet (525 Gb), in the machine-learning-ready and cloud-ready TACO format through HuggingFace at significantly reduced sizes (270 Gb and 8.5 Gb, respectively) without compromising quality (PSNR 55.77-56.65 and 60.15). No performance loss is observed when the compressed versions of these datasets are used in their respective deep learning-based downstream tasks (next step reflectance prediction and landcover segmentation). In conclusion, xarrayvideo presents an efficient solution for handling the rapidly growing size of Earth observation datasets, making advanced compression techniques accessible and practical to the Earth science community. The library is available for use at https://github.com/IPL-UV/xarrayvideo
☆ PEVLM: Parallel Encoding for Vision-Language Models
Vision-Language Models (VLMs) have demonstrated strong performance in video-language tasks, yet their application to long video understanding remains constrained by the quadratic complexity of standard attention mechanisms. In this paper, we propose \textbf{PEVLM}, a parallel encoding strategy specifically designed to improve the prefill efficiency of VLMs without requiring model finetuning. PEVLM partitions the input into block-wise segments with a shared sink, preserves full-attention positional embeddings, and aligns attention weights to mimic full-attention distributions. This design reduces attention computation from $O((T \times N)^2)$ to $O(T \times N)$ while maintaining high accuracy. Extensive experiments on the LongVideoBench benchmark show that PEVLM achieves up to 8.37\% accuracy improvement over existing inference-efficient methods and delivers up to 7.47x speedup in attention computation and 40\% reduction in end-to-end latency. Under strict latency constraints, PEVLM significantly outperforms baselines, raising accuracy from 23.26\% to 61.03\%. These results highlight PEVLM's effectiveness for low-latency, long-context video understanding, making it well-suited for real-world applications such as autonomous driving.
☆ HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions
When humans and robotic agents coexist in an environment, scene understanding becomes crucial for the agents to carry out various downstream tasks like navigation and planning. Hence, an agent must be capable of localizing and identifying actions performed by the human. Current research lacks reliable datasets for performing scene understanding within indoor environments where humans are also a part of the scene. Scene Graphs enable us to generate a structured representation of a scene or an image to perform visual scene understanding. To tackle this, we present HOIverse a synthetic dataset at the intersection of scene graph and human-object interaction, consisting of accurate and dense relationship ground truths between humans and surrounding objects along with corresponding RGB images, segmentation masks, depth images and human keypoints. We compute parametric relations between various pairs of objects and human-object pairs, resulting in an accurate and unambiguous relation definitions. In addition, we benchmark our dataset on state-of-the-art scene graph generation models to predict parametric relations and human-object interactions. Through this dataset, we aim to accelerate research in the field of scene understanding involving people.
☆ VideoPCDNet: Video Parsing and Prediction with Phase Correlation Networks ICANN 2025
Understanding and predicting video content is essential for planning and reasoning in dynamic environments. Despite advancements, unsupervised learning of object representations and dynamics remains challenging. We present VideoPCDNet, an unsupervised framework for object-centric video decomposition and prediction. Our model uses frequency-domain phase correlation techniques to recursively parse videos into object components, which are represented as transformed versions of learned object prototypes, enabling accurate and interpretable tracking. By explicitly modeling object motion through a combination of frequency domain operations and lightweight learned modules, VideoPCDNet enables accurate unsupervised object tracking and prediction of future video frames. In our experiments, we demonstrate that VideoPCDNet outperforms multiple object-centric baseline models for unsupervised tracking and prediction on several synthetic datasets, while learning interpretable object and motion representations.
comment: Accepted for Publication at ICANN 2025
☆ Filling of incomplete sinograms from sparse PET detector configurations using a residual U-Net
Long axial field-of-view PET scanners offer increased field-of-view and sensitivity compared to traditional PET scanners. However, a significant cost is associated with the densely packed photodetectors required for the extended-coverage systems, limiting clinical utilisation. To mitigate the cost limitations, alternative sparse system configurations have been proposed, allowing an extended field-of-view PET design with detector costs similar to a standard PET system, albeit at the expense of image quality. In this work, we propose a deep sinogram restoration network to fill in the missing sinogram data. Our method utilises a modified Residual U-Net, trained on clinical PET scans from a GE Signa PET/MR, simulating the removal of 50% of the detectors in a chessboard pattern (retaining only 25% of all lines of response). The model successfully recovers missing counts, with a mean absolute error below two events per pixel, outperforming 2D interpolation in both sinogram and reconstructed image domain. Notably, the predicted sinograms exhibit a smoothing effect, leading to reconstructed images lacking sharpness in finer details. Despite these limitations, the model demonstrates a substantial capacity for compensating for the undersampling caused by the sparse detector configuration. This proof-of-concept study suggests that sparse detector configurations, combined with deep learning techniques, offer a viable alternative to conventional PET scanner designs. This approach supports the development of cost-effective, total body PET scanners, allowing a significant step forward in medical imaging technology.
comment: 15 pages, 9 figures
☆ Implementing blind navigation through multi-modal sensing and gait guidance
By the year 2023, the global population of individuals with impaired vision has surpassed 220 million. People with impaired vision will find it difficult while finding path or avoiding obstacles, and must ask for auxiliary tools for help. Although traditional aids such as guide canes and guide dogs exist, they still have some shortcomings. In this paper, we present our wearable blind guiding device, what perform navigation guidance through our proposed Gait-based Guiding System. Our device innovatively integrates gait phase analysis for walking guide, and in terms of environmental perception, we use multimodal sensing to acquire diverse environment information. During the experiment, we conducted both indoor and outdoor experiments, and compared with the standard guide cane. The result shows superior performance of our device in blind guidance.
☆ Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications
Cloud cover in multispectral imagery (MSI) poses significant challenges for early season crop mapping, as it leads to missing or corrupted spectral information. Synthetic aperture radar (SAR) data, which is not affected by cloud interference, offers a complementary solution, but lack sufficient spectral detail for precise crop mapping. To address this, we propose a novel framework, Time-series MSI Image Reconstruction using Vision Transformer (ViT), to reconstruct MSI data in cloud-covered regions by leveraging the temporal coherence of MSI and the complementary information from SAR from the attention mechanism. Comprehensive experiments, using rigorous reconstruction evaluation metrics, demonstrate that Time-series ViT framework significantly outperforms baselines that use non-time-series MSI and SAR or time-series MSI without SAR, effectively enhancing MSI image reconstruction in cloud-covered regions.
comment: This paper has been accepted as a conference paper at the 2025 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
☆ Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
The segmentation of metastatic bone disease (MBD) in whole-body MRI (WB-MRI) is a challenging problem. Due to varying appearances and anatomical locations of lesions, ambiguous boundaries, and severe class imbalance, obtaining reliable segmentations requires large, well-annotated datasets capturing lesion variability. Generating such datasets requires substantial time and expertise, and is prone to error. While self-supervised learning (SSL) can leverage large unlabeled datasets, learned generic representations often fail to capture the nuanced features needed for accurate lesion detection. In this work, we propose a Supervised Anatomical Pretraining (SAP) method that learns from a limited dataset of anatomical labels. First, an MRI-based skeletal segmentation model is developed and trained on WB-MRI scans from healthy individuals for high-quality skeletal delineation. Then, we compare its downstream efficacy in segmenting MBD on a cohort of 44 patients with metastatic prostate cancer, against both a baseline random initialization and a state-of-the-art SSL method. SAP significantly outperforms both the baseline and SSL-pretrained models, achieving a normalized surface Dice of 0.76 and a Dice coefficient of 0.64. The method achieved a lesion detection F2 score of 0.44, improving on 0.24 (baseline) and 0.31 (SSL). When considering only clinically relevant lesions larger than 1~ml, SAP achieves a detection sensitivity of 100% in 28 out of 32 patients. Learning bone morphology from anatomy yields an effective and domain-relevant inductive bias that can be leveraged for the downstream segmentation task of bone lesions. All code and models are made publicly available.
comment: This preprint is currently under review at *Computers in Biology and Medicine* (Elsevier). This version has not been peer-reviewed
☆ SMARTIES: Spectrum-Aware Multi-Sensor Auto-Encoder for Remote Sensing Images
From optical sensors to microwave radars, leveraging the complementary strengths of remote sensing (RS) sensors is crucial for achieving dense spatio-temporal monitoring of our planet. In contrast, recent deep learning models, whether task-specific or foundational, are often specific to single sensors or to fixed combinations: adapting such models to different sensory inputs requires both architectural changes and re-training, limiting scalability and generalization across multiple RS sensors. On the contrary, a single model able to modulate its feature representations to accept diverse sensors as input would pave the way to agile and flexible multi-sensor RS data processing. To address this, we introduce SMARTIES, a generic and versatile foundation model lifting sensor-specific/dependent efforts and enabling scalability and generalization to diverse RS sensors: SMARTIES projects data from heterogeneous sensors into a shared spectrum-aware space, enabling the use of arbitrary combinations of bands both for training and inference. To obtain sensor-agnostic representations, we train a single, unified transformer model reconstructing masked multi-sensor data with cross-sensor token mixup. On both single- and multi-modal tasks across diverse sensors, SMARTIES outperforms previous models that rely on sensor-specific pretraining. Our code and pretrained models are available at https://gsumbul.github.io/SMARTIES.
☆ Fake or Real, Can Robots Tell? Evaluating Embodied Vision-Language Models on Real and 3D-Printed Objects
Robotic scene understanding increasingly relies on vision-language models (VLMs) to generate natural language descriptions of the environment. In this work, we present a comparative study of captioning strategies for tabletop scenes captured by a robotic arm equipped with an RGB camera. The robot collects images of objects from multiple viewpoints, and we evaluate several models that generate scene descriptions. We compare the performance of various captioning models, like BLIP and VLMs. Our experiments examine the trade-offs between single-view and multi-view captioning, and difference between recognising real-world and 3D printed objects. We quantitatively evaluate object identification accuracy, completeness, and naturalness of the generated captions. Results show that VLMs can be used in robotic settings where common objects need to be recognised, but fail to generalise to novel representations. Our findings provide practical insights into deploying foundation models for embodied agents in real-world settings.
☆ MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification
Recent advances in deep learning for vision tasks have seen the rise of State Space Models (SSMs) like Mamba, celebrated for their linear scalability. However, their adaptation to 2D visual data often necessitates complex modifications that may diminish efficiency. In this paper, we introduce MambaOutRS, a novel hybrid convolutional architecture for remote sensing image classification that re-evaluates the necessity of recurrent SSMs. MambaOutRS builds upon stacked Gated CNN blocks for local feature extraction and introduces a novel Fourier Filter Gate (FFG) module that operates in the frequency domain to capture global contextual information efficiently. Our architecture employs a four-stage hierarchical design and was extensively evaluated on challenging remote sensing datasets: UC Merced, AID, NWPU-RESISC45, and EuroSAT. MambaOutRS consistently achieved state-of-the-art (SOTA) performance across these benchmarks. Notably, our MambaOutRS-t variant (24.0M parameters) attained the highest F1-scores of 98.41\% on UC Merced and 95.99\% on AID, significantly outperforming existing baselines, including larger transformer models and Mamba-based architectures, despite using considerably fewer parameters. An ablation study conclusively demonstrates the critical role of the Fourier Filter Gate in enhancing the model's ability to capture global spatial patterns, leading to robust and accurate classification. These results strongly suggest that the complexities of recurrent SSMs can be effectively superseded by a judicious combination of gated convolutions for spatial mixing and frequency-based gates for spectral global context. Thus, MambaOutRS provides a compelling and efficient paradigm for developing high-performance deep learning models in remote sensing and other vision domains, particularly where computational efficiency is paramount.
☆ ConCM: Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning (FSCIL) requires models to adapt to novel classes with limited supervision while preserving learned knowledge. Existing prospective learning-based space construction methods reserve space to accommodate novel classes. However, prototype deviation and structure fixity limit the expressiveness of the embedding space. In contrast to fixed space reservation, we explore the optimization of feature-structure dual consistency and propose a Consistency-driven Calibration and Matching Framework (ConCM) that systematically mitigate the knowledge conflict inherent in FSCIL. Specifically, inspired by hippocampal associative memory, we design a memory-aware prototype calibration that extracts generalized semantic attributes from base classes and reintegrates them into novel classes to enhance the conceptual center consistency of features. Further, we propose dynamic structure matching, which adaptively aligns the calibrated features to a session-specific optimal manifold space, ensuring cross-session structure consistency. Theoretical analysis shows that our method satisfies both geometric optimality and maximum matching, thereby overcoming the need for class-number priors. On large-scale FSCIL benchmarks including mini-ImageNet and CUB200, ConCM achieves state-of-the-art performance, surpassing current optimal method by 3.20% and 3.68% in harmonic accuracy of incremental sessions.
comment: 9 pages, 5 figures(Excluding the appendix)
☆ General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound MICCAI 2025
With access to large-scale, unlabeled medical datasets, researchers are confronted with two questions: Should they attempt to pretrain a custom foundation model on this medical data, or use transfer-learning from an existing generalist model? And, if a custom model is pretrained, are novel methods required? In this paper we explore these questions by conducting a case-study, in which we train a foundation model on a large regional fetal ultrasound dataset of 2M images. By selecting the well-established DINOv2 method for pretraining, we achieve state-of-the-art results on three fetal ultrasound datasets, covering data from different countries, classification, segmentation, and few-shot tasks. We compare against a series of models pretrained on natural images, ultrasound images, and supervised baselines. Our results demonstrate two key insights: (i) Pretraining on custom data is worth it, even if smaller models are trained on less data, as scaling in natural image pretraining does not translate to ultrasound performance. (ii) Well-tuned methods from computer vision are making it feasible to train custom foundation models for a given medical domain, requiring no hyperparameter tuning and little methodological adaptation. Given these findings, we argue that a bias towards methodological innovation should be avoided when developing domain specific foundation models under common computational resource constraints.
comment: Submitted version of paper accepted at MICCAI 2025
☆ Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks ICIP 2021
Backdoor attacks embed a hidden functionality into deep neural networks, causing the network to display anomalous behavior when activated by a predetermined pattern in the input Trigger, while behaving well otherwise on public test data. Recent works have shown that backdoored face recognition (FR) systems can respond to natural-looking triggers like a particular pair of sunglasses. Such attacks pose a serious threat to the applicability of FR systems in high-security applications. We propose a novel technique to (1) detect whether an FR network is compromised with a natural, physically realizable trigger, and (2) identify such triggers given a compromised network. We demonstrate the effectiveness of our methods with a compromised FR network, where we are able to identify the trigger (e.g., green sunglasses or red hat) with a top-5 accuracy of 74%, whereas a naive brute force baseline achieves 56% accuracy.
comment: Accepted to ICIP 2021
☆ ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation
Artifacts in kilo-Voltage CT (kVCT) imaging degrade image quality, impacting clinical decisions. We propose a deep learning framework for metal artifact reduction (MAR) and domain transformation from kVCT to Mega-Voltage CT (MVCT). The proposed framework, ReMAR-DS, utilizes an encoder-decoder architecture with enhanced feature recalibration, effectively reducing artifacts while preserving anatomical structures. This ensures that only relevant information is utilized in the reconstruction process. By infusing recalibrated features from the encoder block, the model focuses on relevant spatial regions (e.g., areas with artifacts) and highlights key features across channels (e.g., anatomical structures), leading to improved reconstruction of artifact-corrupted regions. Unlike traditional MAR methods, our approach bridges the gap between high-resolution kVCT and artifact-resistant MVCT, enhancing radiotherapy planning. It produces high-quality MVCT-like reconstructions, validated through qualitative and quantitative evaluations. Clinically, this enables oncologists to rely on kVCT alone, reducing repeated high-dose MVCT scans and lowering radiation exposure for cancer patients.
comment: Accepted in 23rd International Conference on Image Analysis and Processing (ICIAP) 2025, Italy
☆ Visual hallucination detection in large vision-language models via evidential conflict
Despite the remarkable multimodal capabilities of Large Vision-Language Models (LVLMs), discrepancies often occur between visual inputs and textual outputs--a phenomenon we term visual hallucination. This critical reliability gap poses substantial risks in safety-critical Artificial Intelligence (AI) applications, necessitating a comprehensive evaluation benchmark and effective detection methods. Firstly, we observe that existing visual-centric hallucination benchmarks mainly assess LVLMs from a perception perspective, overlooking hallucinations arising from advanced reasoning capabilities. We develop the Perception-Reasoning Evaluation Hallucination (PRE-HAL) dataset, which enables the systematic evaluation of both perception and reasoning capabilities of LVLMs across multiple visual semantics, such as instances, scenes, and relations. Comprehensive evaluation with this new benchmark exposed more visual vulnerabilities, particularly in the more challenging task of relation reasoning. To address this issue, we propose, to the best of our knowledge, the first Dempster-Shafer theory (DST)-based visual hallucination detection method for LVLMs through uncertainty estimation. This method aims to efficiently capture the degree of conflict in high-level features at the model inference phase. Specifically, our approach employs simple mass functions to mitigate the computational complexity of evidence combination on power sets. We conduct an extensive evaluation of state-of-the-art LVLMs, LLaVA-v1.5, mPLUG-Owl2 and mPLUG-Owl3, with the new PRE-HAL benchmark. Experimental results indicate that our method outperforms five baseline uncertainty metrics, achieving average AUROC improvements of 4%, 10%, and 7% across three LVLMs. Our code is available at https://github.com/HT86159/Evidential-Conflict.
☆ Experimental Assessment of Neural 3D Reconstruction for Small UAV-based Applications
The increasing miniaturization of Unmanned Aerial Vehicles (UAVs) has expanded their deployment potential to indoor and hard-to-reach areas. However, this trend introduces distinct challenges, particularly in terms of flight dynamics and power consumption, which limit the UAVs' autonomy and mission capabilities. This paper presents a novel approach to overcoming these limitations by integrating Neural 3D Reconstruction (N3DR) with small UAV systems for fine-grained 3-Dimensional (3D) digital reconstruction of small static objects. Specifically, we design, implement, and evaluate an N3DR-based pipeline that leverages advanced models, i.e., Instant-ngp, Nerfacto, and Splatfacto, to improve the quality of 3D reconstructions using images of the object captured by a fleet of small UAVs. We assess the performance of the considered models using various imagery and pointcloud metrics, comparing them against the baseline Structure from Motion (SfM) algorithm. The experimental results demonstrate that the N3DR-enhanced pipeline significantly improves reconstruction quality, making it feasible for small UAVs to support high-precision 3D mapping and anomaly detection in constrained environments. In more general terms, our results highlight the potential of N3DR in advancing the capabilities of miniaturized UAV systems.
comment: 6 pages, 7 figures, 2 tables, accepted at IEEE International Symposium on Personal, Indoor and Mobile Radio Communications 2025
☆ SceneCrafter: Controllable Multi-View Driving Scene Editing CVPR 2025
Simulation is crucial for developing and evaluating autonomous vehicle (AV) systems. Recent literature builds on a new generation of generative models to synthesize highly realistic images for full-stack simulation. However, purely synthetically generated scenes are not grounded in reality and have difficulty in inspiring confidence in the relevance of its outcomes. Editing models, on the other hand, leverage source scenes from real driving logs, and enable the simulation of different traffic layouts, behaviors, and operating conditions such as weather and time of day. While image editing is an established topic in computer vision, it presents fresh sets of challenges in driving simulation: (1) the need for cross-camera 3D consistency, (2) learning ``empty street" priors from driving data with foreground occlusions, and (3) obtaining paired image tuples of varied editing conditions while preserving consistent layout and geometry. To address these challenges, we propose SceneCrafter, a versatile editor for realistic 3D-consistent manipulation of driving scenes captured from multiple cameras. We build on recent advancements in multi-view diffusion models, using a fully controllable framework that scales seamlessly to multi-modality conditions like weather, time of day, agent boxes and high-definition maps. To generate paired data for supervising the editing model, we propose a novel framework on top of Prompt-to-Prompt to generate geometrically consistent synthetic paired data with global edits. We also introduce an alpha-blending framework to synthesize data with local edits, leveraging a model trained on empty street priors through novel masked training and multi-view repaint paradigm. SceneCrafter demonstrates powerful editing capabilities and achieves state-of-the-art realism, controllability, 3D consistency, and scene editing quality compared to existing baselines.
comment: CVPR 2025
☆ HMSViT: A Hierarchical Masked Self-Supervised Vision Transformer for Corneal Nerve Segmentation and Diabetic Neuropathy Diagnosis
Diabetic Peripheral Neuropathy (DPN) affects nearly half of diabetes patients, requiring early detection. Corneal Confocal Microscopy (CCM) enables non-invasive diagnosis, but automated methods suffer from inefficient feature extraction, reliance on handcrafted priors, and data limitations. We propose HMSViT, a novel Hierarchical Masked Self-Supervised Vision Transformer (HMSViT) designed for corneal nerve segmentation and DPN diagnosis. Unlike existing methods, HMSViT employs pooling-based hierarchical and dual attention mechanisms with absolute positional encoding, enabling efficient multi-scale feature extraction by capturing fine-grained local details in early layers and integrating global context in deeper layers, all at a lower computational cost. A block-masked self supervised learning framework is designed for the HMSViT that reduces reliance on labelled data, enhancing feature robustness, while a multi-scale decoder is used for segmentation and classification by fusing hierarchical features. Experiments on clinical CCM datasets showed HMSViT achieves state-of-the-art performance, with 61.34% mIoU for nerve segmentation and 70.40% diagnostic accuracy, outperforming leading hierarchical models like the Swin Transformer and HiViT by margins of up to 6.39% in segmentation accuracy while using fewer parameters. Detailed ablation studies further reveal that integrating block-masked SSL with hierarchical multi-scale feature extraction substantially enhances performance compared to conventional supervised training. Overall, these comprehensive experiments confirm that HMSViT delivers excellent, robust, and clinically viable results, demonstrating its potential for scalable deployment in real-world diagnostic applications.
☆ USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation
Inspired by the biological visual system that selectively allocates attention to efficiently identify salient objects or regions, underwater salient instance segmentation (USIS) aims to jointly address the problems of where to look (saliency prediction) and what is there (instance segmentation) in underwater scenarios. However, USIS remains an underexplored challenge due to the inaccessibility and dynamic nature of underwater environments, as well as the scarcity of large-scale, high-quality annotated datasets. In this paper, we introduce USIS16K, a large-scale dataset comprising 16,151 high-resolution underwater images collected from diverse environmental settings and covering 158 categories of underwater objects. Each image is annotated with high-quality instance-level salient object masks, representing a significant advance in terms of diversity, complexity, and scalability. Furthermore, we provide benchmark evaluations on underwater object detection and USIS tasks using USIS16K. To facilitate future research in this domain, the dataset and benchmark models are publicly available.
comment: 8 pages 10 figures
☆ Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning
In recent years, significant progress has been made in the field of surgical scene understanding, particularly in the task of Visual Question Localized-Answering in robotic surgery (Surgical-VQLA). However, existing Surgical-VQLA models lack deep reasoning capabilities and interpretability in surgical scenes, which limits their reliability and potential for development in clinical applications. To address this issue, inspired by the development of Reasoning Multimodal Large Language Models (MLLMs), we first build the Surgery-R1-54k dataset, including paired data for Visual-QA, Grounding-QA, and Chain-of-Thought (CoT). Then, we propose the first Reasoning MLLM for Surgical-VQLA (Surgery-R1). In our Surgery-R1, we design a two-stage fine-tuning mechanism to enable the basic MLLM with complex reasoning abilities by utilizing supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Furthermore, for an efficient and high-quality rule-based reward system in our RFT, we design a Multimodal Coherence reward mechanism to mitigate positional illusions that may arise in surgical scenarios. Experiment results demonstrate that Surgery-R1 outperforms other existing state-of-the-art (SOTA) models in the Surgical-VQLA task and widely-used MLLMs, while also validating its reasoning capabilities and the effectiveness of our approach. The code and dataset will be organized in https://github.com/FiFi-HAO467/Surgery-R1.
☆ Stylized Structural Patterns for Improved Neural Network Pre-training
Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative, yet models trained with it often underperform. This paper proposes a two-step approach to bridge this gap. First, we propose an improved neural fractal formulation through which we introduce a new class of synthetic data. Second, we propose reverse stylization, a technique that transfers visual features from a small, license-free set of real images onto synthetic datasets, enhancing their effectiveness. We analyze the domain gap between our synthetic datasets and real images using Kernel Inception Distance (KID) and show that our method achieves a significantly lower distributional gap compared to existing synthetic datasets. Furthermore, our experiments across different tasks demonstrate the practical impact of this reduced gap. We show that pretraining the EDM2 diffusion model on our synthetic dataset leads to an 11% reduction in FID during image generation, compared to models trained on existing synthetic datasets, and a 20% decrease in autoencoder reconstruction error, indicating improved performance in data representation. Furthermore, a ViT-S model trained for classification on this synthetic data achieves over a 10% improvement in ImageNet-100 accuracy. Our work opens up exciting possibilities for training practical models when sufficiently large real training sets are not available.
☆ Assessing Risk of Stealing Proprietary Models for Medical Imaging Tasks MICCAI 2024
The success of deep learning in medical imaging applications has led several companies to deploy proprietary models in diagnostic workflows, offering monetized services. Even though model weights are hidden to protect the intellectual property of the service provider, these models are exposed to model stealing (MS) attacks, where adversaries can clone the model's functionality by querying it with a proxy dataset and training a thief model on the acquired predictions. While extensively studied on general vision tasks, the susceptibility of medical imaging models to MS attacks remains inadequately explored. This paper investigates the vulnerability of black-box medical imaging models to MS attacks under realistic conditions where the adversary lacks access to the victim model's training data and operates with limited query budgets. We demonstrate that adversaries can effectively execute MS attacks by using publicly available datasets. To further enhance MS capabilities with limited query budgets, we propose a two-step model stealing approach termed QueryWise. This method capitalizes on unlabeled data obtained from a proxy distribution to train the thief model without incurring additional queries. Evaluation on two medical imaging models for Gallbladder Cancer and COVID-19 classification substantiates the effectiveness of the proposed attack. The source code is available at https://github.com/rajankita/QueryWise.
comment: Accepted to MICCAI 2024
☆ Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography datasets. While making high-quality vascular angiography synthesis crucial, it remains challenging. We find that current medical image synthesis primarily operates at pixel level and struggles to adapt to the complex geometric structure of blood vessels, resulting in unsatisfactory quality of blood vessel image synthesis, such as disconnections or unnatural curvatures. To overcome this issue, we propose a self-supervised method via diffusion models to transform non-angiographic X-rays into angiographic X-rays, mitigating data shortages for data-driven approaches. Our model comprises a diffusion model that learns the distribution of vascular data from diffusion latent, a generator for vessel synthesis, and a mask-based adversarial module. To enhance geometric accuracy, we propose a parametric vascular model to fit the shape and distribution of blood vessels. The proposed method contributes a pipeline and a synthetic dataset for X-ray angiography. We conducted extensive comparative and ablation experiments to evaluate the Angio-Diff. The results demonstrate that our method achieves state-of-the-art performance in synthetic angiography image quality and more accurately synthesizes the geometric structure of blood vessels. The code is available at https://github.com/zfw-cv/AngioDiff.
☆ Deblurring in the Wild: A Real-World Dataset from Smartphone High-Speed Videos
We introduce the largest real-world image deblurring dataset constructed from smartphone slow-motion videos. Using 240 frames captured over one second, we simulate realistic long-exposure blur by averaging frames to produce blurry images, while using the temporally centered frame as the sharp reference. Our dataset contains over 42,000 high-resolution blur-sharp image pairs, making it approximately 10 times larger than widely used datasets, with 8 times the amount of different scenes, including indoor and outdoor environments, with varying object and camera motions. We benchmark multiple state-of-the-art (SOTA) deblurring models on our dataset and observe significant performance degradation, highlighting the complexity and diversity of our benchmark. Our dataset serves as a challenging new benchmark to facilitate robust and generalizable deblurring models.
comment: 8 pages (without references), 3 figures. Dataset https://huggingface.co/datasets/masterda/SloMoBlur
☆ AMF-MedIT: An Efficient Align-Modulation-Fusion Framework for Medical Image-Tabular Data
Multimodal medical analysis combining image and tabular data has gained increasing attention. However, effective fusion remains challenging due to cross-modal discrepancies in feature dimensions and modality contributions, as well as the noise from high-dimensional tabular inputs. To address these problems, we present AMF-MedIT, an efficient Align-Modulation-Fusion framework for medical image and tabular data integration, particularly under data-scarce conditions. To harmonize dimension discrepancies and dynamically adjust modality contributions, we propose the Adaptive Modulation and Fusion (AMF) module, a novel modulation-based fusion paradigm with a streamlined architecture. We first derive the modulation objectives and introduce a modality confidence ratio, enabling the incorporation of prior knowledge into the fusion process. Then, the feature masks, density and leakage losses are proposed to achieve the modulation objectives. Additionally, we introduce FT-Mamba, a powerful tabular encoder leveraging a selective mechanism to handle noisy medical tabular data efficiently. Furthermore, interpretability studies are conducted to explore how different tabular encoders supervise the imaging modality during contrastive pretraining for the first time. Extensive experiments demonstrate that AMF-MedIT achieves a superior balance between multimodal performance and data efficiency while showing strong adaptability to incomplete tabular data. Interpretability analysis also highlights FT-Mamba's capabilities in extracting distinct tabular features and guiding the image encoder toward more accurate and flexible attention patterns.
☆ Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
Vision-and-Language Navigation (VLN) in large-scale urban environments requires embodied agents to ground linguistic instructions in complex scenes and recall relevant experiences over extended time horizons. Prior modular pipelines offer interpretability but lack unified memory, while end-to-end (M)LLM agents excel at fusing vision and language yet remain constrained by fixed context windows and implicit spatial reasoning. We introduce \textbf{Mem4Nav}, a hierarchical spatial-cognition long-short memory system that can augment any VLN backbone. Mem4Nav fuses a sparse octree for fine-grained voxel indexing with a semantic topology graph for high-level landmark connectivity, storing both in trainable memory tokens embedded via a reversible Transformer. Long-term memory (LTM) compresses and retains historical observations at both octree and graph nodes, while short-term memory (STM) caches recent multimodal entries in relative coordinates for real-time obstacle avoidance and local planning. At each step, STM retrieval sharply prunes dynamic context, and, when deeper history is needed, LTM tokens are decoded losslessly to reconstruct past embeddings. Evaluated on Touchdown and Map2Seq across three backbones (modular, state-of-the-art VLN with prompt-based LLM, and state-of-the-art VLN with strided-attention MLLM), Mem4Nav yields 7-13 pp gains in Task Completion, sufficient SPD reduction, and >10 pp nDTW improvement. Ablations confirm the indispensability of both the hierarchical map and dual memory modules. Our codes are open-sourced via https://github.com/tsinghua-fib-lab/Mem4Nav.
☆ Virtual Memory for 3D Gaussian Splatting
3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically increased the size of scenes that can be created. In this work, we present a method for rendering large and complex 3D Gaussian Splatting scenes using virtual memory. By leveraging well-established virtual memory and virtual texturing techniques, our approach efficiently identifies visible Gaussians and dynamically streams them to the GPU just in time for real-time rendering. Selecting only the necessary Gaussians for both storage and rendering results in reduced memory usage and effectively accelerates rendering, especially for highly complex scenes. Furthermore, we demonstrate how level of detail can be integrated into our proposed method to further enhance rendering speed for large-scale scenes. With an optimized implementation, we highlight key practical considerations and thoroughly evaluate the proposed technique and its impact on desktop and mobile devices.
comment: Based on the Master Thesis from Jonathan Haberl from 2024, Submitted to TVCG in Feb. 2025;
☆ A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation
With the rapid development of ultra-high resolution (UHR) remote sensing technology, the demand for accurate and efficient semantic segmentation has increased significantly. However, existing methods face challenges in computational efficiency and multi-scale feature fusion. To address these issues, we propose GLCANet (Global-Local Cross-Attention Network), a lightweight segmentation framework designed for UHR remote sensing imagery.GLCANet employs a dual-stream architecture to efficiently fuse global semantics and local details while minimizing GPU usage. A self-attention mechanism enhances long-range dependencies, refines global features, and preserves local details for better semantic consistency. A masked cross-attention mechanism also adaptively fuses global-local features, selectively enhancing fine-grained details while exploiting global context to improve segmentation accuracy. Experimental results show that GLCANet outperforms state-of-the-art methods regarding accuracy and computational efficiency. The model effectively processes large, high-resolution images with a small memory footprint, providing a promising solution for real-world remote sensing applications.
☆ Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling
Downscaling is essential for generating the high-resolution climate data needed for local planning, but traditional methods remain computationally demanding. Recent years have seen impressive results from AI downscaling models, particularly diffusion models, which have attracted attention due to their ability to generate ensembles and overcome the smoothing problem common in other AI methods. However, these models typically remain computationally intensive. We introduce a Hierarchical Diffusion Downscaling (HDD) model, which introduces an easily-extensible hierarchical sampling process to the diffusion framework. A coarse-to-fine hierarchy is imposed via a simple downsampling scheme. HDD achieves competitive accuracy on ERA5 reanalysis datasets and CMIP6 models, significantly reducing computational load by running on up to half as many pixels with competitive results. Additionally, a single model trained at 0.25{\deg} resolution transfers seamlessly across multiple CMIP6 models with much coarser resolution. HDD thus offers a lightweight alternative for probabilistic climate downscaling, facilitating affordable large-ensemble high-resolution climate projections. See a full code implementation at: https://github.com/HDD-Hierarchical-Diffusion-Downscaling/HDD-Hierarchical-Diffusion-Downscaling.
comment: 8 pages
☆ Emergence of Text Readability in Vision Language Models CVPR 2025
We investigate how the ability to recognize textual content within images emerges during the training of Vision-Language Models (VLMs). Our analysis reveals a critical phenomenon: the ability to read textual information in a given image \textbf{(text readability)} emerges abruptly after substantial training iterations, in contrast to semantic content understanding which develops gradually from the early stages of training. This delayed emergence may reflect how contrastive learning tends to initially prioritize general semantic understanding, with text-specific symbolic processing developing later. Interestingly, the ability to match images with rendered text develops even slower, indicating a deeper need for semantic integration. These findings highlight the need for tailored training strategies to accelerate robust text comprehension in VLMs, laying the groundwork for future research on optimizing multimodal learning.
comment: EVAL-FoMo Workshop @ CVPR 2025
☆ Online camera-pose-free stereo endoscopic tissue deformation recovery with tissue-invariant vision-biomechanics consistency
Tissue deformation recovery based on stereo endoscopic images is crucial for tool-tissue interaction analysis and benefits surgical navigation and autonomous soft tissue manipulation. Previous research suffers from the problems raised from camera motion, occlusion, large tissue deformation, lack of tissue-specific biomechanical priors, and reliance on offline processing. Unlike previous studies where the tissue geometry and deformation are represented by 3D points and displacements, the proposed method models tissue geometry as the 3D point and derivative map and tissue deformation as the 3D displacement and local deformation map. For a single surface point, 6 parameters are used to describe its rigid motion and 3 parameters for its local deformation. The method is formulated under the camera-centric setting, where all motions are regarded as the scene motion with respect to the camera. Inter-frame alignment is realized by optimizing the inter-frame deformation, making it unnecessary to estimate camera pose. The concept of the canonical map is introduced to optimize tissue geometry and deformation in an online approach. Quantitative and qualitative experiments were conducted using in vivo and ex vivo laparoscopic datasets. With the inputs of depth and optical flow, the method stably models tissue geometry and deformation even when the tissue is partially occluded or moving outside the field of view. Results show that the 3D reconstruction accuracy in the non-occluded and occluded areas reaches 0.37$\pm$0.27 mm and 0.39$\pm$0.21 mm in terms of surface distance, respectively. The method can also estimate surface strain distribution during various manipulations as an extra modality for mechanical-based analysis.
☆ NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs
Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more effectively than high-frequency details. This leads to the loss of fine details, which is particularly problematic in dental radiographs where preserving subtle anatomical structures is crucial. While self-attention mechanisms can help mitigate this issue by emphasizing important features, conventional attention methods often prioritize features corresponding to cleaner regions and may overlook those obscured by noise. To address this limitation, we propose a noise-aware self-attention method, which allows the model to effectively focus on and recover key features even within noisy regions. Building on this approach, we introduce the noise-aware attention-enhanced denoising autoencoder (NAADA) network for enhancing noisy panoramic dental radiographs. Compared with the recent state of the art (and much heavier) methods like Uformer, MResDNN etc., our method improves the reconstruction of fine details, ensuring better image quality and diagnostic accuracy.
comment: 10 pages, 8 figures
☆ Reconsidering Explicit Longitudinal Mammography Alignment for Enhanced Breast Cancer Risk Prediction MICCAI 2025
Regular mammography screening is essential for early breast cancer detection. Deep learning-based risk prediction methods have sparked interest to adjust screening intervals for high-risk groups. While early methods focused only on current mammograms, recent approaches leverage the temporal aspect of screenings to track breast tissue changes over time, requiring spatial alignment across different time points. Two main strategies for this have emerged: explicit feature alignment through deformable registration and implicit learned alignment using techniques like transformers, with the former providing more control. However, the optimal approach for explicit alignment in mammography remains underexplored. In this study, we provide insights into where explicit alignment should occur (input space vs. representation space) and if alignment and risk prediction should be jointly optimized. We demonstrate that jointly learning explicit alignment in representation space while optimizing risk estimation performance, as done in the current state-of-the-art approach, results in a trade-off between alignment quality and predictive performance and show that image-level alignment is superior to representation-level alignment, leading to better deformation field quality and enhanced risk prediction accuracy. The code is available at https://github.com/sot176/Longitudinal_Mammogram_Alignment.git.
comment: MICCAI 2025, early accepted
☆ SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation USENIX Security
Advances in generative models have transformed the field of synthetic image generation for privacy-preserving data synthesis (PPDS). However, the field lacks a comprehensive survey and comparison of synthetic image generation methods across diverse settings. In particular, when we generate synthetic images for the purpose of training a classifier, there is a pipeline of generation-sampling-classification which takes private training as input and outputs the final classifier of interest. In this survey, we systematically categorize existing image synthesis methods, privacy attacks, and mitigations along this generation-sampling-classification pipeline. To empirically compare diverse synthesis approaches, we provide a benchmark with representative generative methods and use model-agnostic membership inference attacks (MIAs) as a measure of privacy risk. Through this study, we seek to answer critical questions in PPDS: Can synthetic data effectively replace real data? Which release strategy balances utility and privacy? Do mitigations improve the utility-privacy tradeoff? Which generative models perform best across different scenarios? With a systematic evaluation of diverse methods, our study provides actionable insights into the utility-privacy tradeoffs of synthetic data generation methods and guides the decision on optimal data releasing strategies for real-world applications.
comment: Accepted at the 34th USENIX Security Symposium (USENIX Security '25). 21 pages, plus a 6-page appendix
☆ Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation
Distilled video generation models offer fast and efficient synthesis but struggle with motion customization when guided by reference videos, especially under training-free settings. Existing training-free methods, originally designed for standard diffusion models, fail to generalize due to the accelerated generative process and large denoising steps in distilled models. To address this, we propose MotionEcho, a novel training-free test-time distillation framework that enables motion customization by leveraging diffusion teacher forcing. Our approach uses high-quality, slow teacher models to guide the inference of fast student models through endpoint prediction and interpolation. To maintain efficiency, we dynamically allocate computation across timesteps according to guidance needs. Extensive experiments across various distilled video generation models and benchmark datasets demonstrate that our method significantly improves motion fidelity and generation quality while preserving high efficiency. Project page: https://euminds.github.io/motionecho/
☆ Image Segmentation using Chan-Vese Active Contours
This paper presents a comprehensive derivation and implementation of the Chan-Vese active contour model for image segmentation. The model, derived from the Mumford-Shah variational framework, evolves contours based on regional intensity differences rather than image gradients, making it highly effective for segmenting noisy images or images with weak boundaries. We provide a rigorous mathematical derivation of the level set formulation, including detailed treatment of each energy term using the divergence theorem and curve evolution theory. The resulting algorithm is implemented in Python using finite difference methods with special care to numerical stability, including an upwind entropy scheme and curvature-based regularization. Experimental results on medical and synthetic images demonstrate accurate segmentation, robustness to noise, and superior performance compared to classical edge-based methods. This study confirms the suitability of the Chan-Vese model for complex segmentation tasks and highlights its potential for use in real-world imaging applications.
☆ Trajectory Prediction in Dynamic Object Tracking: A Critical Study
This study provides a detailed analysis of current advancements in dynamic object tracking (DOT) and trajectory prediction (TP) methodologies, including their applications and challenges. It covers various approaches, such as feature-based, segmentation-based, estimation-based, and learning-based methods, evaluating their effectiveness, deployment, and limitations in real-world scenarios. The study highlights the significant impact of these technologies in automotive and autonomous vehicles, surveillance and security, healthcare, and industrial automation, contributing to safety and efficiency. Despite the progress, challenges such as improved generalization, computational efficiency, reduced data dependency, and ethical considerations still exist. The study suggests future research directions to address these challenges, emphasizing the importance of multimodal data integration, semantic information fusion, and developing context-aware systems, along with ethical and privacy-preserving frameworks.
☆ Segment Any 3D-Part in a Scene from a Sentence
This paper aims to achieve the segmentation of any 3D part in a scene based on natural language descriptions, extending beyond traditional object-level 3D scene understanding and addressing both data and methodological challenges. Due to the expensive acquisition and annotation burden, existing datasets and methods are predominantly limited to object-level comprehension. To overcome the limitations of data and annotation availability, we introduce the 3D-PU dataset, the first large-scale 3D dataset with dense part annotations, created through an innovative and cost-effective method for constructing synthetic 3D scenes with fine-grained part-level annotations, paving the way for advanced 3D-part scene understanding. On the methodological side, we propose OpenPart3D, a 3D-input-only framework to effectively tackle the challenges of part-level segmentation. Extensive experiments demonstrate the superiority of our approach in open-vocabulary 3D scene understanding tasks at the part level, with strong generalization capabilities across various 3D scene datasets.
☆ Comparative Performance of Finetuned ImageNet Pre-trained Models for Electronic Component Classification
Electronic component classification and detection are crucial in manufacturing industries, significantly reducing labor costs and promoting technological and industrial development. Pre-trained models, especially those trained on ImageNet, are highly effective in image classification, allowing researchers to achieve excellent results even with limited data. This paper compares the performance of twelve ImageNet pre-trained models in classifying electronic components. Our findings show that all models tested delivered respectable accuracies. MobileNet-V2 recorded the highest at 99.95%, while EfficientNet-B0 had the lowest at 92.26%. These results underscore the substantial benefits of using ImageNet pre-trained models in image classification tasks and confirm the practical applicability of these methods in the electronics manufacturing sector.
comment: This is the author's version of the accepted paper. The final version will appear in IEEE UV 2024
☆ Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learning MICCAI2025
Multimodal pathology-genomic analysis is critical for cancer survival prediction. However, existing approaches predominantly integrate formalin-fixed paraffin-embedded (FFPE) slides with genomic data, while neglecting the availability of other preservation slides, such as Fresh Froze (FF) slides. Moreover, as the high-resolution spatial nature of pathology data tends to dominate the cross-modality fusion process, it hinders effective multimodal fusion and leads to modality imbalance challenges between pathology and genomics. These methods also typically require complete data modalities, limiting their clinical applicability with incomplete modalities, such as missing either pathology or genomic data. In this paper, we propose a multimodal survival prediction framework that leverages hypergraph learning to effectively integrate multi-WSI information and cross-modality interactions between pathology slides and genomics data while addressing modality imbalance. In addition, we introduce a memory mechanism that stores previously learned paired pathology-genomic features and dynamically compensates for incomplete modalities. Experiments on five TCGA datasets demonstrate that our model outperforms advanced methods by over 2.3% in C-Index. Under incomplete modality scenarios, our approach surpasses pathology-only (3.3%) and gene-only models (7.9%). Code: https://github.com/MCPathology/M2Surv
comment: accepted by MICCAI2025 code: https://github.com/MCPathology/M2Surv
☆ Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities MICCAI 2025
Traditional fundus image analysis models focus on single-modal tasks, ignoring fundus modality complementarity, which limits their versatility. Recently, retinal foundation models have emerged, but most still remain modality-specific. Integrating multiple fundus imaging modalities into a single foundation model is valuable. However, in dynamic environments, data from different modalities often arrive incrementally, necessitating continual pre-training. To address this, we propose RetCoP, the first continual vision-language pre-training framework in the fundus domain, which incrementally integrates image and text features from different imaging modalities into a single unified foundation model. To mitigate catastrophic forgetting in continual pre-training, we introduce a rehearsal strategy utilizing representative image-text pairs and an off-diagonal information distillation approach. The former allows the model to revisit knowledge from previous stages, while the latter explicitly preserves the alignment between image and text representations. Experiments show that RetCoP outperforms all the compared methods, achieving the best generalization and lowest forgetting rate. The code can be found at https://github.com/Yuang-Yao/RetCoP.
comment: Accepted by MICCAI 2025
☆ Progressive Modality Cooperation for Multi-Modality Domain Adaptation
In this work, we propose a new generic multi-modality domain adaptation framework called Progressive Modality Cooperation (PMC) to transfer the knowledge learned from the source domain to the target domain by exploiting multiple modality clues (\eg, RGB and depth) under the multi-modality domain adaptation (MMDA) and the more general multi-modality domain adaptation using privileged information (MMDA-PI) settings. Under the MMDA setting, the samples in both domains have all the modalities. In two newly proposed modules of our PMC, the multiple modalities are cooperated for selecting the reliable pseudo-labeled target samples, which captures the modality-specific information and modality-integrated information, respectively. Under the MMDA-PI setting, some modalities are missing in the target domain. Hence, to better exploit the multi-modality data in the source domain, we further propose the PMC with privileged information (PMC-PI) method by proposing a new multi-modality data generation (MMG) network. MMG generates the missing modalities in the target domain based on the source domain data by considering both domain distribution mismatch and semantics preservation, which are respectively achieved by using adversarial learning and conditioning on weighted pseudo semantics. Extensive experiments on three image datasets and eight video datasets for various multi-modality cross-domain visual recognition tasks under both MMDA and MMDA-PI settings clearly demonstrate the effectiveness of our proposed PMC framework.
☆ Capturing Fine-Grained Alignments Improves 3D Affordance Detection
In this work, we address the challenge of affordance detection in 3D point clouds, a task that requires effectively capturing fine-grained alignments between point clouds and text. Existing methods often struggle to model such alignments, resulting in limited performance on standard benchmarks. A key limitation of these approaches is their reliance on simple cosine similarity between point cloud and text embeddings, which lacks the expressiveness needed for fine-grained reasoning. To address this limitation, we propose LM-AD, a novel method for affordance detection in 3D point clouds. Moreover, we introduce the Affordance Query Module (AQM), which efficiently captures fine-grained alignment between point clouds and text by leveraging a pretrained language model. We demonstrated that our method outperformed existing approaches in terms of accuracy and mean Intersection over Union on the 3D AffordanceNet dataset.
comment: MVA 2025 (Oral)
☆ Airway Skill Assessment with Spatiotemporal Attention Mechanisms Using Human Gaze
Airway management skills are critical in emergency medicine and are typically assessed through subjective evaluation, often failing to gauge competency in real-world scenarios. This paper proposes a machine learning-based approach for assessing airway skills, specifically endotracheal intubation (ETI), using human gaze data and video recordings. The proposed system leverages an attention mechanism guided by the human gaze to enhance the recognition of successful and unsuccessful ETI procedures. Visual masks were created from gaze points to guide the model in focusing on task-relevant areas, reducing irrelevant features. An autoencoder network extracts features from the videos, while an attention module generates attention from the visual masks, and a classifier outputs a classification score. This method, the first to use human gaze for ETI, demonstrates improved accuracy and efficiency over traditional methods. The integration of human gaze data not only enhances model performance but also offers a robust, objective assessment tool for clinical skills, particularly in high-stress environments such as military settings. The results show improvements in prediction accuracy, sensitivity, and trustworthiness, highlighting the potential for this approach to improve clinical training and patient outcomes in emergency medicine.
comment: 13 pages, 6 figures, 14 equations,
☆ Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models
Open-Vocabulary Camouflaged Object Segmentation (OVCOS) seeks to segment and classify camouflaged objects from arbitrary categories, presenting unique challenges due to visual ambiguity and unseen categories.Recent approaches typically adopt a two-stage paradigm: first segmenting objects, then classifying the segmented regions using Vision Language Models (VLMs).However, these methods (1) suffer from a domain gap caused by the mismatch between VLMs' full-image training and cropped-region inference, and (2) depend on generic segmentation models optimized for well-delineated objects, making them less effective for camouflaged objects.Without explicit guidance, generic segmentation models often overlook subtle boundaries, leading to imprecise segmentation.In this paper,we introduce a novel VLM-guided cascaded framework to address these issues in OVCOS.For segmentation, we leverage the Segment Anything Model (SAM), guided by the VLM.Our framework uses VLM-derived features as explicit prompts to SAM, effectively directing attention to camouflaged regions and significantly improving localization accuracy.For classification, we avoid the domain gap introduced by hard cropping.Instead, we treat the segmentation output as a soft spatial prior via the alpha channel, which retains the full image context while providing precise spatial guidance, leading to more accurate and context-aware classification of camouflaged objects.The same VLM is shared across both segmentation and classification to ensure efficiency and semantic consistency.Extensive experiments on both OVCOS and conventional camouflaged object segmentation benchmarks demonstrate the clear superiority of our method, highlighting the effectiveness of leveraging rich VLM semantics for both segmentation and classification of camouflaged objects.
☆ Explicit Residual-Based Scalable Image Coding for Humans and Machines
Scalable image compression is a technique that progressively reconstructs multiple versions of an image for different requirements. In recent years, images have increasingly been consumed not only by humans but also by image recognition models. This shift has drawn growing attention to scalable image compression methods that serve both machine and human vision (ICMH). Many existing models employ neural network-based codecs, known as learned image compression, and have made significant strides in this field by carefully designing the loss functions. In some cases, however, models are overly reliant on their learning capacity, and their architectural design is not sufficiently considered. In this paper, we enhance the coding efficiency and interpretability of ICMH framework by integrating an explicit residual compression mechanism, which is commonly employed in resolution scalable coding methods such as JPEG2000. Specifically, we propose two complementary methods: Feature Residual-based Scalable Coding (FR-ICMH) and Pixel Residual-based Scalable Coding (PR-ICMH). These proposed methods are applicable to various machine vision tasks. Moreover, they provide flexibility to choose between encoder complexity and compression performance, making it adaptable to diverse application requirements. Experimental results demonstrate the effectiveness of our proposed methods, with PR-ICMH achieving up to 29.57% BD-rate savings over the previous work.
☆ HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
We propose HoliGS, a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos. Unlike prior 4D Gaussian splatting and dynamic NeRF pipelines, which struggle with training overhead in minute-long captures, our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately. Specifically, we decompose each scene into a static background plus time-varying objects, each represented by learned Gaussian primitives undergoing global rigid transformations, skeleton-driven articulation, and subtle non-rigid deformations via an invertible neural flow. This hierarchical warping strategy enables robust free-viewpoint novel-view rendering from various embodied camera trajectories by attaching Gaussians to a complete canonical foreground shape (\eg, egocentric or third-person follow), which may involve substantial viewpoint changes and interactions between multiple actors. Our experiments demonstrate that \ourmethod~ achieves superior reconstruction quality on challenging datasets while significantly reducing both training and rendering time compared to state-of-the-art monocular deformable NeRFs. These results highlight a practical and scalable solution for EVS in real-world scenarios. The source code will be released.
☆ Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding
Automated waterway environment perception is crucial for enabling unmanned surface vessels (USVs) to understand their surroundings and make informed decisions. Most existing waterway perception models primarily focus on instance-level object perception paradigms (e.g., detection, segmentation). However, due to the complexity of waterway environments, current perception datasets and models fail to achieve global semantic understanding of waterways, limiting large-scale monitoring and structured log generation. With the advancement of vision-language models (VLMs), we leverage image captioning to introduce WaterCaption, the first captioning dataset specifically designed for waterway environments. WaterCaption focuses on fine-grained, multi-region long-text descriptions, providing a new research direction for visual geo-understanding and spatial scene cognition. Exactly, it includes 20.2k image-text pair data with 1.8 million vocabulary size. Additionally, we propose Da Yu, an edge-deployable multi-modal large language model for USVs, where we propose a novel vision-to-language projector called Nano Transformer Adaptor (NTA). NTA effectively balances computational efficiency with the capacity for both global and fine-grained local modeling of visual features, thereby significantly enhancing the model's ability to generate long-form textual outputs. Da Yu achieves an optimal balance between performance and efficiency, surpassing state-of-the-art models on WaterCaption and several other captioning benchmarks.
comment: 14 pages, 13 figures
☆ AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration
While multi-vehicular collaborative driving demonstrates clear advantages over single-vehicle autonomy, traditional infrastructure-based V2X systems remain constrained by substantial deployment costs and the creation of "uncovered danger zones" in rural and suburban areas. We present AirV2X-Perception, a large-scale dataset that leverages Unmanned Aerial Vehicles (UAVs) as a flexible alternative or complement to fixed Road-Side Units (RSUs). Drones offer unique advantages over ground-based perception: complementary bird's-eye-views that reduce occlusions, dynamic positioning capabilities that enable hovering, patrolling, and escorting navigation rules, and significantly lower deployment costs compared to fixed infrastructure. Our dataset comprises 6.73 hours of drone-assisted driving scenarios across urban, suburban, and rural environments with varied weather and lighting conditions. The AirV2X-Perception dataset facilitates the development and standardized evaluation of Vehicle-to-Drone (V2D) algorithms, addressing a critical gap in the rapidly expanding field of aerial-assisted autonomous driving systems. The dataset and development kits are open-sourced at https://github.com/taco-group/AirV2X-Perception.
☆ Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation
This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The domain-collaborative learning aims to learn domain-specific feature representation to preserve the discriminability for the target domain, while the domain adversarial learning aims to learn domain-invariant feature representation to reduce the domain distribution mismatch between the source and target domains. We show that these two learning strategies can be uniformly formulated as domain classifier learning with positive or negative weights on the losses. We then design a collaborative and adversarial training scheme, which automatically learns domain-specific representations from lower blocks in CNNs through collaborative learning and domain-invariant representations from higher blocks through adversarial learning. Moreover, to further enhance the discriminability in the target domain, we propose Self-Paced CAN (SPCAN), which progressively selects pseudo-labeled target samples for re-training the classifiers. We employ a self-paced learning strategy to select pseudo-labeled target samples in an easy-to-hard fashion. Comprehensive experiments on different benchmark datasets, Office-31, ImageCLEF-DA, and VISDA-2017 for the object recognition task, and UCF101-10 and HMDB51-10 for the video action recognition task, show our newly proposed approaches achieve the state-of-the-art performance, which clearly demonstrates the effectiveness of our proposed approaches for unsupervised domain adaptation.
☆ Convergent and divergent connectivity patterns of the arcuate fasciculus in macaques and humans
The organization and connectivity of the arcuate fasciculus (AF) in nonhuman primates remain contentious, especially concerning how its anatomy diverges from that of humans. Here, we combined cross-scale single-neuron tracing - using viral-based genetic labeling and fluorescence micro-optical sectioning tomography in macaques (n = 4; age 3 - 11 years) - with whole-brain tractography from 11.7T diffusion MRI. Complemented by spectral embedding analysis of 7.0T MRI in humans, we performed a comparative connectomic analysis of the AF across species. We demonstrate that the macaque AF originates in the temporal-parietal cortex, traverses the auditory cortex and parietal operculum, and projects into prefrontal regions. In contrast, the human AF exhibits greater expansion into the middle temporal gyrus and stronger prefrontal and parietal operculum connectivity - divergences quantified by Kullback-Leibler analysis that likely underpin the evolutionary specialization of human language networks. These interspecies differences - particularly the human AF's broader temporal integration and strengthened frontoparietal linkages - suggest a connectivity-based substrate for the emergence of advanced language processing unique to humans. Furthermore, our findings offer a neuroanatomical framework for understanding AF-related disorders such as aphasia and dyslexia, where aberrant connectivity disrupts language function.
comment: 34 pages, 6 figures
☆ 3D-SSM: A Novel 3D Selective Scan Module for Remote Sensing Change Detection
Existing Mamba-based approaches in remote sensing change detection have enhanced scanning models, yet remain limited by their inability to capture long-range dependencies between image channels effectively, which restricts their feature representation capabilities. To address this limitation, we propose a 3D selective scan module (3D-SSM) that captures global information from both the spatial plane and channel perspectives, enabling a more comprehensive understanding of the data.Based on the 3D-SSM, we present two key components: a spatiotemporal interaction module (SIM) and a multi-branch feature extraction module (MBFEM). The SIM facilitates bi-temporal feature integration by enabling interactions between global and local features across images from different time points, thereby enhancing the detection of subtle changes. Meanwhile, the MBFEM combines features from the frequency domain, spatial domain, and 3D-SSM to provide a rich representation of contextual information within the image. Our proposed method demonstrates favourable performance compared to state-of-the-art change detection methods on five benchmark datasets through extensive experiments. Code is available at https://github.com/VerdantMist/3D-SSM
☆ Automated Image Recognition Framework
While the efficacy of deep learning models heavily relies on data, gathering and annotating data for specific tasks, particularly when addressing novel or sensitive subjects lacking relevant datasets, poses significant time and resource challenges. In response to this, we propose a novel Automated Image Recognition (AIR) framework that harnesses the power of generative AI. AIR empowers end-users to synthesize high-quality, pre-annotated datasets, eliminating the necessity for manual labeling. It also automatically trains deep learning models on the generated datasets with robust image recognition performance. Our framework includes two main data synthesis processes, AIR-Gen and AIR-Aug. The AIR-Gen enables end-users to seamlessly generate datasets tailored to their specifications. To improve image quality, we introduce a novel automated prompt engineering module that leverages the capabilities of large language models. We also introduce a distribution adjustment algorithm to eliminate duplicates and outliers, enhancing the robustness and reliability of generated datasets. On the other hand, the AIR-Aug enhances a given dataset, thereby improving the performance of deep classifier models. AIR-Aug is particularly beneficial when users have limited data for specific tasks. Through comprehensive experiments, we demonstrated the efficacy of our generated data in training deep learning models and showcased the system's potential to provide image recognition models for a wide range of objects. We also conducted a user study that achieved an impressive score of 4.4 out of 5.0, underscoring the AI community's positive perception of AIR.
comment: ICCCI 2025
☆ MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly vulnerable to harmful multimodal prompts that can trigger unethical or unsafe behaviors. Existing safety alignment approaches, primarily designed for unimodal language models, fall short in addressing the complex and nuanced threats posed by multimodal inputs. Moreover, current safety datasets lack the fine-grained, policy-grounded reasoning required to robustly align reasoning-capable VLMs. In this work, we introduce {MSR-Align}, a high-quality Multimodal Safety Reasoning dataset tailored to bridge this gap. MSR-Align supports fine-grained, deliberative reasoning over standardized safety policies across both vision and text modalities. Our data generation pipeline emphasizes multimodal diversity, policy-grounded reasoning, and rigorous quality filtering using strong multimodal judges. Extensive experiments demonstrate that fine-tuning VLMs on MSR-Align substantially improves robustness against both textual and vision-language jailbreak attacks, while preserving or enhancing general reasoning performance. MSR-Align provides a scalable and effective foundation for advancing the safety alignment of reasoning-capable VLMs. Our dataset is made publicly available at https://huggingface.co/datasets/Leigest/MSR-Align.
☆ Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology
Anomaly detection has been widely studied in the context of industrial defect inspection, with numerous methods developed to tackle a range of challenges. In digital pathology, anomaly detection holds significant potential for applications such as rare disease identification, artifact detection, and biomarker discovery. However, the unique characteristics of pathology images, such as their large size, multi-scale structures, stain variability, and repetitive patterns, introduce new challenges that current anomaly detection algorithms struggle to address. In this quantitative study, we benchmark over 20 classical and prevalent anomaly detection methods through extensive experiments. We curated five digital pathology datasets, both real and synthetic, to systematically evaluate these approaches. Our experiments investigate the influence of image scale, anomaly pattern types, and training epoch selection strategies on detection performance. The results provide a detailed comparison of each method's strengths and limitations, establishing a comprehensive benchmark to guide future research in anomaly detection for digital pathology images.
☆ Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
Multi-modal large language models (MLLMs) models have made significant progress in video understanding over the past few years. However, processing long video inputs remains a major challenge due to high memory and computational costs. This makes it difficult for current models to achieve both strong performance and high efficiency in long video understanding. To address this challenge, we propose Video-XL-2, a novel MLLM that delivers superior cost-effectiveness for long-video understanding based on task-aware KV sparsification. The proposed framework operates with two key steps: chunk-based pre-filling and bi-level key-value decoding. Chunk-based pre-filling divides the visual token sequence into chunks, applying full attention within each chunk and sparse attention across chunks. This significantly reduces computational and memory overhead. During decoding, bi-level key-value decoding selectively reloads either dense or sparse key-values for each chunk based on its relevance to the task. This approach further improves memory efficiency and enhances the model's ability to capture fine-grained information. Video-XL-2 achieves state-of-the-art performance on various long video understanding benchmarks, outperforming existing open-source lightweight models. It also demonstrates exceptional efficiency, capable of processing over 10,000 frames on a single NVIDIA A100 (80GB) GPU and thousands of frames in just a few seconds.
comment: 12 pages, 5 Figure, 3 Table
☆ Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network
Effective representation of Regions of Interest (ROI) and independent alignment of these ROIs can significantly enhance the performance of deformable medical image registration (DMIR). However, current learning-based DMIR methods have limitations. Unsupervised techniques disregard ROI representation and proceed directly with aligning pairs of images, while weakly-supervised methods heavily depend on label constraints to facilitate registration. To address these issues, we introduce a novel ROI-based registration approach named EASR-DCN. Our method represents medical images through effective ROIs and achieves independent alignment of these ROIs without requiring labels. Specifically, we first used a Gaussian mixture model for intensity analysis to represent images using multiple effective ROIs with distinct intensities. Furthermore, we propose a novel Divide-and-Conquer Network (DCN) to process these ROIs through separate channels to learn feature alignments for each ROI. The resultant correspondences are seamlessly integrated to generate a comprehensive displacement vector field. Extensive experiments were performed on three MRI and one CT datasets to showcase the superior accuracy and deformation reduction efficacy of our EASR-DCN. Compared to VoxelMorph, our EASR-DCN achieved improvements of 10.31\% in the Dice score for brain MRI, 13.01\% for cardiac MRI, and 5.75\% for hippocampus MRI, highlighting its promising potential for clinical applications. The code for this work will be released upon acceptance of the paper.
☆ MedErr-CT: A Visual Question Answering Benchmark for Identifying and Correcting Errors in CT Reports CVPR 2025
Computed Tomography (CT) plays a crucial role in clinical diagnosis, but the growing demand for CT examinations has raised concerns about diagnostic errors. While Multimodal Large Language Models (MLLMs) demonstrate promising comprehension of medical knowledge, their tendency to produce inaccurate information highlights the need for rigorous validation. However, existing medical visual question answering (VQA) benchmarks primarily focus on simple visual recognition tasks, lacking clinical relevance and failing to assess expert-level knowledge. We introduce MedErr-CT, a novel benchmark for evaluating medical MLLMs' ability to identify and correct errors in CT reports through a VQA framework. The benchmark includes six error categories - four vision-centric errors (Omission, Insertion, Direction, Size) and two lexical error types (Unit, Typo) - and is organized into three task levels: classification, detection, and correction. Using this benchmark, we quantitatively assess the performance of state-of-the-art 3D medical MLLMs, revealing substantial variation in their capabilities across different error types. Our benchmark contributes to the development of more reliable and clinically applicable MLLMs, ultimately helping reduce diagnostic errors and improve accuracy in clinical practice. The code and datasets are available at https://github.com/babbu3682/MedErr-CT.
comment: 14 pages, 5 figures, submitted to CVPR 2025
☆ ToSA: Token Merging with Spatial Awareness IROS 2025
Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token's feature similarity for token merging, overlooking the potential of integrating spatial information, which can serve as a reliable criterion for token merging in the early layers of ViT, where the visual tokens only possess weak visual information. In this paper, we propose ToSA, a novel token merging method that combines both semantic and spatial awareness to guide the token merging process. ToSA leverages the depth image as input to generate pseudo spatial tokens, which serve as auxiliary spatial information for the visual token merging process. With the introduced spatial awareness, ToSA achieves a more informed merging strategy that better preserves critical scene structure. Experimental results demonstrate that ToSA outperforms previous token merging methods across multiple benchmarks on visual and embodied question answering while largely reducing the runtime of the ViT, making it an efficient solution for ViT acceleration. The code will be available at: https://github.com/hsiangwei0903/ToSA
comment: Accepted by IROS 2025
☆ VoxelOpt: Voxel-Adaptive Message Passing for Discrete Optimization in Deformable Abdominal CT Registration MICCAI 2025
Recent developments in neural networks have improved deformable image registration (DIR) by amortizing iterative optimization, enabling fast and accurate DIR results. However, learning-based methods often face challenges with limited training data, large deformations, and tend to underperform compared to iterative approaches when label supervision is unavailable. While iterative methods can achieve higher accuracy in such scenarios, they are considerably slower than learning-based methods. To address these limitations, we propose VoxelOpt, a discrete optimization-based DIR framework that combines the strengths of learning-based and iterative methods to achieve a better balance between registration accuracy and runtime. VoxelOpt uses displacement entropy from local cost volumes to measure displacement signal strength at each voxel, which differs from earlier approaches in three key aspects. First, it introduces voxel-wise adaptive message passing, where voxels with lower entropy receives less influence from their neighbors. Second, it employs a multi-level image pyramid with 27-neighbor cost volumes at each level, avoiding exponential complexity growth. Third, it replaces hand-crafted features or contrastive learning with a pretrained foundational segmentation model for feature extraction. In abdominal CT registration, these changes allow VoxelOpt to outperform leading iterative in both efficiency and accuracy, while matching state-of-the-art learning-based methods trained with label supervision. The source code will be available at https://github.com/tinymilky/VoxelOpt
comment: Accepted for publication at MICCAI 2025
☆ EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression
Density map estimation has become the mainstream paradigm in crowd counting. However, most existing methods overlook the extreme sparsity of ground-truth density maps. In real-world crowd scenes, the vast majority of spatial regions (often over 95%) contain no people, leading to heavily imbalanced count distributions. Ignoring this imbalance can bias models toward overestimating dense regions and underperforming in sparse areas. Furthermore, most loss functions used in density estimation are majorly based on MSE and implicitly assume Gaussian distributions, which are ill-suited for modeling discrete, non-negative count data. In this paper, we propose EBC-ZIP, a crowd counting framework that models the spatial distribution of counts using a Zero-Inflated Poisson (ZIP) regression formulation. Our approach replaces the traditional regression loss with the negative log-likelihood of the ZIP distribution, enabling better handling of zero-heavy distributions while preserving count accuracy. Built upon the recently proposed Enhanced Block Classification (EBC) framework, EBC-ZIP inherits EBC's advantages in preserving the discreteness of targets and ensuring training stability, while further improving performance through a more principled probabilistic loss. We also evaluate EBC-ZIP with backbones of varying computational complexity to assess its scalability. Extensive experiments on four crowd counting benchmarks demonstrate that EBC-ZIP consistently outperforms EBC and achieves state-of-the-art results.
☆ Computer Vision based Automated Quantification of Agricultural Sprayers Boom Displacement
Application rate errors when using self-propelled agricultural sprayers for agricultural production remain a concern. Among other factors, spray boom instability is one of the major contributors to application errors. Spray booms' width of 38m, combined with 30 kph driving speeds, varying terrain, and machine dynamics when maneuvering complex field boundaries, make controls of these booms very complex. However, there is no quantitative knowledge on the extent of boom movement to systematically develop a solution that might include boom designs and responsive boom control systems. Therefore, this study was conducted to develop an automated computer vision system to quantify the boom movement of various agricultural sprayers. A computer vision system was developed to track a target on the edge of the sprayer boom in real time. YOLO V7, V8, and V11 neural network models were trained to track the boom's movements in field operations to quantify effective displacement in the vertical and transverse directions. An inclinometer sensor was mounted on the boom to capture boom angles and validate the neural network model output. The results showed that the model could detect the target with more than 90 percent accuracy, and distance estimates of the target on the boom were within 0.026 m of the inclinometer sensor data. This system can quantify the boom movement on the current sprayer and potentially on any other sprayer with minor modifications. The data can be used to make design improvements to make sprayer booms more stable and achieve greater application accuracy.
comment: Under publication process for COMPAG
☆ Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
Large language models (LLMs) predominantly use autoregressive (AR) approaches, but masked diffusion models (MDMs) are emerging as viable alternatives. A key challenge in comparing AR and MDM paradigms is their typical architectural difference: AR models are often decoder-only, while MDMs have largely been encoder-only. This practice of changing both the modeling paradigm and architecture simultaneously makes direct comparisons unfair, as it's hard to distinguish whether observed differences stem from the paradigm itself or the architectural shift. This research evaluates MDMs within a decoder-only framework to: (1) equitably compare MDM (as Any-Order AR, or AO-AR) and standard AR paradigms. Our investigation suggests that the standard AO-AR objective, which averages over all token permutations, may benefit from refinement, as many permutations appear less informative compared to the language's inherent left-to-right structure. (2) Investigate architectural influences (decoder-only vs. encoder-only) within MDMs. We demonstrate that while encoder-only MDMs model a simpler conditional probability space, decoder-only MDMs can achieve dramatic generation speedups ($\sim25\times$) and comparable perplexity with temperature annealing despite modeling a vastly larger space, highlighting key trade-offs. This work thus decouples core paradigm differences from architectural influences, offering insights for future model design. Code is available at https://github.com/scxue/AO-GPT-MDM.
♻ ☆ ObjCtrl-2.5D: Training-free Object Control with Camera Poses
This study aims to achieve more precise and versatile object control in image-to-video (I2V) generation. Current methods typically represent the spatial movement of target objects with 2D trajectories, which often fail to capture user intention and frequently produce unnatural results. To enhance control, we present ObjCtrl-2.5D, a training-free object control approach that uses a 3D trajectory, extended from a 2D trajectory with depth information, as a control signal. By modeling object movement as camera movement, ObjCtrl-2.5D represents the 3D trajectory as a sequence of camera poses, enabling object motion control using an existing camera motion control I2V generation model (CMC-I2V) without training. To adapt the CMC-I2V model originally designed for global motion control to handle local object motion, we introduce a module to isolate the target object from the background, enabling independent local control. In addition, we devise an effective way to achieve more accurate object control by sharing low-frequency warped latent within the object's region across frames. Extensive experiments demonstrate that ObjCtrl-2.5D significantly improves object control accuracy compared to training-free methods and offers more diverse control capabilities than training-based approaches using 2D trajectories, enabling complex effects like object rotation. Code and results are available at https://wzhouxiff.github.io/projects/ObjCtrl-2.5D/.
comment: Project Page: https://wzhouxiff.github.io/projects/ObjCtrl-2.5D/
♻ ☆ Two-Stream Spatial-Temporal Transformer Framework for Person Identification via Natural Conversational Keypoints
In the age of AI-driven generative technologies, traditional biometric recognition systems face unprecedented challenges, particularly from sophisticated deepfake and face reenactment techniques. In this study, we propose a Two-Stream Spatial-Temporal Transformer Framework for person identification using upper body keypoints visible during online conversations, which we term conversational keypoints. Our framework processes both spatial relationships between keypoints and their temporal evolution through two specialized branches: a Spatial Transformer (STR) that learns distinctive structural patterns in keypoint configurations, and a Temporal Transformer (TTR) that captures sequential motion patterns. Using the state-of-the-art Sapiens pose estimator, we extract 133 keypoints (based on COCO-WholeBody format) representing facial features, head pose, and hand positions. The framework was evaluated on a dataset of 114 individuals engaged in natural conversations, achieving recognition accuracies of 80.12% for the spatial stream, 63.61% for the temporal stream. We then explored two fusion strategies: a shared loss function approach achieving 82.22% accuracy, and a feature-level fusion method that concatenates feature maps from both streams, significantly improving performance to 94.86%. By jointly modeling both static anatomical relationships and dynamic movement patterns, our approach learns comprehensive identity signatures that are more robust to spoofing than traditional appearance-based methods.
comment: I would like to withdraw this submission due to the need for substantial revisions in the results and analysis. I plan to correct and improve the study and submit a more complete version in the near future
♻ ☆ Aligning Anime Video Generation with Human Feedback
Anime video generation faces significant challenges due to the scarcity of anime data and unusual motion patterns, leading to issues such as motion distortion and flickering artifacts, which result in misalignment with human preferences. Existing reward models, designed primarily for real-world videos, fail to capture the unique appearance and consistency requirements of anime. In this work, we propose a pipeline to enhance anime video generation by leveraging human feedback for better alignment. Specifically, we construct the first multi-dimensional reward dataset for anime videos, comprising 30k human-annotated samples that incorporating human preferences for both visual appearance and visual consistency. Based on this, we develop AnimeReward, a powerful reward model that employs specialized vision-language models for different evaluation dimensions to guide preference alignment. Furthermore, we introduce Gap-Aware Preference Optimization (GAPO), a novel training method that explicitly incorporates preference gaps into the optimization process, enhancing alignment performance and efficiency. Extensive experiment results show that AnimeReward outperforms existing reward models, and the inclusion of GAPO leads to superior alignment in both quantitative benchmarks and human evaluations, demonstrating the effectiveness of our pipeline in enhancing anime video quality. Our code and dataset are publicly available at https://github.com/bilibili/Index-anisora.
comment: 10 pages, 7 figures, 7 tables
♻ ☆ RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories IROS 2025
Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to address this issue by introducing external constraints but fall short of achieving satisfactory accuracy, particularly when camera trajectories are complex. In this paper, we propose a novel method, RA-NeRF, capable of predicting highly accurate camera poses even with complex camera trajectories. Following the incremental pipeline, RA-NeRF reconstructs the scene using NeRF with photometric consistency and incorporates flow-driven pose regulation to enhance robustness during initialization and localization. Additionally, RA-NeRF employs an implicit pose filter to capture the camera movement pattern and eliminate the noise for pose estimation. To validate our method, we conduct extensive experiments on the Tanks\&Temple dataset for standard evaluation, as well as the NeRFBuster dataset, which presents challenging camera pose trajectories. On both datasets, RA-NeRF achieves state-of-the-art results in both camera pose estimation and visual quality, demonstrating its effectiveness and robustness in scene reconstruction under complex pose trajectories.
comment: IROS 2025
♻ ☆ Grounding Beyond Detection: Enhancing Contextual Understanding in Embodied 3D Grounding
Embodied 3D grounding aims to localize target objects described in human instructions from ego-centric viewpoint. Most methods typically follow a two-stage paradigm where a trained 3D detector's optimized backbone parameters are used to initialize a grounding model. In this study, we explore a fundamental question: Does embodied 3D grounding benefit enough from detection? To answer this question, we assess the grounding performance of detection models using predicted boxes filtered by the target category. Surprisingly, these detection models without any instruction-specific training outperform the grounding models explicitly trained with language instructions. This indicates that even category-level embodied 3D grounding may not be well resolved, let alone more fine-grained context-aware grounding. Motivated by this finding, we propose DEGround, which shares DETR queries as object representation for both DEtection and Grounding and enables the grounding to benefit from basic category classification and box detection. Based on this framework, we further introduce a regional activation grounding module that highlights instruction-related regions and a query-wise modulation module that incorporates sentence-level semantic into the query representation, strengthening the context-aware understanding of language instructions. Remarkably, DEGround outperforms state-of-the-art model BIP3D by 7.52% at overall accuracy on the EmbodiedScan validation set. The source code will be publicly available at https://github.com/zyn213/DEGround.
comment: 1st place on EmbodiedScan visual grounding
♻ ☆ Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Rendering
Deep learning based rendering has achieved major improvements in photo-realistic image synthesis, with potential applications including visual effects in movies and photo-realistic scene building in video games. However, a significant limitation is the difficulty of decomposing the illumination and material parameters, which limits such methods to reconstructing an input scene, without any possibility to control these parameters. This paper introduces a novel physics based neural deferred shading pipeline to decompose the data-driven rendering process, learn a generalizable shading function to produce photo-realistic results for shading and relighting tasks; we also propose a shadow estimator to efficiently mimic shadowing effects. Our model achieves improved performance compared to classical models and a state-of-art neural shading model, and enables generalizable photo-realistic shading from arbitrary illumination input.
♻ ☆ ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval
E-commerce is increasingly multimedia-enriched, with products exhibited in a broad-domain manner as images, short videos, or live stream promotions. A unified and vectorized cross-domain production representation is essential. Due to large intra-product variance and high inter-product similarity in the broad-domain scenario, a visual-only representation is inadequate. While Automatic Speech Recognition (ASR) text derived from the short or live-stream videos is readily accessible, how to de-noise the excessively noisy text for multimodal representation learning is mostly untouched. We propose ASR-enhanced Multimodal Product Representation Learning (AMPere). In order to extract product-specific information from the raw ASR text, AMPere uses an easy-to-implement LLM-based ASR text summarizer. The LLM-summarized text, together with visual data, is then fed into a multi-branch network to generate compact multimodal embeddings. Extensive experiments on a large-scale tri-domain dataset verify the effectiveness of AMPere in obtaining a unified multimodal product representation that clearly improves cross-domain product retrieval.
comment: accepted for publication as a REGULAR paper in the IEEE Transactions on Multimedia
♻ ☆ IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study
Minimizing the need for pixel-level annotated data to train PET lesion detection and segmentation networks is highly desired and can be transformative, given time and cost constraints associated with expert annotations. Current unsupervised or weakly-supervised anomaly detection methods rely on autoencoder or generative adversarial networks (GANs) trained only on healthy data. While these approaches reduce annotation dependency, GAN-based methods are notably more challenging to train than non-GAN alternatives (such as autoencoders) due to issues such as the simultaneous optimization of two competing networks, mode collapse, and training instability. In this paper, we present the weakly-supervised $\textbf{I}$mplicitly-$\textbf{g}$uided $\textbf{CO}$u$\textbf{N}$terfactual diffusion model for $\textbf{D}$etecting $\textbf{A}$nomalies in $\textbf{PET}$ images (IgCONDA-PET). The solution is developed and validated using PET scans from six retrospective cohorts consisting of a total of 2652 cases (multi-cancer, multi-tracer) containing both local and public datasets (spanning multiple centers). The training is conditioned on image class labels (healthy vs. unhealthy) via attention modules, and we employ implicit diffusion guidance. We perform counterfactual generation which facilitates "unhealthy-to-healthy" domain translation by generating a synthetic, healthy version of an unhealthy input image, enabling the detection of anomalies through the calculated differences. The performance of our method was compared against several other deep learning based weakly-supervised or unsupervised methods as well as traditional methods like 41% SUV$_\text{max}$ thresholding. We also highlight the importance of incorporating attention modules in our network for the detection of small anomalies. The code is publicly available at: https://github.com/ahxmeds/IgCONDA-PET.git.
comment: 48 pages, 13 figures, 4 tables
♻ ☆ Light of Normals: Unified Feature Representation for Universal Photometric Stereo
Universal photometric stereo (PS) aims to recover high-quality surface normals from objects under arbitrary lighting conditions without relying on specific illumination models. Despite recent advances such as SDM-UniPS and Uni MS-PS, two fundamental challenges persist: 1) the deep coupling between varying illumination and surface normal features, where ambiguity in observed intensity makes it difficult to determine whether brightness variations stem from lighting changes or surface orientation; and 2) the preservation of high-frequency geometric details in complex surfaces, where intricate geometries create self-shadowing, inter-reflections, and subtle normal variations that conventional feature processing operations struggle to capture accurately.
comment: Home: https://houyuanchen111.github.io/lino.github.io Github: https://github.com/houyuanchen111/LINO_UniPS HuggingFace Demo: https://huggingface.co/spaces/houyuanchen/lino
♻ ☆ MAMMA: Markerless & Automatic Multi-Person Motion Action Capture
We present MAMMA, a markerless motion-capture pipeline that accurately recovers SMPL-X parameters from multi-view video of two-person interaction sequences. Traditional motion-capture systems rely on physical markers. Although they offer high accuracy, their requirements of specialized hardware, manual marker placement, and extensive post-processing make them costly and time-consuming. Recent learning-based methods attempt to overcome these limitations, but most are designed for single-person capture, rely on sparse keypoints, or struggle with occlusions and physical interactions. In this work, we introduce a method that predicts dense 2D surface landmarks conditioned on segmentation masks, enabling person-specific correspondence estimation even under heavy occlusion. We employ a novel architecture that exploits learnable queries for each landmark. We demonstrate that our approach can handle complex person--person interaction and offers greater accuracy than existing methods. To train our network, we construct a large, synthetic multi-view dataset combining human motions from diverse sources, including extreme poses, hand motions, and close interactions. Our dataset yields high-variability synthetic sequences with rich body contact and occlusion, and includes SMPL-X ground-truth annotations with dense 2D landmarks. The result is a system capable of capturing human motion without the need for markers. Our approach offers competitive reconstruction quality compared to commercial marker-based motion-capture solutions, without the extensive manual cleanup. Finally, we address the absence of common benchmarks for dense-landmark prediction and markerless motion capture by introducing two evaluation settings built from real multi-view sequences. We will release our dataset, benchmark, method, training code, and pre-trained model weights for research purposes.
♻ ☆ LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, limiting flexibility for specific edits. First-frame-guided editing provides control over the first frame, but lacks flexibility over subsequent frames. To address this, we propose a mask-based LoRA (Low-Rank Adaptation) tuning method that adapts pretrained Image-to-Video (I2V) models for flexible video editing. Our approach preserves background regions while enabling controllable edits propagation. This solution offers efficient and adaptable video editing without altering the model architecture. To better steer this process, we incorporate additional references, such as alternate viewpoints or representative scene states, which serve as visual anchors for how content should unfold. We address the control challenge using a mask-driven LoRA tuning strategy that adapts a pre-trained image-to-video model to the editing context. The model must learn from two distinct sources: the input video provides spatial structure and motion cues, while reference images offer appearance guidance. A spatial mask enables region-specific learning by dynamically modulating what the model attends to, ensuring that each area draws from the appropriate source. Experimental results show our method achieves superior video editing performance compared to state-of-the-art methods. Project Page: https://cjeen.github.io/LoraEditPaper
comment: 12 pages
♻ ☆ FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models ICML25
Federated prompt learning (FPL) for vision-language models is a powerful approach to collaboratively adapt models across distributed clients while preserving data privacy. However, existing FPL approaches suffer from a trade-off between performance and robustness, particularly in out-of-distribution (OOD) shifts, limiting their reliability in real-world scenarios. The inherent in-distribution (ID) data heterogeneity among different clients makes it more challenging to maintain this trade-off. To fill this gap, we introduce a Federated OOD-aware Context Optimization (FOCoOp) framework, which captures diverse distributions among clients using ID global prompts, local prompts, and OOD prompts. Specifically, FOCoOp leverages three sets of prompts to create both class-level and distribution-level separations, which adapt to OOD shifts through bi-level distributionally robust optimization. Additionally, FOCoOp improves the discrimination consistency among clients, i.e., calibrating global prompts, seemingly OOD prompts, and OOD prompts by semi-unbalanced optimal transport. The extensive experiments on real-world datasets demonstrate that FOCoOp effectively captures decentralized heterogeneous distributions and enhances robustness of different OOD shifts. The project is available at GitHub.
comment: Accepted by ICML25
♻ ☆ GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation CVPR 2025
A key challenge in model-free category-level pose estimation is the extraction of contextual object features that generalize across varying instances within a specific category. Recent approaches leverage foundational features to capture semantic and geometry cues from data. However, these approaches fail under partial visibility. We overcome this with a first-complete-then-aggregate strategy for feature extraction utilizing class priors. In this paper, we present GCE-Pose, a method that enhances pose estimation for novel instances by integrating category-level global context prior. GCE-Pose performs semantic shape reconstruction with a proposed Semantic Shape Reconstruction (SSR) module. Given an unseen partial RGB-D object instance, our SSR module reconstructs the instance's global geometry and semantics by deforming category-specific 3D semantic prototypes through a learned deep Linear Shape Model. We further introduce a Global Context Enhanced (GCE) feature fusion module that effectively fuses features from partial RGB-D observations and the reconstructed global context. Extensive experiments validate the impact of our global context prior and the effectiveness of the GCE fusion module, demonstrating that GCE-Pose significantly outperforms existing methods on challenging real-world datasets HouseCat6D and NOCS-REAL275. Our project page is available at https://colin-de.github.io/GCE-Pose/.
comment: CVPR 2025 accepted
♻ ☆ crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023
The cross-Modality Domain Adaptation (crossMoDA) challenge series, initiated in 2021 in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), focuses on unsupervised cross-modality segmentation, learning from contrast-enhanced T1 (ceT1) and transferring to T2 MRI. The task is an extreme example of domain shift chosen to serve as a meaningful and illustrative benchmark. From a clinical application perspective, it aims to automate Vestibular Schwannoma (VS) and cochlea segmentation on T2 scans for more cost-effective VS management. Over time, the challenge objectives have evolved to enhance its clinical relevance. The challenge evolved from using single-institutional data and basic segmentation in 2021 to incorporating multi-institutional data and Koos grading in 2022, and by 2023, it included heterogeneous routine data and sub-segmentation of intra- and extra-meatal tumour components. In this work, we report the findings of the 2022 and 2023 editions and perform a retrospective analysis of the challenge progression over the years. The observations from the successive challenge contributions indicate that the number of outliers decreases with an expanding dataset. This is notable since the diversity of scanning protocols of the datasets concurrently increased. The winning approach of the 2023 edition reduced the number of outliers on the 2021 and 2022 testing data, demonstrating how increased data heterogeneity can enhance segmentation performance even on homogeneous data. However, the cochlea Dice score declined in 2023, likely due to the added complexity from tumour sub-annotations affecting overall segmentation performance. While progress is still needed for clinically acceptable VS segmentation, the plateauing performance suggests that a more challenging cross-modal task may better serve future benchmarking.
♻ ☆ FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction
We propose end-to-end differentiable model that predicts robot trajectories on rough offroad terrain from camera images and/or lidar point clouds. The model integrates a learnable component that predicts robot-terrain interaction forces with a neural-symbolic layer that enforces the laws of classical mechanics and consequently improves generalization on out-of-distribution data. The neural-symbolic layer includes a differentiable physics engine that computes the robot's trajectory by querying these forces at the points of contact with the terrain. As the proposed architecture comprises substantial geometrical and physics priors, the resulting model can also be seen as a learnable physics engine conditioned on real sensor data that delivers $10^4$ trajectories per second. We argue and empirically demonstrate that this architecture reduces the sim-to-real gap and mitigates out-of-distribution sensitivity. The differentiability, in conjunction with the rapid simulation speed, makes the model well-suited for various applications including model predictive control, trajectory shooting, supervised and reinforcement learning, or SLAM.
comment: Code: https://github.com/ctu-vras/fusionforce
♻ ☆ AI-based Multimodal Biometrics for Detecting Smartphone Distractions: Application to Online Learning
This work investigates the use of multimodal biometrics to detect distractions caused by smartphone use during tasks that require sustained attention, with a focus on computer-based online learning. Although the methods are applicable to various domains, such as autonomous driving, we concentrate on the challenges learners face in maintaining engagement amid internal (e.g., motivation), system-related (e.g., course design) and contextual (e.g., smartphone use) factors. Traditional learning platforms often lack detailed behavioral data, but Multimodal Learning Analytics (MMLA) and biosensors provide new insights into learner attention. We propose an AI-based approach that leverages physiological signals and head pose data to detect phone use. Our results show that single biometric signals, such as brain waves or heart rate, offer limited accuracy, while head pose alone achieves 87%. A multimodal model combining all signals reaches 91% accuracy, highlighting the benefits of integration. We conclude by discussing the implications and limitations of deploying these models for real-time support in online learning environments.
comment: Accepted in EC-TEL25: 20th European Conference on Technology Enhanced Learning, Newcastle and Durham, UK, 15-19 September 2025
♻ ☆ Contactless Cardiac Pulse Monitoring Using Event Cameras
Time event cameras are a novel technology for recording scene information at extremely low latency and with low power consumption. Event cameras output a stream of events that encapsulate pixel-level light intensity changes within the scene, capturing information with a higher dynamic range and temporal resolution than traditional cameras. This study investigates the contact-free reconstruction of an individual's cardiac pulse signal from time event recording of their face using a supervised convolutional neural network (CNN) model. An end-to-end model is trained to extract the cardiac signal from a two-dimensional representation of the event stream, with model performance evaluated based on the accuracy of the calculated heart rate. The experimental results confirm that physiological cardiac information in the facial region is effectively preserved within the event stream, showcasing the potential of this novel sensor for remote heart rate monitoring. The model trained on event frames achieves a root mean square error (RMSE) of 3.32 beats per minute (bpm) compared to the RMSE of 2.92 bpm achieved by the baseline model trained on standard camera frames. Furthermore, models trained on event frames generated at 60 and 120 FPS outperformed the 30 FPS standard camera results, achieving an RMSE of 2.54 and 2.13 bpm, respectively.
♻ ☆ Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlases
Anatomical atlases are widely used for population studies and analysis. Conditional atlases target a specific sub-population defined via certain conditions, such as demographics or pathologies, and allow for the investigation of fine-grained anatomical differences like morphological changes associated with ageing or disease. Existing approaches use either registration-based methods that are often unable to handle large anatomical variations or generative adversarial models, which are challenging to train since they can suffer from training instabilities. Instead of generating atlases directly in as intensities, we propose using latent diffusion models to generate deformation fields, which transform a general population atlas into one representing a specific sub-population. Our approach ensures structural integrity, enhances interpretability and avoids hallucinations that may arise during direct image synthesis by generating this deformation field and regularising it using a neighbourhood of images. We compare our method to several state-of-the-art atlas generation methods using brain MR images from the UK Biobank. Our method generates highly realistic atlases with smooth transformations and high anatomical fidelity, outperforming existing baselines. We demonstrate the quality of these atlases through comprehensive evaluations, including quantitative metrics for anatomical accuracy, perceptual similarity, and qualitative analyses displaying the consistency and realism of the generated atlases.
♻ ☆ ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
Recent advancements in large reasoning models (LRMs) like DeepSeek-R1 and OpenAI o1 series have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT). However, an emerging issue is their inclination to produce excessively verbose reasoning processes, leading to the inefficiency problem. Existing literature on improving efficiency mainly adheres to the before-reasoning paradigms such as prompting and reasoning or fine-tuning and reasoning, but ignores the promising direction of directly encouraging the model to speak concisely by intervening during the generation of reasoning. In order to fill the blank, we propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely by injecting the textual hint (manually designed or trained on the concise data) during the token generation of the reasoning process. Besides, ConciseHint is adaptive to the complexity of the query by adaptively adjusting the hint intensity, which ensures it will not undermine model performance. Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning processes while maintaining performance well. For instance, we achieve a reduction ratio of 65\% for the reasoning length on GSM8K benchmark with Qwen-3 4B with nearly no accuracy loss.
comment: Codes are available at https://github.com/tsa18/ConciseHint
♻ ☆ Cross-sensor self-supervised training and alignment for remote sensing
Large-scale ''foundation models'' have gained traction as a way to leverage the vast amounts of unlabeled remote sensing data collected every day. However, due to the multiplicity of Earth Observation satellites, these models should learn ''sensor agnostic'' representations, that generalize across sensor characteristics with minimal fine-tuning. This is complicated by data availability, as low-resolution imagery, such as Sentinel-2 and Landsat-8 data, are available in large amounts, while very high-resolution aerial or satellite data is less common. To tackle these challenges, we introduce cross-sensor self-supervised training and alignment for remote sensing (X-STARS). We design a self-supervised training loss, the Multi-Sensor Alignment Dense loss (MSAD), to align representations across sensors, even with vastly different resolutions. Our X-STARS can be applied to train models from scratch, or to adapt large models pretrained on e.g low-resolution EO data to new high-resolution sensors, in a continual pretraining framework. We collect and release MSC-France, a new multi-sensor dataset, on which we train our X-STARS models, then evaluated on seven downstream classification and segmentation tasks. We demonstrate that X-STARS outperform s the state-of-the-art by a significant margin with less data across various conditions of data availability and resolutions.
♻ ☆ Improving Out-of-Distribution Detection via Dynamic Covariance Calibration ICML25
Out-of-Distribution (OOD) detection is essential for the trustworthiness of AI systems. Methods using prior information (i.e., subspace-based methods) have shown effective performance by extracting information geometry to detect OOD data with a more appropriate distance metric. However, these methods fail to address the geometry distorted by ill-distributed samples, due to the limitation of statically extracting information geometry from the training distribution. In this paper, we argue that the influence of ill-distributed samples can be corrected by dynamically adjusting the prior geometry in response to new data. Based on this insight, we propose a novel approach that dynamically updates the prior covariance matrix using real-time input features, refining its information. Specifically, we reduce the covariance along the direction of real-time input features and constrain adjustments to the residual space, thus preserving essential data characteristics and avoiding effects on unintended directions in the principal space. We evaluate our method on two pre-trained models for the CIFAR dataset and five pre-trained models for ImageNet-1k, including the self-supervised DINO model. Extensive experiments demonstrate that our approach significantly enhances OOD detection across various models. The code is released at https://github.com/workerbcd/ooddcc.
comment: Accepted by ICML25
♻ ☆ DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their ability to precisely attribute responses to specific video moments, especially under constrained supervision. We introduce DaMO, a data-efficient Video LLM explicitly designed for accurate temporal reasoning and multimodal understanding. At its core, the proposed Temporal-aware Fuseformer employs a hierarchical dual-stream architecture that progressively captures temporal dynamics within each modality and effectively fuses complementary visual and audio information. To further enhance computational efficiency, DaMO integrates a global residual that reduces spatial redundancy while preserving essential semantic details. We train DaMO via a structured four-stage progressive training paradigm, incrementally equipping the model with multimodal alignment, semantic grounding, and temporal reasoning capabilities. This work also contributes multiple datasets augmented from existing ones with GPT-generated temporally grounded QA pairs for tasks requiring temporal supervision. Comprehensive experiments on temporal grounding and video QA benchmarks demonstrate that DaMO consistently surpasses prior methods, particularly in tasks demanding precise temporal alignment and reasoning. Our work establishes a promising direction for data-efficient video-language modeling.
comment: I would like to request the withdrawal of this submission because the current version contains significant errors and incomplete results. I intend to revise the manuscript thoroughly before resubmitting. I apologize for the oversight and appreciate your understanding
♻ ☆ SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM IROS 2025
We propose SemGauss-SLAM, a dense semantic SLAM system utilizing 3D Gaussian representation, that enables accurate 3D semantic mapping, robust camera tracking, and high-quality rendering simultaneously. In this system, we incorporate semantic feature embedding into 3D Gaussian representation, which effectively encodes semantic information within the spatial layout of the environment for precise semantic scene representation. Furthermore, we propose feature-level loss for updating 3D Gaussian representation, enabling higher-level guidance for 3D Gaussian optimization. In addition, to reduce cumulative drift in tracking and improve semantic reconstruction accuracy, we introduce semantic-informed bundle adjustment. By leveraging multi-frame semantic associations, this strategy enables joint optimization of 3D Gaussian representation and camera poses, resulting in low-drift tracking and accurate semantic mapping. Our SemGauss-SLAM demonstrates superior performance over existing radiance field-based SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in high-precision semantic segmentation and dense semantic mapping.
comment: IROS 2025
♻ ☆ Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages
We developed a proof-of-concept method for the automatic analysis of the structure and content of incunabula pages. A custom dataset comprising 500 annotated pages from five different incunabula was created using resources from the Jagiellonian Digital Library. Each page was manually labeled with five predefined classes: Text, Title, Picture, Table, and Handwriting. Additionally, the publicly available DocLayNet dataset was utilized as supplementary training data. To perform object detection, YOLO11n and YOLO11s models were employed and trained using two strategies: a combined dataset (DocLayNet and the custom dataset) and the custom dataset alone. The highest performance (F1 = 0.94) was achieved by the YOLO11n model trained exclusively on the custom data. Optical character recognition was then conducted on regions classified as Text, using both Tesseract and Kraken OCR, with Tesseract demonstrating superior results. Subsequently, image classification was applied to the Picture class using a ResNet18 model, achieving an accuracy of 98.7% across five subclasses: Decorative_letter, Illustration, Other, Stamp, and Wrong_detection. Furthermore, the CLIP model was utilized to generate semantic descriptions of illustrations. The results confirm the potential of machine learning in the analysis of early printed books, while emphasizing the need for further advancements in OCR performance and visual content interpretation.
comment: 10 pages, 8 figures; submitted to TPDL 2025; change in v2: updated e-mail address
♻ ☆ Privacy Attacks on Image AutoRegressive Models ICML2025
Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation speed. However, the privacy risks associated with IARs remain unexplored, raising concerns regarding their responsible deployment. To address this gap, we conduct a comprehensive privacy analysis of IARs, comparing their privacy risks to the ones of DMs as reference points. Concretely, we develop a novel membership inference attack (MIA) that achieves a remarkably high success rate in detecting training images (with a True Positive Rate at False Positive Rate = 1% of 86.38% vs. 6.38% for DMs with comparable attacks). We leverage our novel MIA to provide dataset inference (DI) for IARs, and show that it requires as few as 6 samples to detect dataset membership (compared to 200 for DI in DMs), confirming a higher information leakage in IARs. Finally, we are able to extract hundreds of training data points from an IAR (e.g., 698 from VAR-d30). Our results suggest a fundamental privacy-utility trade-off: while IARs excel in image generation quality and speed, they are empirically significantly more vulnerable to privacy attacks compared to DMs that achieve similar performance. We release the code at https://github.com/sprintml/privacy_attacks_against_iars for reproducibility.
comment: Accepted at ICML2025
♻ ☆ PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications
Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications like smart glasses and IoT devices. We introduce PicoSAM2, a lightweight (1.3M parameters, 336M MACs) promptable segmentation model optimized for edge and in-sensor execution, including the Sony IMX500. It builds on a depthwise separable U-Net, with knowledge distillation and fixed-point prompt encoding to learn from the Segment Anything Model 2 (SAM2). On COCO and LVIS, it achieves 51.9% and 44.9% mIoU, respectively. The quantized model (1.22MB) runs at 14.3 ms on the IMX500-achieving 86 MACs/cycle, making it the only model meeting both memory and compute constraints for in-sensor deployment. Distillation boosts LVIS performance by +3.5% mIoU and +5.1% mAP. These results demonstrate that efficient, promptable segmentation is feasible directly on-camera, enabling privacy-preserving vision without cloud or host processing.
♻ ☆ Multimodal Fusion SLAM with Fourier Attention
Visual SLAM is particularly challenging in environments affected by noise, varying lighting conditions, and darkness. Learning-based optical flow algorithms can leverage multiple modalities to address these challenges, but traditional optical flow-based visual SLAM approaches often require significant computational resources.To overcome this limitation, we propose FMF-SLAM, an efficient multimodal fusion SLAM method that utilizes fast Fourier transform (FFT) to enhance the algorithm efficiency. Specifically, we introduce a novel Fourier-based self-attention and cross-attention mechanism to extract features from RGB and depth signals. We further enhance the interaction of multimodal features by incorporating multi-scale knowledge distillation across modalities. We also demonstrate the practical feasibility of FMF-SLAM in real-world scenarios with real time performance by integrating it with a security robot by fusing with a global positioning module GNSS-RTK and global Bundle Adjustment. Our approach is validated using video sequences from TUM, TartanAir, and our real-world datasets, showcasing state-of-the-art performance under noisy, varying lighting, and dark conditions.Our code and datasets are available at https://github.com/youjie-zhou/FMF-SLAM.git.
comment: Accepted in IEEE RAL
♻ ☆ Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization
High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g., species, brands) by self-supervised learning becomes a feasible solution. However, recent researches find that existing self-supervised learning methods are less qualified to represent fine-grained categories. The bottleneck lies in that the pre-text representation is built from every patch-wise embedding, while fine-grained categories are only determined by several key patches of an image. In this paper, we propose a Cross-level Multi-instance Distillation (CMD) framework to tackle the challenge. Our key idea is to consider the importance of each image patch in determining the fine-grained pre-text representation by multiple instance learning. To comprehensively learn the relation between informative patches and fine-grained semantics, the multi-instance knowledge distillation is implemented on both the region/image crop pairs from the teacher and student net, and the region-image crops inside the teacher / student net, which we term as intra-level multi-instance distillation and inter-level multi-instance distillation. Extensive experiments on CUB-200-2011, Stanford Cars and FGVC Aircraft show that the proposed method outperforms the contemporary method by upto 10.14% and existing state-of-the-art self-supervised learning approaches by upto 19.78% on both top-1 accuracy and Rank-1 retrieval metric.
comment: Accepted by IEEE Transactions on Image Processing (TIP)
♻ ☆ Exclusive Style Removal for Cross Domain Novel Class Discovery
As a promising field in open-world learning, \textit{Novel Class Discovery} (NCD) is usually a task to cluster unseen novel classes in an unlabeled set based on the prior knowledge of labeled data within the same domain. However, the performance of existing NCD methods could be severely compromised when novel classes are sampled from a different distribution with the labeled ones. In this paper, we explore and establish the solvability of NCD with cross domain setting under the necessary condition that the style information needs to be removed. Based on the theoretical analysis, we introduce an exclusive style removal module for extracting style information that is distinctive from the baseline features, thereby facilitating inference. Moreover, this module is easy to integrate with other NCD methods, acting as a plug-in to improve performance on novel classes with different distributions compared to the labeled set. Additionally, recognizing the non-negligible influence of different backbones and pre-training strategies on the performance of the NCD methods, we build a fair benchmark for future NCD research. Extensive experiments on three common datasets demonstrate the effectiveness of our proposed style removal strategy.
♻ ☆ DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy
The widespread adoption of facial recognition (FR) models raises serious concerns about their potential misuse, motivating the development of anti-facial recognition (AFR) to protect user facial privacy. In this paper, we argue that the static FR strategy, predominantly adopted in prior literature for evaluating AFR efficacy, cannot faithfully characterize the actual capabilities of determined trackers who aim to track a specific target identity. In particular, we introduce DynTracker, a dynamic FR strategy where the model's gallery database is iteratively updated with newly recognized target identity images. Surprisingly, such a simple approach renders all the existing AFR protections ineffective. To mitigate the privacy threats posed by DynTracker, we advocate for explicitly promoting diversity in the AFR-protected images. We hypothesize that the lack of diversity is the primary cause of the failure of existing AFR methods. Specifically, we develop DivTrackee, a novel method for crafting diverse AFR protections that builds upon a text-guided image generation framework and diversity-promoting adversarial losses. Through comprehensive experiments on various image benchmarks and feature extractors, we demonstrate DynTracker's strength in breaking existing AFR methods and the superiority of DivTrackee in preventing user facial images from being identified by dynamic FR strategies. We believe our work can act as an important initial step towards developing more effective AFR methods for protecting user facial privacy against determined trackers.
♻ ☆ RRCANet: Recurrent Reusable-Convolution Attention Network for Infrared Small Target Detection
Infrared small target detection is a challenging task due to its unique characteristics (e.g., small, dim, shapeless and changeable). Recently published CNN-based methods have achieved promising performance with heavy feature extraction and fusion modules. To achieve efficient and effective detection, we propose a recurrent reusable-convolution attention network (RRCA-Net) for infrared small target detection. Specifically, RRCA-Net incorporates reusable-convolution block (RuCB) in a recurrent manner without introducing extra parameters. With the help of the repetitive iteration in RuCB, the high-level information of small targets in the deep layers can be well maintained and further refined. Then, a dual interactive attention aggregation module (DIAAM) is proposed to promote the mutual enhancement and fusion of refined information. In this way, RRCA-Net can both achieve high-level feature refinement and enhance the correlation of contextual information between adjacent layers. Moreover, to achieve steady convergence, we design a target characteristic inspired loss function (DpT-k loss) by integrating physical and mathematical constraints. Experimental results on three benchmark datasets (e.g. NUAA-SIRST, IRSTD-1k, DenseSIRST) demonstrate that our RRCA-Net can achieve comparable performance to the state-of-the-art methods while maintaining a small number of parameters, and act as a plug and play module to introduce consistent performance improvement for several popular IRSTD methods. Our code will be available at https://github.com/yongxianLiu/ soon.
comment: We have corrected some annotation errors in the figures
♻ ☆ Improved and Explainable Cervical Cancer Classification using Ensemble Pooling of Block Fused Descriptors
Cervical cancer is the second most common cancer in women and causes high death rates. Earlier models for detecting cervical cancer had limited success. In this work, we propose new models that substantially outperform previous models. Previous studies show that pretrained ResNets extract features from cervical cancer images well. Hence, our first model involves working with three ResNets (50, 101, 152). All the existing works use only the last convolution block of their respective ResNet, which captures abstract features (e.g., shapes, objects). However, we believe that detailed features (e.g., color, edges, texture), coming from earlier convolution blocks, are equally important for cancer (specifically cervical cancer) classification. Since now the number of features become large, we use a novel feature selection technique of Global Max Pooling for detailed features and Global Average Pooling for abstract features. Hence, our second model consists of the resulting Cascaded Block Fused variants of the three ResNets. To improve the performance further, we combine and normalize the features of the three standard ResNets as well as our proposed three Cascaded Block Fused ResNets. This type of combination is also new in cancer classification domain (also in cervical cancer), and results in our third and fourth models, respectively. We use a linear SVM for classification. We exhaustively perform experiments on two public datasets, IARC and AnnoCerv, achieving an average performance of 97.92% and 92.97% surpassing standard ResNets performance of 90.89% and 87.97%, respectively. We outperform the competitive approach available on IARC dataset with an average gain of 13.20%, while no prior competitive work available on AnnoCerv. Additionally, we introduce a novel SHAP+LIME explainability method, accurately identifying the cancerous region in 97% of cases.
comment: 26 Pages, 10 figures, and 8 tables
♻ ☆ Controllable Video Generation with Provable Disentanglement
Controllable video generation remains a significant challenge, despite recent advances in generating high-quality and consistent videos. Most existing methods for controlling video generation treat the video as a whole, neglecting intricate fine-grained spatiotemporal relationships, which limits both control precision and efficiency. In this paper, we propose Controllable Video Generative Adversarial Networks (CoVoGAN) to disentangle the video concepts, thus facilitating efficient and independent control over individual concepts. Specifically, following the minimal change principle, we first disentangle static and dynamic latent variables. We then leverage the sufficient change property to achieve component-wise identifiability of dynamic latent variables, enabling disentangled control of video generation. To establish the theoretical foundation, we provide a rigorous analysis demonstrating the identifiability of our approach. Building on these theoretical insights, we design a Temporal Transition Module to disentangle latent dynamics. To enforce the minimal change principle and sufficient change property, we minimize the dimensionality of latent dynamic variables and impose temporal conditional independence. To validate our approach, we integrate this module as a plug-in for GANs. Extensive qualitative and quantitative experiments on various video generation benchmarks demonstrate that our method significantly improves generation quality and controllability across diverse real-world scenarios.
♻ ☆ FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs ACM MM 2024
Dynamic Facial Expression Recognition (DFER) is crucial for understanding human behavior. However, current methods exhibit limited performance mainly due to the scarcity of high-quality data, the insufficient utilization of facial dynamics, and the ambiguity of expression semantics, etc. To this end, we propose a novel framework, named Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs (FineCLIPER), incorporating the following novel designs: 1) To better distinguish between similar facial expressions, we extend the class labels to textual descriptions from both positive and negative aspects, and obtain supervision by calculating the cross-modal similarity based on the CLIP model; 2) Our FineCLIPER adopts a hierarchical manner to effectively mine useful cues from DFE videos. Specifically, besides directly embedding video frames as input (low semantic level), we propose to extract the face segmentation masks and landmarks based on each frame (middle semantic level) and utilize the Multi-modal Large Language Model (MLLM) to further generate detailed descriptions of facial changes across frames with designed prompts (high semantic level). Additionally, we also adopt Parameter-Efficient Fine-Tuning (PEFT) to enable efficient adaptation of large pre-trained models (i.e., CLIP) for this task. Our FineCLIPER achieves SOTA performance on the DFEW, FERV39k, and MAFW datasets in both supervised and zero-shot settings with few tunable parameters. Project Page: https://haroldchen19.github.io/FineCLIPER-Page/
comment: Accepted to ACM MM 2024
♻ ☆ VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos
Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such multimodal contexts, success hinges not just on perception, but on selectively identifying and integrating the right contextual details from a rich and noisy stream of content. To this end, we introduce VideoMathQA, a benchmark designed to evaluate whether models can perform such temporally extended cross-modal reasoning on videos. The benchmark spans 10 diverse mathematical domains, covering videos ranging from 10 seconds to over 1 hour. It requires models to interpret structured visual content, understand instructional narratives, and jointly ground concepts across visual, audio, and textual modalities. We employ graduate-level experts to ensure high quality, totaling over $920$ man-hours of annotation. To reflect real-world scenarios, questions are designed around three core reasoning challenges: direct problem solving, where answers are grounded in the presented question; conceptual transfer, which requires applying learned methods to new problems; and deep instructional comprehension, involving multi-step reasoning over extended explanations and partially worked-out solutions. Each question includes multi-step reasoning annotations, enabling fine-grained diagnosis of model capabilities. Through this benchmark, we highlight the limitations of existing approaches and establish a systematic evaluation framework for models that must reason, rather than merely perceive, across temporally extended and modality-rich mathematical problem settings. Our benchmark and evaluation code are available at: https://mbzuai-oryx.github.io/VideoMathQA
comment: VideoMathQA Technical Report
♻ ☆ Flopping for FLOPs: Leveraging equivariance for computational efficiency ICML 2025
Incorporating geometric invariance into neural networks enhances parameter efficiency but typically increases computational costs. This paper introduces new equivariant neural networks that preserve symmetry while maintaining a comparable number of floating-point operations (FLOPs) per parameter to standard non-equivariant networks. We focus on horizontal mirroring (flopping) invariance, common in many computer vision tasks. The main idea is to parametrize the feature spaces in terms of mirror-symmetric and mirror-antisymmetric features, i.e., irreps of the flopping group. This decomposes the linear layers to be block-diagonal, requiring half the number of FLOPs. Our approach reduces both FLOPs and wall-clock time, providing a practical solution for efficient, scalable symmetry-aware architectures.
comment: ICML 2025
♻ ☆ Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction
The proliferation of multi-source remote sensing data has propelled the development of deep learning for dense prediction, yet significant challenges in data and task unification persist. Current deep learning architectures for remote sensing are fundamentally rigid. They are engineered for fixed input-output configurations, restricting their adaptability to the heterogeneous spatial, temporal, and spectral dimensions inherent in real-world data. Furthermore, these models neglect the intrinsic correlations among semantic segmentation, binary change detection, and semantic change detection, necessitating the development of distinct models or task-specific decoders. This paradigm is also constrained to a predefined set of output semantic classes, where any change to the classes requires costly retraining. To overcome these limitations, we introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling. STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands by leveraging their metadata for a unified representation. Moreover, STSUN unifies disparate dense prediction tasks within a single architecture by conditioning the model on trainable task embeddings. Similarly, STSUN facilitates flexible prediction across any set of semantic categories by integrating trainable category embeddings as metadata. Extensive experiments on multiple datasets with diverse STS configurations in multiple scenarios demonstrate that a single STSUN model effectively adapts to heterogeneous inputs and outputs, unifying various dense prediction tasks and diverse semantic class predictions. The proposed approach consistently achieves state-of-the-art performance, highlighting its robustness and generalizability for complex remote sensing applications.
comment: 14 pages, 6 figures, Code link:https://github.com/walking-shadow/Official_TSSUN
♻ ☆ DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing
Text-guided image editing faces significant challenges when considering training and inference flexibility. Much literature collects large amounts of annotated image-text pairs to train text-conditioned generative models from scratch, which is expensive and not efficient. After that, some approaches that leverage pre-trained vision-language models have been proposed to avoid data collection, but they are limited by either per text-prompt optimization or inference-time hyper-parameters tuning. To address these issues, we investigate and identify a specific space, referred to as CLIP DeltaSpace, where the CLIP visual feature difference of two images is semantically aligned with the CLIP textual feature difference of their corresponding text descriptions. Based on DeltaSpace, we propose a novel framework called DeltaEdit, which maps the CLIP visual feature differences to the latent space directions of a generative model during the training phase, and predicts the latent space directions from the CLIP textual feature differences during the inference phase. And this design endows DeltaEdit with two advantages: (1) text-free training; (2) generalization to various text prompts for zero-shot inference. Extensive experiments validate the effectiveness and versatility of DeltaEdit with different generative models, including both the GAN model and the diffusion model, in achieving flexible text-guided image editing. Code is available at https://github.com/Yueming6568/DeltaEdit.
comment: 18 pages. arXiv admin note: text overlap with arXiv:2303.06285
♻ ☆ Dynamic PET Image Reconstruction via Non-negative INR Factorization
The reconstruction of dynamic positron emission tomography (PET) images from noisy projection data is a significant but challenging problem. In this paper, we introduce an unsupervised learning approach, Non-negative Implicit Neural Representation Factorization (\texttt{NINRF}), based on low rank matrix factorization of unknown images and employing neural networks to represent both coefficients and bases. Mathematically, we demonstrate that if a sequence of dynamic PET images satisfies a generalized non-negative low-rank property, it can be decomposed into a set of non-negative continuous functions varying in the temporal-spatial domain. This bridges the well-established non-negative matrix factorization (NMF) with continuous functions and we propose using implicit neural representations (INRs) to connect matrix with continuous functions. The neural network parameters are obtained by minimizing the KL divergence, with additional sparsity regularization on coefficients and bases. Extensive experiments on dynamic PET reconstruction with Poisson noise demonstrate the effectiveness of the proposed method compared to other methods, while giving continuous representations for object's detailed geometric features and regional concentration variation.
♻ ☆ Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers ICLR 2025
We introduce BrainSAIL, a method for linking neural selectivity with spatially distributed semantic visual concepts in natural scenes. BrainSAIL leverages recent advances in large-scale artificial neural networks, using them to provide insights into the functional topology of the brain. To overcome the challenge presented by the co-occurrence of multiple categories in natural images, BrainSAIL exploits semantically consistent, dense spatial features from pre-trained vision models, building upon their demonstrated ability to robustly predict neural activity. This method derives clean, spatially dense embeddings without requiring any additional training, and employs a novel denoising process that leverages the semantic consistency of images under random augmentations. By unifying the space of whole-image embeddings and dense visual features and then applying voxel-wise encoding models to these features, we enable the identification of specific subregions of each image which drive selectivity patterns in different areas of the higher visual cortex. This provides a powerful tool for dissecting the neural mechanisms that underlie semantic visual processing for natural images. We validate BrainSAIL on cortical regions with known category selectivity, demonstrating its ability to accurately localize and disentangle selectivity to diverse visual concepts. Next, we demonstrate BrainSAIL's ability to characterize high-level visual selectivity to scene properties and low-level visual features such as depth, luminance, and saturation, providing insights into the encoding of complex visual information. Finally, we use BrainSAIL to directly compare the feature selectivity of different brain encoding models across different regions of interest in visual cortex. Our innovative method paves the way for significant advances in mapping and decomposing high-level visual representations in the human brain.
comment: Accepted at ICLR 2025, code: https://github.com/aluo-x/BrainSAIL
♻ ☆ Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformer
Constrained by the low-rank bottleneck inherent in attention mechanisms, current stereo matching transformers suffer from limited nonlinear expressivity, which renders their feature representations sensitive to challenging conditions such as reflections. To overcome this difficulty, we present the Hadamard Attention Recurrent Stereo Transformer (HART). HART includes a novel attention mechanism that incorporates the following components: 1) The Dense Attention Kernel (DAK) maps the attention weight distribution into a high-dimensional space over (0, +$\infty$). By removing the upper bound constraint on attention weights, DAK enables more flexible modeling of complex feature interactions. This reduces feature collinearity. 2) The Multi Kernel & Order Interaction (MKOI) module extends the attention mechanism by unifying semantic and spatial knowledge learning. This integration improves the ability of HART to learn features in binocular images. Experimental results demonstrate the effectiveness of our HART. In reflective area, HART ranked 1st on the KITTI 2012 benchmark among all published methods at the time of submission. Code is available at https://github.com/ZYangChen/HART.
♻ ☆ Super-Resolution with Structured Motion
We consider the limits of super-resolution using imaging constraints. Due to various theoretical and practical limitations, reconstruction-based methods have been largely restricted to small increases in resolution. In addition, motion-blur is usually seen as a nuisance that impedes super-resolution. We show that by using high-precision motion information, sparse image priors, and convex optimization, it is possible to increase resolution by large factors. A key operation in super-resolution is deconvolution with a box. In general, convolution with a box is not invertible. However, we obtain perfect reconstructions of sparse signals using convex optimization. We also show that motion blur can be helpful for super-resolution. We demonstrate that using pseudo-random motion it is possible to reconstruct a high-resolution target using a single low-resolution image. We present numerical experiments with simulated data and results with real data captured by a camera mounted on a computer controlled stage.
♻ ☆ VesselSAM: Leveraging SAM for Aortic Vessel Segmentation with AtrousLoRA
Medical image segmentation is crucial for clinical diagnosis and treatment planning, especially when dealing with complex anatomical structures such as vessels. However, accurately segmenting vessels remains challenging due to their small size, intricate edge structures, and susceptibility to artifacts and imaging noise. In this work, we propose VesselSAM, an enhanced version of the Segment Anything Model (SAM), specifically tailored for aortic vessel segmentation. VesselSAM incorporates AtrousLoRA, a novel module integrating Atrous Attention and Low-Rank Adaptation (LoRA), to enhance segmentation performance. Atrous Attention enables the model to capture multi-scale contextual information, preserving both fine-grained local details and broader global context. Additionally, LoRA facilitates efficient fine-tuning of the frozen SAM image encoder, reducing the number of trainable parameters and thereby enhancing computational efficiency. We evaluate VesselSAM using two challenging datasets: the Aortic Vessel Tree (AVT) dataset and the Type-B Aortic Dissection (TBAD) dataset. VesselSAM achieves state-of-the-art performance, attaining DSC scores of 93.50\%, 93.25\%, 93.02\%, and 93.26\% across multi-center datasets. Our results demonstrate that VesselSAM delivers high segmentation accuracy while significantly reducing computational overhead compared to existing large-scale models. This development paves the way for enhanced AI-based aortic vessel segmentation in clinical environments. The code and models will be released at https://github.com/Adnan-CAS/AtrousLora.
comment: Work in progress
♻ ☆ LAuReL: Learned Augmented Residual Layer
One of the core pillars of efficient deep learning methods is architectural improvements such as the residual/skip connection, which has led to significantly better model convergence and quality. Since then the residual connection has become ubiquitous in not just convolutional neural networks but also transformer-based architectures, the backbone of LLMs. In this paper we introduce Learned Augmented Residual Layer (LAuReL) -- a novel generalization of the canonical residual connection -- with the goal to be an in-situ replacement of the latter while outperforming on both model quality and footprint metrics. Our experiments show that using LAuReL can help boost performance for both vision and language models. For example, on the ResNet-50, ImageNet 1K task, it achieves 60% of the gains from adding an extra layer, while only adding 0.003% more parameters, and matches it while adding 2.6 times fewer parameters. Similarly, when pre-training 1B and 4B parameter LLMs, LAuReL improves performance on a variety of challenging downstream evaluation tasks by 2.54% to 20.05%, while adding only 0.012% and 0.1% additional parameters, respectively.
comment: Accepted at 42nd International Conference on Machine Learning (2025), Vancouver, Canada
♻ ☆ Classification in Japanese Sign Language Based on Dynamic Facial Expressions
Sign language is a visual language expressed through hand movements and non-manual markers. Non-manual markers include facial expressions and head movements. These expressions vary across different nations. Therefore, specialized analysis methods for each sign language are necessary. However, research on Japanese Sign Language (JSL) recognition is limited due to a lack of datasets. The development of recognition models that consider both manual and non-manual features of JSL is crucial for precise and smooth communication with deaf individuals. In JSL, sentence types such as affirmative statements and questions are distinguished by facial expressions. In this paper, we propose a JSL recognition method that focuses on facial expressions. Our proposed method utilizes a neural network to analyze facial features and classify sentence types. Through the experiments, we confirm our method's effectiveness by achieving a classification accuracy of 96.05%.
comment: Accepted by 2024 IEEE 13th Global Conference on Consumer Electronics (GCCE 2024)
♻ ☆ SycnMapV2: Robust and Adaptive Unsupervised Segmentation
Human vision excels at segmenting visual cues without the need for explicit training, and it remains remarkably robust even as noise severity increases. In contrast, existing AI algorithms struggle to maintain accuracy under similar conditions. Here, we present SyncMapV2, the first to solve unsupervised segmentation with state-of-the-art robustness. SyncMapV2 exhibits a minimal drop in mIoU, only 0.01%, under digital corruption, compared to a 23.8% drop observed in SOTA methods. This superior performance extends across various types of corruption: noise (7.3% vs. 37.7%), weather (7.5% vs. 33.8%), and blur (7.0% vs. 29.5%). Notably, SyncMapV2 accomplishes this without any robust training, supervision, or loss functions. It is based on a learning paradigm that uses self-organizing dynamical equations combined with concepts from random networks. Moreover, unlike conventional methods that require re-initialization for each new input, SyncMapV2 adapts online, mimicking the continuous adaptability of human vision. Thus, we go beyond the accurate and robust results, and present the first algorithm that can do all the above online, adapting to input rather than re-initializing. In adaptability tests, SyncMapV2 demonstrates near-zero performance degradation, which motivates and fosters a new generation of robust and adaptive intelligence in the near future.
♻ ☆ ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis
Meteorological heatmaps play a vital role in deciphering extreme weather phenomena, yet their inherent complexities marked by irregular contours, unstructured patterns, and complex color variations present unique analytical hurdles for state-of-the-art Vision-Language Models (VLMs). Current state-of-the-art models like GPT-4o, Qwen-VL, and LLaVA 1.6 struggle with tasks such as precise color identification and spatial localization, resulting in inaccurate or incomplete interpretations. To address these challenges, we introduce Sparse Position and Outline Tracking (SPOT), a novel algorithm specifically designed to process irregularly shaped colored regions in visual data. SPOT identifies and localizes these regions by extracting their spatial coordinates, enabling structured representations of irregular shapes. Building on SPOT, we construct ClimateIQA, a novel meteorological visual question answering (VQA) dataset, comprising 26,280 high-resolution heatmaps and 762,120 instruction samples for wind gust, total precipitation, wind chill index and heat index analysis. ClimateIQA enhances VLM training by incorporating spatial cues, geographic metadata, and reanalysis data, improving model accuracy in interpreting and describing extreme weather features. Furthermore, we develop Climate-Zoo, a suite of fine-tuned VLMs based on SPOT-empowered ClimateIQA, which significantly outperforms existing models in meteorological heatmap tasks.
♻ ☆ Referring Expression Instance Retrieval and A Strong End-to-End Baseline
Natural language querying of visual content underpins many vision-language tasks, typically categorized by text granularity and visual search scope. Text-Image Retrieval (TIR) retrieves whole images using coarse descriptions, while Referring Expression Comprehension (REC) localizes objects using fine-grained expressions within a single image. However, real-world scenarios often require both instance-level retrieval and localization across large galleries -- tasks where TIR lacks precision and REC lacks scalability. To address this gap, we propose a new task: Referring Expression Instance Retrieval (REIR), which jointly supports instance-level retrieval and localization. We introduce REIRCOCO, a large-scale benchmark constructed by prompting vision-language models to generate fine-grained expressions for MSCOCO and RefCOCO instances. We also present a baseline method, CLARE, featuring a dual-stream architecture with a Mix of Relation Experts (MORE) module for capturing inter-instance relationships. CLARE integrates object detection and REC pretraining with Contrastive Language-Instance Alignment (CLIA) for end-to-end optimization. Experiments show that CLARE achieves state-of-the-art performance on REIR and generalizes well to TIR and REC, highlighting its effectiveness and versatility.
♻ ☆ Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation
Open-vocabulary segmentation aims to achieve segmentation of arbitrary categories given unlimited text inputs as guidance. To achieve this, recent works have focused on developing various technical routes to exploit the potential of large-scale pre-trained vision-language models and have made significant progress on existing benchmarks. However, we find that existing test sets are limited in measuring the models' comprehension of ``open-vocabulary" concepts, as their semantic space closely resembles the training space, even with many overlapping categories. To this end, we present a new benchmark named OpenBench that differs significantly from the training semantics. It is designed to better assess the model's ability to understand and segment a wide range of real-world concepts. When testing existing methods on OpenBench, we find that their performance diverges from the conclusions drawn on existing test sets. In addition, we propose a method named OVSNet to improve the segmentation performance for diverse and open scenarios. Through elaborate fusion of heterogeneous features and cost-free expansion of the training space, OVSNet achieves state-of-the-art results on both existing datasets and our proposed OpenBench. Corresponding analysis demonstrate the soundness and effectiveness of our proposed benchmark and method.
♻ ☆ Not All Thats Rare Is Lost: Causal Paths to Rare Concept Synthesis
Diffusion models have shown strong capabilities in high-fidelity image generation but often falter when synthesizing rare concepts, i.e., prompts that are infrequently observed in the training distribution. In this paper, we introduce RAP, a principled framework that treats rare concept generation as navigating a latent causal path: a progressive, model-aligned trajectory through the generative space from frequent concepts to rare targets. Rather than relying on heuristic prompt alternation, we theoretically justify that rare prompt guidance can be approximated by semantically related frequent prompts. We then formulate prompt switching as a dynamic process based on score similarity, enabling adaptive stage transitions. Furthermore, we reinterpret prompt alternation as a second-order denoising mechanism, promoting smooth semantic progression and coherent visual synthesis. Through this causal lens, we align input scheduling with the model's internal generative dynamics. Experiments across diverse diffusion backbones demonstrate that RAP consistently enhances rare concept generation, outperforming strong baselines in both automated evaluations and human studies.
♻ ☆ Dataset of soil images with corresponding particle size distributions for photogranulometry
Traditional particle size distribution (PSD) analyses create significant downtime and are expensive in labor and maintenance. These drawbacks could be alleviated using optical grain size analysis integrated into routine geotechnical laboratory workflow. This paper presents a high-resolution dataset of 12,714 images of 321 different soil samples collected in the Montreal, Quebec region, alongside their PSD analysis. It is designed to provide a robust starting point for training convolutional neural networks (CNN) in geotechnical applications. Soil samples were photographed in a standardized top-view position with a resolution of 45 MP and a minimum scale of 39.4 micrometers per pixel, both in their moist and dry states. A custom test bench employing 13x9 inch white aluminum trays, on which the samples are spread in a thin layer, was used. For samples exceeding a size limit, a coning and quartering method was employed for mass reduction.
comment: 8 pages, 10 figures, conference
♻ ☆ Pro-AD: Learning Comprehensive Prototypes with Prototype-based Constraint for Multi-class Unsupervised Anomaly Detection
Prototype-based reconstruction methods for unsupervised anomaly detection utilize a limited set of learnable prototypes which only aggregates insufficient normal information, resulting in undesirable reconstruction. However, increasing the number of prototypes may lead to anomalies being well reconstructed through the attention mechanism, which we refer to as the "Soft Identity Mapping" problem. In this paper, we propose Pro-AD to address these issues and fully utilize the prototypes to boost the performance of anomaly detection. Specifically, we first introduce an expanded set of learnable prototypes to provide sufficient capacity for semantic information. Then we employ a Dynamic Bidirectional Decoder which integrates the process of the normal information aggregation and the target feature reconstruction via prototypes, with the aim of allowing the prototypes to aggregate more comprehensive normal semantic information from different levels of the image features and the target feature reconstruction to not only utilize its contextual information but also dynamically leverage the learned comprehensive prototypes. Additionally, to prevent the anomalies from being well reconstructed using sufficient semantic information through the attention mechanism, Pro-AD introduces a Prototype-based Constraint that applied within the target feature reconstruction process of the decoder, which further improves the performance of our approach. Extensive experiments on multiple challenging benchmarks demonstrate that our Pro-AD achieve state-of-the-art performance, highlighting its superior robustness and practical effectiveness for Multi-class Unsupervised Anomaly Detection task.
♻ ☆ Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation IROS 2025
3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving, enabling precise scene understanding through point-wise classification. While unsupervised domain adaptation (UDA) mitigates label scarcity in PCSS, existing methods critically overlook the inherent vulnerability to real-world perturbations (e.g., snow, fog, rain) and adversarial distortions. This work first identifies two intrinsic limitations that undermine current PCSS-UDA robustness: (a) unsupervised features overlap from unaligned boundaries in shared-class regions and (b) feature structure erosion caused by domain-invariant learning that suppresses target-specific patterns. To address the proposed problems, we propose a tripartite framework consisting of: 1) a robustness evaluation model quantifying resilience against adversarial attack/corruption types through robustness metrics; 2) an invertible attention alignment module (IAAM) enabling bidirectional domain mapping while preserving discriminative structure via attention-guided overlap suppression; and 3) a contrastive memory bank with quality-aware contrastive learning that progressively refines pseudo-labels with feature quality for more discriminative representations. Extensive experiments on SynLiDAR-to-SemanticPOSS adaptation demonstrate a maximum mIoU improvement of 14.3\% under adversarial attack.
comment: This paper has been accepted to the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
♻ ☆ MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network
Since rainy weather always degrades image quality and poses significant challenges to most computer vision-based intelligent systems, image de-raining has been a hot research topic. Fortunately, in a rainy light field (LF) image, background obscured by rain streaks in one sub-view may be visible in the other sub-views, and implicit depth information and recorded 4D structural information may benefit rain streak detection and removal. However, existing LF image rain removal methods either do not fully exploit the global correlations of 4D LF data or only utilize partial sub-views, resulting in sub-optimal rain removal performance and no-equally good quality for all de-rained sub-views. In this paper, we propose an efficient network, called MDeRainNet, for rain streak removal from LF images. The proposed network adopts a multi-scale encoder-decoder architecture, which directly works on Macro-pixel images (MPIs) to improve the rain removal performance. To fully model the global correlation between the spatial and the angular information, we propose an Extended Spatial-Angular Interaction (ESAI) module to merge them, in which a simple and effective Transformer-based Spatial-Angular Interaction Attention (SAIA) block is also proposed for modeling long-range geometric correlations and making full use of the angular information. Furthermore, to improve the generalization performance of our network on real-world rainy scenes, we propose a novel semi-supervised learning framework for our MDeRainNet, which utilizes multi-level KL loss to bridge the domain gap between features of synthetic and real-world rain streaks and introduces colored-residue image guided contrastive regularization to reconstruct rain-free images. Extensive experiments conducted on synthetic and real-world LFIs demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.
comment: 14 pages, 14 figures, 4 tables
♻ ☆ FusionSAM: Visual Multi-Modal Learning with Segment Anything
Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements due to a lack of comprehensive fusion features for guidance during training. While the Segment Anything Model (SAM) allows precise control during fine-tuning through its flexible prompting encoder, its potential remains largely unexplored in the context of multimodal segmentation for natural images. In this paper, we introduce SAM into multimodal image segmentation for the first time, proposing a novel framework that combines Latent Space Token Generation (LSTG) and Fusion Mask Prompting (FMP) modules. This approach transforms the training methodology for multimodal segmentation from a traditional black-box approach to a controllable, prompt-based mechanism. Specifically, we obtain latent space features for both modalities through vector quantization and embed them into a cross-attention-based inter-domain fusion module to establish long-range dependencies between modalities. We then use these comprehensive fusion features as prompts to guide precise pixel-level segmentation. Extensive experiments on multiple public datasets demonstrate that our method significantly outperforms SAM and SAM2 in multimodal autonomous driving scenarios, achieving an average improvement of 4.1$\%$ over the state-of-the-art method in segmentation mIoU, and the performance is also optimized in other multi-modal visual scenes.
♻ ☆ MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching
Many keypoint detection and description methods have been proposed for image matching or registration. While these methods demonstrate promising performance for single-modality image matching, they often struggle with multimodal data because the descriptors trained on single-modality data tend to lack robustness against the non-linear variations present in multimodal data. Extending such methods to multimodal image matching often requires well-aligned multimodal data to learn modality-invariant descriptors. However, acquiring such data is often costly and impractical in many real-world scenarios. To address this challenge, we propose a modality-invariant feature learning network (MIFNet) to compute modality-invariant features for keypoint descriptions in multimodal image matching using only single-modality training data. Specifically, we propose a novel latent feature aggregation module and a cumulative hybrid aggregation module to enhance the base keypoint descriptors trained on single-modality data by leveraging pre-trained features from Stable Diffusion models. %, our approach generates robust and invariant features across diverse and unknown modalities. We validate our method with recent keypoint detection and description methods in three multimodal retinal image datasets (CF-FA, CF-OCT, EMA-OCTA) and two remote sensing datasets (Optical-SAR and Optical-NIR). Extensive experiments demonstrate that the proposed MIFNet is able to learn modality-invariant feature for multimodal image matching without accessing the targeted modality and has good zero-shot generalization ability. The code will be released at https://github.com/lyp-deeplearning/MIFNet.
comment: Accept by IEEE TIP 2025
♻ ☆ Object-aware Sound Source Localization via Audio-Visual Scene Understanding CVPR 2025
Audio-visual sound source localization task aims to spatially localize sound-making objects within visual scenes by integrating visual and audio cues. However, existing methods struggle with accurately localizing sound-making objects in complex scenes, particularly when visually similar silent objects coexist. This limitation arises primarily from their reliance on simple audio-visual correspondence, which does not capture fine-grained semantic differences between sound-making and silent objects. To address these challenges, we propose a novel sound source localization framework leveraging Multimodal Large Language Models (MLLMs) to generate detailed contextual information that explicitly distinguishes between sound-making foreground objects and silent background objects. To effectively integrate this detailed information, we introduce two novel loss functions: Object-aware Contrastive Alignment (OCA) loss and Object Region Isolation (ORI) loss. Extensive experimental results on MUSIC and VGGSound datasets demonstrate the effectiveness of our approach, significantly outperforming existing methods in both single-source and multi-source localization scenarios. Code and generated detailed contextual information are available at: https://github.com/VisualAIKHU/OA-SSL.
comment: Accepted at CVPR 2025
♻ ☆ A Contrastive Learning Foundation Model Based on Perfectly Aligned Sample Pairs for Remote Sensing Images
Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference. However, due to the significant domain gap, while CL methods have achieved great success in many computer vision tasks, they still require specific adaptation for Remote Sensing (RS) images. To this end, we present a novel self-supervised method called PerA, which produces all-purpose RS features through semantically Perfectly Aligned sample pairs. Specifically, PerA obtains features from sampled views by applying spatially disjoint masks to augmented images rather than random cropping. Our framework provides high-quality features by ensuring consistency between teacher and student and predicting learnable mask tokens. Compared to previous contrastive methods, our method demonstrates higher memory efficiency and can be trained with larger batches due to its sparse inputs. Additionally, the proposed method demonstrates remarkable adaptability to uncurated RS data and reduce the impact of the potential semantic inconsistency. We also collect an unlabeled pre-training dataset, which contains about 5 million RS images. We conducted experiments on multiple downstream task datasets and achieved performance comparable to previous state-of-the-art methods with a limited model scale, demonstrating the effectiveness of our approach. We hope this work will contribute to practical remote sensing interpretation works.
♻ ☆ Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models ICML 2025
The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search engines and other similar tools. In this context, this paper seeks to protect users' privacy by implementing defenses at the image compression stage to prevent exploitation. Specifically, we propose a flexible coding method, termed Privacy-Shielded Image Compression (PSIC), that can produce bitstreams with multiple decoding options. By default, the bitstream is decoded to preserve satisfactory perceptual quality while preventing interpretation by VLP models. Our method also retains the original image compression functionality. With a customizable input condition, the proposed scheme can reconstruct the image that preserves its full semantic information. A Conditional Latent Trigger Generation (CLTG) module is proposed to produce bias information based on customizable conditions to guide the decoding process into different reconstructed versions, and an Uncertainty-Aware Encryption-Oriented (UAEO) optimization function is designed to leverage the soft labels inferred from the target VLP model's uncertainty on the training data. This paper further incorporates an adaptive multi-objective optimization strategy to obtain improved encrypting performance and perceptual quality simultaneously within a unified training process. The proposed scheme is plug-and-play and can be seamlessly integrated into most existing Learned Image Compression (LIC) models. Extensive experiments across multiple downstream tasks have demonstrated the effectiveness of our design.
comment: 11 pages, 6 figures, publised to ICML 2025
♻ ☆ DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilizing an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image within the global dataset in logarithmic time. Via curriculum learning, we then dynamically re-formulate an unbiased subsample dataset for NAS optimisation, upon which the current NAS solution architecture performs poorly. We show that our DDS-NAS framework speeds up gradient-based NAS strategies by up to 27x without loss in performance. By maximising the contribution of each image sample during training, we reduce the duration of a NAS training cycle and the number of iterations required for convergence.
comment: 27 single-column pages, 8 figures, to be published in Pattern Recognition
♻ ☆ Screen Them All: High-Throughput Pan-Cancer Genetic and Phenotypic Biomarker Screening from H&E Whole Slide Images
Molecular assays are standard of care for detecting genomic alterations in cancer prognosis and therapy selection but are costly, tissue-destructive and time-consuming. Artificial intelligence (AI) applied to routine hematoxylin and eosin (H&E)-stained whole slide images (WSIs) offers a fast and economical alternative for screening molecular biomarkers. We introduce OmniScreen, a high-throughput AI-based system leveraging Virchow2 embeddings extracted from 60,529 cancer patients with paired 489-gene MSK-IMPACT targeted biomarker panel and WSIs. Unlike conventional approaches that train separate models for each biomarker, OmniScreen employs a unified model to predict a broad range of clinically relevant biomarkers across cancers, including low-prevalence targets impractical to model individually. OmniScreen reliably identifies therapeutic targets and shared phenotypic features across common and rare tumors. We investigate the biomarker prediction probabilities and accuracies of OmniScreen in relation to tumor area, cohort size, histologic subtype alignment, and pathway-level morphological patterns. These findings underscore the potential of OmniScreen for routine clinical screening.
♻ ☆ DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While data augmentation techniques have been widely adopted to enhance the resilience of a trained model against such perturbations, there remains significant room for improvement in robustness against corrupted data and adversarial attacks simultaneously. To address this challenge, we introduce DRO-Augment, a novel framework that integrates Wasserstein Distributionally Robust Optimization (W-DRO) with various data augmentation strategies to improve the robustness of the models significantly across a broad spectrum of corruptions. Our method outperforms existing augmentation methods under severe data perturbations and adversarial attack scenarios while maintaining the accuracy on the clean datasets on a range of benchmark datasets, including but not limited to CIFAR-10-C, CIFAR-100-C, MNIST, and Fashion-MNIST. On the theoretical side, we establish novel generalization error bounds for neural networks trained using a computationally efficient, variation-regularized loss function closely related to the W-DRO problem.
comment: 26 pages,3 figures
♻ ☆ From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially under accelerated acquisitions or patient motion. However, this task remains challenging due to hierarchical structural disruptions. It includes local detail loss from k-space undersampling, global structural aliasing caused by motion, and volumetric anisotropy. Therefore, we propose a progressive refinement implicit neural representation (PR-INR) framework. Our PR-INR unifies motion correction, structural refinement, and volumetric synthesis within a geometry-aware coordinate space. Specifically, a motion-aware diffusion module is first employed to generate coarse volumetric reconstructions that suppress motion artifacts and preserve global anatomical structures. Then, we introduce an implicit detail restoration module that performs residual refinement by aligning spatial coordinates with visual features. It corrects local structures and enhances boundary precision. Further, a voxel continuous-aware representation module represents the image as a continuous function over 3D coordinates. It enables accurate inter-slice completion and high-frequency detail recovery. We evaluate PR-INR on five public MRI datasets under various motion conditions (3% and 5% displacement), undersampling rates (4x and 8x) and slice resolutions (scale = 5). Experimental results demonstrate that PR-INR outperforms state-of-the-art methods in both quantitative reconstruction metrics and visual quality. It further shows generalization and robustness across diverse unseen domains.
♻ ☆ WAFFLE: Finetuning Multi-Modal Model for Automated Front-End Development
Web development involves turning UI designs into functional webpages, which can be difficult for both beginners and experienced developers due to the complexity of HTML's hierarchical structures and styles. While Large Language Models (LLMs) have shown promise in generating source code, two major challenges persist in UI-to-HTML code generation: (1) effectively representing HTML's hierarchical structure for LLMs, and (2) bridging the gap between the visual nature of UI designs and the text-based format of HTML code. To tackle these challenges, we introduce Waffle, a new fine-tuning strategy that uses a structure-aware attention mechanism to improve LLMs' understanding of HTML's structure and a contrastive fine-tuning approach to align LLMs' understanding of UI images and HTML code. Models fine-tuned with Waffle show up to 9.00 pp (percentage point) higher HTML match, 0.0982 higher CW-SSIM, 32.99 higher CLIP, and 27.12 pp higher LLEM on our new benchmark WebSight-Test and an existing benchmark Design2Code, outperforming current fine-tuning methods.
♻ ☆ MaizeField3D: A Curated 3D Point Cloud and Procedural Model Dataset of Field-Grown Maize from a Diversity Panel
The development of artificial intelligence (AI) and machine learning (ML) based tools for 3D phenotyping, especially for maize, has been limited due to the lack of large and diverse 3D datasets. 2D image datasets fail to capture essential structural details such as leaf architecture, plant volume, and spatial arrangements that 3D data provide. To address this limitation, we present MaizeField3D (https://baskargroup.github.io/MaizeField3D/), a curated dataset of 3D point clouds of field-grown maize plants from a diverse genetic panel, designed to be AI-ready for advancing agricultural research. Our dataset includes 1,045 high-quality point clouds of field-grown maize collected using a terrestrial laser scanner (TLS). Point clouds of 520 plants from this dataset were segmented and annotated using a graph-based segmentation method to isolate individual leaves and stalks, ensuring consistent labeling across all samples. This labeled data was then used for fitting procedural models that provide a structured parametric representation of the maize plants. The leaves of the maize plants in the procedural models are represented using Non-Uniform Rational B-Spline (NURBS) surfaces that were generated using a two-step optimization process combining gradient-free and gradient-based methods. We conducted rigorous manual quality control on all datasets, correcting errors in segmentation, ensuring accurate leaf ordering, and validating metadata annotations. The dataset also includes metadata detailing plant morphology and quality, alongside multi-resolution subsampled point cloud data (100k, 50k, 10k points), which can be readily used for different downstream computational tasks. MaizeField3D will serve as a comprehensive foundational dataset for AI-driven phenotyping, plant structural analysis, and 3D applications in agricultural research.
comment: Elvis Kimara and Mozhgan Hadadi contributed equally to this work
♻ ☆ Temporal Differential Fields for 4D Motion Modeling via Image-to-Video Synthesis MICCAI
Temporal modeling on regular respiration-induced motions is crucial to image-guided clinical applications. Existing methods cannot simulate temporal motions unless high-dose imaging scans including starting and ending frames exist simultaneously. However, in the preoperative data acquisition stage, the slight movement of patients may result in dynamic backgrounds between the first and last frames in a respiratory period. This additional deviation can hardly be removed by image registration, thus affecting the temporal modeling. To address that limitation, we pioneeringly simulate the regular motion process via the image-to-video (I2V) synthesis framework, which animates with the first frame to forecast future frames of a given length. Besides, to promote the temporal consistency of animated videos, we devise the Temporal Differential Diffusion Model to generate temporal differential fields, which measure the relative differential representations between adjacent frames. The prompt attention layer is devised for fine-grained differential fields, and the field augmented layer is adopted to better interact these fields with the I2V framework, promoting more accurate temporal variation of synthesized videos. Extensive results on ACDC cardiac and 4D Lung datasets reveal that our approach simulates 4D videos along the intrinsic motion trajectory, rivaling other competitive methods on perceptual similarity and temporal consistency. Codes will be available soon.
comment: early accepted by MICCAI
♻ ☆ Exploring AI-based System Design for Pixel-level Protected Health Information Detection in Medical Images
De-identification of medical images is a critical step to ensure privacy during data sharing in research and clinical settings. The initial step in this process involves detecting Protected Health Information (PHI), which can be found in image metadata or imprinted within image pixels. Despite the importance of such systems, there has been limited evaluation of existing AI-based solutions, creating barriers to the development of reliable and robust tools. In this study, we present an AI-based pipeline for PHI detection, comprising three key modules: text detection, text extraction, and text analysis. We benchmark three models - YOLOv11, EasyOCR, and GPT-4o - across different setups corresponding to these modules, evaluating their performance on two different datasets encompassing multiple imaging modalities and PHI categories. Our findings indicate that the optimal setup involves utilizing dedicated vision and language models for each module, which achieves a commendable balance in performance, latency, and cost associated with the usage of Large Language Models (LLMs). Additionally, we show that the application of LLMs not only involves identifying PHI content but also enhances OCR tasks and facilitates an end-to-end PHI detection pipeline, showcasing promising outcomes through our analysis.
comment: In progress
♻ ☆ Shape and Texture Recognition in Large Vision-Language Models
Shapes and textures are the basic building blocks of visual perception. The ability to identify shapes regardless of orientation, texture, or context, and to recognize textures and materials independently of their associated objects, is essential for a general visual understanding of the world. This work introduces the Large Shape and Textures dataset (LAS&T), a giant collection of highly diverse shapes and textures, created by unsupervised extraction of patterns from natural images. This dataset is used to benchmark how effectively leading Large Vision-Language Models (LVLMs) understand shapes, textures, and materials in 2D and 3D scenes. For shape recognition, we test the models' ability to match images of identical shapes that differ in orientation, texture, color, or environment. Our results show that the shape recognition capabilities of the LVLMs remain significantly below human performance. LVLMs rely predominantly on high-level and semantic features and struggle with abstract shapes lacking clear class associations. For texture and material recognition, we evaluated the models' ability to identify images with identical textures and materials across different objects and environments. Interestingly, leading LVLMs approach human-level performance in recognizing materials in 3D scenes, yet substantially underperform humans when identifying simpler more abstract 2D textures. These results are consistent across a wide range of leading VLMs (GPT/Gemini/LLama/Qwen) and foundation vision models (DINO/CLIP), exposing major deficiencies in the ability of leading models to understand fundamental visual concepts. In contrast, simple nets trained directly for these tasks achieve high accuracy. The LAS&T dataset, featuring over 600,000 images for 2D/3D shape, texture, and material recognition and retrieval, is publicly available.
♻ ☆ GlyphPattern: An Abstract Pattern Recognition Benchmark for Vision-Language Models
Vision-Language Models (VLMs) building upon the foundation of powerful large language models have made rapid progress in reasoning across visual and textual data. While VLMs perform well on vision tasks that they are trained on, our results highlight key challenges in abstract pattern recognition. We present GlyphPattern, a 954 item dataset that pairs 318 human-written descriptions of visual patterns from 40 writing systems with three visual presentation styles. GlyphPattern evaluates abstract pattern recognition in VLMs, requiring models to understand and judge natural language descriptions of visual patterns. GlyphPattern patterns are drawn from a large-scale cognitive science investigation of human writing systems; as a result, they are rich in spatial reference and compositionality. Our experiments show that GlyphPattern is challenging for state-of-the-art VLMs (GPT-4o achieves only 55% accuracy), with marginal gains from few-shot prompting. Our detailed error analysis reveals challenges at multiple levels, including visual processing, natural language understanding, and pattern generalization.
Multimedia 2
☆ A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects
Multi-sensor fusion perception (MSFP) is a key technology for embodied AI, which can serve a variety of downstream tasks (e.g., 3D object detection and semantic segmentation) and application scenarios (e.g., autonomous driving and swarm robotics). Recently, impressive achievements on AI-based MSFP methods have been reviewed in relevant surveys. However, we observe that the existing surveys have some limitations after a rigorous and detailed investigation. For one thing, most surveys are oriented to a single task or research field, such as 3D object detection or autonomous driving. Therefore, researchers in other related tasks often find it difficult to benefit directly. For another, most surveys only introduce MSFP from a single perspective of multi-modal fusion, while lacking consideration of the diversity of MSFP methods, such as multi-view fusion and time-series fusion. To this end, in this paper, we hope to organize MSFP research from a task-agnostic perspective, where methods are reported from various technical views. Specifically, we first introduce the background of MSFP. Next, we review multi-modal and multi-agent fusion methods. A step further, time-series fusion methods are analyzed. In the era of LLM, we also investigate multimodal LLM fusion methods. Finally, we discuss open challenges and future directions for MSFP. We hope this survey can help researchers understand the important progress in MSFP and provide possible insights for future research.
♻ ☆ ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval
E-commerce is increasingly multimedia-enriched, with products exhibited in a broad-domain manner as images, short videos, or live stream promotions. A unified and vectorized cross-domain production representation is essential. Due to large intra-product variance and high inter-product similarity in the broad-domain scenario, a visual-only representation is inadequate. While Automatic Speech Recognition (ASR) text derived from the short or live-stream videos is readily accessible, how to de-noise the excessively noisy text for multimodal representation learning is mostly untouched. We propose ASR-enhanced Multimodal Product Representation Learning (AMPere). In order to extract product-specific information from the raw ASR text, AMPere uses an easy-to-implement LLM-based ASR text summarizer. The LLM-summarized text, together with visual data, is then fed into a multi-branch network to generate compact multimodal embeddings. Extensive experiments on a large-scale tri-domain dataset verify the effectiveness of AMPere in obtaining a unified multimodal product representation that clearly improves cross-domain product retrieval.
comment: accepted for publication as a REGULAR paper in the IEEE Transactions on Multimedia
Computer Vision and Pattern Recognition 9
☆ TC-Light: Temporally Consistent Relighting for Dynamic Long Videos
Editing illumination in long videos with complex dynamics has significant value in various downstream tasks, including visual content creation and manipulation, as well as data scaling up for embodied AI through sim2real and real2real transfer. Nevertheless, existing video relighting techniques are predominantly limited to portrait videos or fall into the bottleneck of temporal consistency and computation efficiency. In this paper, we propose TC-Light, a novel paradigm characterized by the proposed two-stage post optimization mechanism. Starting from the video preliminarily relighted by an inflated video relighting model, it optimizes appearance embedding in the first stage to align global illumination. Then it optimizes the proposed canonical video representation, i.e., Unique Video Tensor (UVT), to align fine-grained texture and lighting in the second stage. To comprehensively evaluate performance, we also establish a long and highly dynamic video benchmark. Extensive experiments show that our method enables physically plausible relighting results with superior temporal coherence and low computation cost. The code and video demos are available at https://dekuliutesla.github.io/tclight/.
comment: Project Page: https://dekuliutesla.github.io/tclight/ Code: https://github.com/Linketic/TC-Light
♻ ☆ Emergent Temporal Correspondences from Video Diffusion Transformers
Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental question persists: how do these models internally establish and represent temporal correspondences across frames? We introduce DiffTrack, the first quantitative analysis framework designed to answer this question. DiffTrack constructs a dataset of prompt-generated video with pseudo ground-truth tracking annotations and proposes novel evaluation metrics to systematically analyze how each component within the full 3D attention mechanism of DiTs (e.g., representations, layers, and timesteps) contributes to establishing temporal correspondences. Our analysis reveals that query-key similarities in specific, but not all, layers play a critical role in temporal matching, and that this matching becomes increasingly prominent during the denoising process. We demonstrate practical applications of DiffTrack in zero-shot point tracking, where it achieves state-of-the-art performance compared to existing vision foundation and self-supervised video models. Further, we extend our findings to motion-enhanced video generation with a novel guidance method that improves temporal consistency of generated videos without additional training. We believe our work offers crucial insights into the inner workings of video DiTs and establishes a foundation for further research and applications leveraging their temporal understanding.
comment: Project page is available at https://cvlab-kaist.github.io/DiffTrack
♻ ☆ Multi-label Scene Classification for Autonomous Vehicles: Acquiring and Accumulating Knowledge from Diverse Datasets
Driving scene identification, which assigns multiple non-exclusive class labels to a scene, provides the contextual awareness necessary for enhancing autonomous vehicles' ability to understand, reason about, and interact with the complex driving environment. As a multi-label classification problem, it is better tackled via multitasking learning. However, directly training a multi-label classification model for driving scene identification through multitask learning presents two main challenges: acquiring a balanced, comprehensively annotated multi-label dataset and balancing learning across different tasks. This paper introduces a novel learning system that synergizes knowledge acquisition and accumulation (KAA) with consistency-based active learning (CAL) to address those challenges. KAA acquires and accumulates knowledge about scene identification from various single-label datasets via monotask learning. Subsequently, CAL effectively resolves the knowledge gap caused by the discrepancy between single-label and multi-label data. An ablation study on our Driving Scene Identification (DSI) dataset demonstrates a 56.1% performance increase over the baseline model pretrained on ImageNet. Of this, KAA accounts for 31.3% of the gain, and CAL contributes 24.8%. Moreover, KAA-CAL stands out as the best performer when compared to state-of-the-art (SOTA) multi-label models on two public datasets, BDD100K and HSD, achieving this while using 85% less data. The DSI dataset and the implementation code for KAA-CAL are available at https://github.com/KELISBU/KAA-CAL .
♻ ☆ EmoAgent: A Multi-Agent Framework for Diverse Affective Image Manipulation
Affective Image Manipulation (AIM) aims to alter visual elements within an image to evoke specific emotional responses from viewers. However, existing AIM approaches rely on rigid \emph{one-to-one} mappings between emotions and visual cues, making them ill-suited for the inherently subjective and diverse ways in which humans perceive and express emotion.To address this, we introduce a novel task setting termed \emph{Diverse AIM (D-AIM)}, aiming to generate multiple visually distinct yet emotionally consistent image edits from a single source image and target emotion. We propose \emph{EmoAgent}, the first multi-agent framework tailored specifically for D-AIM. EmoAgent explicitly decomposes the manipulation process into three specialized phases executed by collaborative agents: a Planning Agent that generates diverse emotional editing strategies, an Editing Agent that precisely executes these strategies, and a Critic Agent that iteratively refines the results to ensure emotional accuracy. This collaborative design empowers EmoAgent to model \emph{one-to-many} emotion-to-visual mappings, enabling semantically diverse and emotionally faithful edits.Extensive quantitative and qualitative evaluations demonstrate that EmoAgent substantially outperforms state-of-the-art approaches in both emotional fidelity and semantic diversity, effectively generating multiple distinct visual edits that convey the same target emotion.
♻ ☆ RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought
Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both low-fidelity and unnatural. We present RealSR-R1 in this work, which empowers the RealSR models with understanding and reasoning capabilities. Inspired by the success of Chain of Thought (CoT) in large language models (LLMs), we simulate the human process of handling degraded images and propose the VLCoT framework, which integrates vision and language reasoning. The framework aims to precisely restore image details by progressively generating more comprehensive text and higher-resolution images. To overcome the challenge of traditional supervised learning CoT failing to generalize to real-world scenarios, we introduce, for the first time, Group Relative Policy Optimization (GRPO) into the Real-World Image Super-Resolution task. We propose VLCoT-GRPO as a solution, which designs four reward functions: (1) Format reward, used to standardize the CoT process; (2) Degradation reward, to incentivize accurate degradation estimation; (3) Understanding reward, to ensure the accuracy of the generated content; and (4) Generation reward, where we propose using a visual expert model to evaluate the quality of generated images, encouraging the model to generate more realistic images. Extensive experiments demonstrate that our proposed RealSR-R1 can generate realistic details and accurately understand image content, particularly in semantically rich scenes or images with severe degradation.
♻ ☆ TextBraTS: Text-Guided Volumetric Brain Tumor Segmentation with Innovative Dataset Development and Fusion Module Exploration
Deep learning has demonstrated remarkable success in medical image segmentation and computer-aided diagnosis. In particular, numerous advanced methods have achieved state-of-the-art performance in brain tumor segmentation from MRI scans. While recent studies in other medical imaging domains have revealed that integrating textual reports with visual data can enhance segmentation accuracy, the field of brain tumor analysis lacks a comprehensive dataset that combines radiological images with corresponding textual annotations. This limitation has hindered the exploration of multimodal approaches that leverage both imaging and textual data. To bridge this critical gap, we introduce the TextBraTS dataset, the first publicly available volume-level multimodal dataset that contains paired MRI volumes and rich textual annotations, derived from the widely adopted BraTS2020 benchmark. Building upon this novel dataset, we propose a novel baseline framework and sequential cross-attention method for text-guided volumetric medical image segmentation. Through extensive experiments with various text-image fusion strategies and templated text formulations, our approach demonstrates significant improvements in brain tumor segmentation accuracy, offering valuable insights into effective multimodal integration techniques. Our dataset, implementation code, and pre-trained models are publicly available at https://github.com/Jupitern52/TextBraTS.
♻ ☆ A Prior-Guided Joint Diffusion Model in Projection Domain for PET Tracer Conversion
Positron emission tomography (PET) is widely used to assess metabolic activity, but its application is limited by the availability of radiotracers. 18F-labeled fluorodeoxyglucose (18F-FDG) is the most commonly used tracer but shows limited effectiveness for certain tumors. In contrast, 6-18F-fluoro-3,4-dihydroxy-L-phenylalanine (18F-DOPA) offers higher specificity for neuroendocrine tumors and neurological disorders. However, the complexity of its synthesis process and constraints on transportation time have limited its clinical application. Among different forms of raw data acquired by the scanner, sinogram is a commonly used representation in PET imaging. Therefore, modeling in projection domain enables more direct utilization of the original information, potentially reducing the accumulation errors during the image reconstruction process. Inspired by these factors, this study proposes a prior-guided joint diffusion model (PJDM) for transforming 18F-FDG PET sinograms into 18F-DOPA PET sinograms. During inference, an initial synthetic 18F-DOPA PET sinogram is first generated using a higher-order hybrid sampler. This sinogram is then degraded and serves as an additional condition to guide the iterative refinement process. Experimental results demonstrated that PJDM effectively improved both sinogram quality and the final synthetic outcomes. The code is available at: https://github.com/yqx7150/PJDM.
♻ ☆ A Comparative Analysis of Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) as Dimensionality Reduction Techniques
High-dimensional image data often require dimensionality reduction before further analysis. This paper provides a purely analytical comparison of two linear techniques-Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). After the derivation of each algorithm from first principles, we assess their interpretability, numerical stability, and suitability for differing matrix shapes. building on classical and recent numerical literature, We synthesize rule-of-thumb guidelines for choosing one out of the two algorithms without empirical benchmarking, building on classical and recent numerical literature. Limitations and directions for future experimental work are outlined at the end.
♻ ☆ An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection
The brain is a highly complex organ that manages many important tasks, including movement, memory and thinking. Brain-related conditions, like tumors and degenerative disorders, can be hard to diagnose and treat. Magnetic Resonance Imaging (MRI) serves as a key tool for identifying these conditions, offering high-resolution images of brain structures. Despite this, interpreting MRI scans can be complicated. This study tackles this challenge by conducting a comparative analysis of Vision Transformer (ViT) and Transfer Learning (TL) models such as VGG16, VGG19, Resnet50V2, MobilenetV2 for classifying brain diseases using MRI data from Bangladesh based dataset. ViT, known for their ability to capture global relationships in images, are particularly effective for medical imaging tasks. Transfer learning helps to mitigate data constraints by fine-tuning pre-trained models. Furthermore, Explainable AI (XAI) methods such as GradCAM, GradCAM++, LayerCAM, ScoreCAM, and Faster-ScoreCAM are employed to interpret model predictions. The results demonstrate that ViT surpasses transfer learning models, achieving a classification accuracy of 94.39%. The integration of XAI methods enhances model transparency, offering crucial insights to aid medical professionals in diagnosing brain diseases with greater precision.
comment: Accepted for publication in 2024 27th International Conference on Computer and Information Technology (ICCIT)
Information Retrieval 15
☆ An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify KDD 2025
Spotify, a large-scale multimedia platform, attracts over 675 million monthly active users who collectively consume millions of hours of music, podcasts, audiobooks, and video content. This diverse content consumption pattern introduces unique challenges for computational advertising, which must effectively integrate a variety of ad modalities, including audio, video, and display, within a single user experience. Traditional ad recommendation models, primarily designed for foregrounded experiences, often struggle to reconcile the platform's inherent audio-centrality with the demands of optimizing ad performance across multiple formats and modalities. To overcome these challenges, we introduce Cross-modal Adaptive Mixture-of-Experts (CAMoE), a novel framework for optimizing click-through rate (CTR) prediction in both audio-centric and multi-modal settings. CAMoE enhances traditional mixture-of-experts models by incorporating modality-aware task grouping, adaptive loss masking, and deep-cross networks (DCN) to capture complex feature interactions within a multi-modal ad ecosystem. Through extensive ablation studies, we demonstrate that this approach achieves near Pareto-optimal performance across audio, video, and display ad formats, significantly improving AUC-PR compared to conventional single-task and content-based multi-task learning baselines. When deployed at scale on Spotify's ad serving platform, CAMoE delivered substantial gains, yielding a 14.5% increase in CTR for audio ads, a 1.3% increase for video ads, and a 4.8% reduction in expected cost-per-click (eCPC) for audio slots.
comment: Accepted at KDD 2025
☆ Harnessing the Power of Reinforcement Learning for Language-Model-Based Information Retriever via Query-Document Co-Augmentation
Recent studies have proposed leveraging Large Language Models (LLMs) as information retrievers through query rewriting. However, for challenging corpora, we argue that enhancing queries alone is insufficient for robust semantic matching; the LLM should also have sufficient understanding of the corpus by directly handling and augmenting the documents themselves. To this end, we present an LLM-based retriever empowered to augment both user queries and corpus documents, with its policy fully explored via reinforcement learning (RL) and minimal human inductive bias. Notably, we find that simply allowing the LLM to modify documents yields little benefit unless paired with our carefully designed bidirectional RL framework, which enables the LLM to simultaneously learn and collaborate on both query and document augmentation policies. A key technical challenge in realizing such a framework lies in jointly updating both policies during training, where the rewards for the two directions depend on each other, making their entangled reward intractable. Our approach addresses this by introducing a reward sampling strategy and a specifically designed RL algorithm that enables effective training with these sampled rewards. Experimental results demonstrate that our approach significantly enhances LLM-based retrieval performance in both sparse and dense settings, particularly in difficult retrieval domains, and achieves strong cross-benchmark generalization. Our code is released at https://github.com/liujm2001/CoAugRetriever.
☆ Rethinking Click Models in Light of Carousel Interfaces: Theory-Based Categorization and Design of Click Models ICTIR 2025
Click models are a well-established for modeling user interactions with web interfaces. Previous work has mainly focused on traditional single-list web search settings; this includes existing surveys that introduced categorizations based on the first generation of probabilistic graphical model (PGM) click models that have become standard. However, these categorizations have become outdated, as their conceptualizations are unable to meaningfully compare PGM with neural network (NN) click models nor generalize to newer interfaces, such as carousel interfaces. We argue that this outdated view fails to adequately explain the fundamentals of click model designs, thus hindering the development of novel click models. This work reconsiders what should be the fundamental concepts in click model design, grounding them - unlike previous approaches - in their mathematical properties. We propose three fundamental key-design choices that explain what statistical patterns a click model can capture, and thus indirectly, what user behaviors they can capture. Based on these choices, we create a novel click model taxonomy that allows a meaningful comparison of all existing click models; this is the first taxonomy of single-list, grid and carousel click models that includes PGMs and NNs. Finally, we show how our conceptualization provides a foundation for future click model design by an example derivation of a novel design for carousel interfaces.
comment: Accepted by ICTIR 2025
☆ When Fine-Tuning Fails: Lessons from MS MARCO Passage Ranking
This paper investigates the counterintuitive phenomenon where fine-tuning pre-trained transformer models degrades performance on the MS MARCO passage ranking task. Through comprehensive experiments involving five model variants-including full parameter fine-tuning and parameter efficient LoRA adaptations-we demonstrate that all fine-tuning approaches underperform the base sentence-transformers/all- MiniLM-L6-v2 model (MRR@10: 0.3026). Our analysis reveals that fine-tuning disrupts the optimal embedding space structure learned during the base model's extensive pre-training on 1 billion sentence pairs, including 9.1 million MS MARCO samples. UMAP visualizations show progressive embedding space flattening, while training dynamics analysis and computational efficiency metrics further support our findings. These results challenge conventional wisdom about transfer learning effectiveness on saturated benchmarks and suggest architectural innovations may be necessary for meaningful improvements.
☆ PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching KDD 2025
With the expansion of business scales and scopes on online platforms, multi-scenario matching has become a mainstream solution to reduce maintenance costs and alleviate data sparsity. The key to effective multi-scenario recommendation lies in capturing both user preferences shared across all scenarios and scenario-aware preferences specific to each scenario. However, existing methods often overlook user-specific modeling, limiting the generation of personalized user representations. To address this, we propose PERSCEN, an innovative approach that incorporates user-specific modeling into multi-scenario matching. PERSCEN constructs a user-specific feature graph based on user characteristics and employs a lightweight graph neural network to capture higher-order interaction patterns, enabling personalized extraction of preferences shared across scenarios. Additionally, we leverage vector quantization techniques to distil scenario-aware preferences from users' behavior sequence within individual scenarios, facilitating user-specific and scenario-aware preference modeling. To enhance efficient and flexible information transfer, we introduce a progressive scenario-aware gated linear unit that allows fine-grained, low-latency fusion. Extensive experiments demonstrate that PERSCEN outperforms existing methods. Further efficiency analysis confirms that PERSCEN effectively balances performance with computational cost, ensuring its practicality for real-world industrial systems.
comment: Accepted by KDD 2025
☆ Bias vs Bias -- Dawn of Justice: A Fair Fight in Recommendation Systems
Recommendation systems play a crucial role in our daily lives by impacting user experience across various domains, including e-commerce, job advertisements, entertainment, etc. Given the vital role of such systems in our lives, practitioners must ensure they do not produce unfair and imbalanced recommendations. Previous work addressing bias in recommendations overlooked bias in certain item categories, potentially leaving some biases unaddressed. Additionally, most previous work on fair re-ranking focused on binary-sensitive attributes. In this paper, we address these issues by proposing a fairness-aware re-ranking approach that helps mitigate bias in different categories of items. This re-ranking approach leverages existing biases to correct disparities in recommendations across various demographic groups. We show how our approach can mitigate bias on multiple sensitive attributes, including gender, age, and occupation. We experimented on three real-world datasets to evaluate the effectiveness of our re-ranking scheme in mitigating bias in recommendations. Our results show how this approach helps mitigate social bias with little to no degradation in performance.
☆ Team LA at SCIDOCA shared task 2025: Citation Discovery via relation-based zero-shot retrieval SC
The Citation Discovery Shared Task focuses on predicting the correct citation from a given candidate pool for a given paragraph. The main challenges stem from the length of the abstract paragraphs and the high similarity among candidate abstracts, making it difficult to determine the exact paper to cite. To address this, we develop a system that first retrieves the top-k most similar abstracts based on extracted relational features from the given paragraph. From this subset, we leverage a Large Language Model (LLM) to accurately identify the most relevant citation. We evaluate our framework on the training dataset provided by the SCIDOCA 2025 organizers, demonstrating its effectiveness in citation prediction.
comment: In the Proceedings of SCIDOCA 2025
☆ Enhancing Document Retrieval in COVID-19 Research: Leveraging Large Language Models for Hidden Relation Extraction SC
In recent years, with the appearance of the COVID-19 pandemic, numerous publications relevant to this disease have been issued. Because of the massive volume of publications, an efficient retrieval system is necessary to provide researchers with useful information if an unexpected pandemic happens so suddenly, like COVID-19. In this work, we present a method to help the retrieval system, the Covrelex-SE system, to provide more high-quality search results. We exploited the power of the large language models (LLMs) to extract the hidden relationships inside the unlabeled publication that cannot be found by the current parsing tools that the system is using. Since then, help the system to have more useful information during retrieval progress.
comment: In the Proceedings of SCIDOCA 2024
☆ LettinGo: Explore User Profile Generation for Recommendation System
User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations. While traditional embedding-based profiles lack interpretability and adaptability, recent advances with large language models (LLMs) enable text-based profiles that are semantically richer and more transparent. However, existing methods often adhere to fixed formats that limit their ability to capture the full diversity of user behaviors. In this paper, we introduce LettinGo, a novel framework for generating diverse and adaptive user profiles. By leveraging the expressive power of LLMs and incorporating direct feedback from downstream recommendation tasks, our approach avoids the rigid constraints imposed by supervised fine-tuning (SFT). Instead, we employ Direct Preference Optimization (DPO) to align the profile generator with task-specific performance, ensuring that the profiles remain adaptive and effective. LettinGo operates in three stages: (1) exploring diverse user profiles via multiple LLMs, (2) evaluating profile quality based on their impact in recommendation systems, and (3) aligning the profile generation through pairwise preference data derived from task performance. Experimental results demonstrate that our framework significantly enhances recommendation accuracy, flexibility, and contextual awareness. This work enhances profile generation as a key innovation for next-generation recommendation systems.
comment: 11 pages, 3 figures
☆ Comparative Analysis of Lion and AdamW Optimizers for Cross-Encoder Reranking with MiniLM, GTE, and ModernBERT
Modern information retrieval systems often employ a two-stage pipeline: an efficient initial retrieval stage followed by a computationally intensive reranking stage. Cross-encoders have shown strong effectiveness for reranking due to their deep analysis of query-document pairs. This paper studies the impact of the Lion optimizer, a recent alternative to AdamW, during fine-tuning of cross-encoder rerankers. We fine-tune three transformer models-MiniLM, GTE, and ModernBERT-on the MS MARCO passage ranking dataset using both optimizers. GTE and ModernBERT support extended context lengths (up to 8192 tokens). We evaluate effectiveness using TREC 2019 Deep Learning Track and MS MARCO dev set (MRR@10). Experiments, run on the Modal cloud platform, reveal that ModernBERT with Lion achieves the best NDCG@10 (0.7225) and MAP (0.5121) on TREC DL 2019, while MiniLM with Lion ties ModernBERT for MRR@10 (0.5988) on MS MARCO dev. Lion also provides superior GPU efficiency, improving utilization by 2.67% to 10.33% across models. We analyze performance trends using standard IR metrics and discuss the optimizer's impact on training dynamics across architectures.
☆ From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.
♻ ☆ Affordable AI Assistants with Knowledge Graph of Thoughts
Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains. However, current state-of-the-art LLM-driven agents face significant challenges, including high operational costs and limited success rates on complex benchmarks like GAIA. To address these issues, we propose Knowledge Graph of Thoughts (KGoT), an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs). KGoT extracts and structures task-relevant knowledge into a dynamic KG representation, iteratively enhanced through external tools such as math solvers, web crawlers, and Python scripts. Such structured representation of task-relevant knowledge enables low-cost models to solve complex tasks effectively while also minimizing bias and noise. For example, KGoT achieves a 29% improvement in task success rates on the GAIA benchmark compared to Hugging Face Agents with GPT-4o mini. Moreover, harnessing a smaller model dramatically reduces operational costs by over 36x compared to GPT-4o. Improvements for other models (e.g., Qwen2.5-32B and Deepseek-R1-70B) and benchmarks (e.g., SimpleQA) are similar. KGoT offers a scalable, affordable, versatile, and high-performing solution for AI assistants.
♻ ☆ C-SEO Bench: Does Conversational SEO Work?
Large Language Models (LLMs) are transforming search engines into Conversational Search Engines (CSE). Consequently, Search Engine Optimization (SEO) is being shifted into Conversational Search Engine Optimization (C-SEO). We are beginning to see dedicated C-SEO methods for modifying web documents to increase their visibility in CSE responses. However, they are often tested only for a limited breadth of application domains; we do not understand whether certain C-SEO methods would be effective for a broad range of domains. Moreover, existing evaluations consider only a single-actor scenario where only one web document adopts a C-SEO method; in reality, multiple players are likely to competitively adopt the cutting-edge C-SEO techniques, drawing an analogy from the dynamics we have seen in SEO. We present C-SEO Bench, the first benchmark designed to evaluate C-SEO methods across multiple tasks, domains, and number of actors. We consider two search tasks, question answering and product recommendation, with three domains each. We also formalize a new evaluation protocol with varying adoption rates among involved actors. Our experiments reveal that most current C-SEO methods are largely ineffective, contrary to reported results in the literature. Instead, traditional SEO strategies, those aiming to improve the ranking of the source in the LLM context, are significantly more effective. We also observe that as we increase the number of C-SEO adopters, the overall gains decrease, depicting a congested and zero-sum nature of the problem. Our code and data are available at https://github.com/parameterlab/c-seo-bench and https://huggingface.co/datasets/parameterlab/c-seo-bench.
♻ ☆ AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articles
Recent advancements in generative AI have fostered the development of highly adept Large Language Models (LLMs) that integrate diverse data types to empower decision-making. Among these, multimodal retrieval-augmented generation (RAG) applications are promising because they combine the strengths of information retrieval and generative models, enhancing their utility across various domains, including clinical use cases. This paper introduces AlzheimerRAG, a Multimodal RAG application for clinical use cases, primarily focusing on Alzheimer's Disease case studies from PubMed articles. This application incorporates cross-modal attention fusion techniques to integrate textual and visual data processing by efficiently indexing and accessing vast amounts of biomedical literature. Our experimental results, compared to benchmarks such as BioASQ and PubMedQA, have yielded improved performance in the retrieval and synthesis of domain-specific information. We also present a case study using our multimodal RAG in various Alzheimer's clinical scenarios. We infer that AlzheimerRAG can generate responses with accuracy non-inferior to humans and with low rates of hallucination.
♻ ☆ Personalized News Recommendation with Multi-granularity Candidate-aware User Modeling
Matching candidate news with user interests is crucial for personalized news recommendations. Most existing methods can represent a user's reading interests through a single profile based on clicked news, which may not fully capture the diversity of user interests. Although some approaches incorporate candidate news or topic information, they remain insufficient because they neglect the multi-granularity relatedness between candidate news and user interests. To address this, this study proposed a multi-granularity candidate-aware user modeling framework that integrated user interest features across various levels of granularity. It consisted of two main components: candidate news encoding and user modeling. A news textual information extractor and a knowledge-enhanced entity information extractor can capture candidate news features, and word-level, entity-level, and news-level candidate-aware mechanisms can provide a comprehensive representation of user interests. Extensive experiments on a real-world dataset demonstrated that the proposed model could significantly outperform baseline models.
Multimedia 7
☆ Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary. By integrating vision and text into a unified space with an expanded vocabulary, our multimodal LLM, Tar, enables cross-modal input and output through a shared interface, without the need for modality-specific designs. Additionally, we propose scale-adaptive encoding and decoding to balance efficiency and visual detail, along with a generative de-tokenizer to produce high-fidelity visual outputs. To address diverse decoding needs, we utilize two complementary de-tokenizers: a fast autoregressive model and a diffusion-based model. To enhance modality fusion, we investigate advanced pre-training tasks, demonstrating improvements in both visual understanding and generation. Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency. Code, models, and data are available at https://tar.csuhan.com
comment: Project page: https://tar.csuhan.com
☆ Let Your Video Listen to Your Music!
Aligning the rhythm of visual motion in a video with a given music track is a practical need in multimedia production, yet remains an underexplored task in autonomous video editing. Effective alignment between motion and musical beats enhances viewer engagement and visual appeal, particularly in music videos, promotional content, and cinematic editing. Existing methods typically depend on labor-intensive manual cutting, speed adjustments, or heuristic-based editing techniques to achieve synchronization. While some generative models handle joint video and music generation, they often entangle the two modalities, limiting flexibility in aligning video to music beats while preserving the full visual content. In this paper, we propose a novel and efficient framework, termed MVAA (Music-Video Auto-Alignment), that automatically edits video to align with the rhythm of a given music track while preserving the original visual content. To enhance flexibility, we modularize the task into a two-step process in our MVAA: aligning motion keyframes with audio beats, followed by rhythm-aware video inpainting. Specifically, we first insert keyframes at timestamps aligned with musical beats, then use a frame-conditioned diffusion model to generate coherent intermediate frames, preserving the original video's semantic content. Since comprehensive test-time training can be time-consuming, we adopt a two-stage strategy: pretraining the inpainting module on a small video set to learn general motion priors, followed by rapid inference-time fine-tuning for video-specific adaptation. This hybrid approach enables adaptation within 10 minutes with one epoch on a single NVIDIA 4090 GPU using CogVideoX-5b-I2V as the backbone. Extensive experiments show that our approach can achieve high-quality beat alignment and visual smoothness.
comment: project page: https://zhangxinyu-xyz.github.io/MVAA/
☆ OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation
Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animations with natural synchronization and fluidity. They also struggle with precise prompt control for fine-grained generation. To tackle these challenges, we introduce OmniAvatar, an innovative audio-driven full-body video generation model that enhances human animation with improved lip-sync accuracy and natural movements. OmniAvatar introduces a pixel-wise multi-hierarchical audio embedding strategy to better capture audio features in the latent space, enhancing lip-syncing across diverse scenes. To preserve the capability for prompt-driven control of foundation models while effectively incorporating audio features, we employ a LoRA-based training approach. Extensive experiments show that OmniAvatar surpasses existing models in both facial and semi-body video generation, offering precise text-based control for creating videos in various domains, such as podcasts, human interactions, dynamic scenes, and singing. Our project page is https://omni-avatar.github.io/.
comment: Project page: https://omni-avatar.github.io/
☆ NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI -- the first standard for end-to-end neural image compression (NIC) methods -- the question of evaluating NIC robustness has become critically significant. However, previous research has been limited to a narrow range of codecs and attacks. To address this, we present \textbf{NIC-RobustBench}, the first open-source framework to evaluate NIC robustness and adversarial defenses' efficiency, in addition to comparing Rate-Distortion (RD) performance. The framework includes the largest number of codecs among all known NIC libraries and is easily scalable. The paper demonstrates a comprehensive overview of the NIC-RobustBench framework and employs it to analyze NIC robustness. Our code is available online at https://github.com/msu-video-group/NIC-RobustBench.
comment: arXiv admin note: text overlap with arXiv:2411.11795
♻ ☆ TextBraTS: Text-Guided Volumetric Brain Tumor Segmentation with Innovative Dataset Development and Fusion Module Exploration
Deep learning has demonstrated remarkable success in medical image segmentation and computer-aided diagnosis. In particular, numerous advanced methods have achieved state-of-the-art performance in brain tumor segmentation from MRI scans. While recent studies in other medical imaging domains have revealed that integrating textual reports with visual data can enhance segmentation accuracy, the field of brain tumor analysis lacks a comprehensive dataset that combines radiological images with corresponding textual annotations. This limitation has hindered the exploration of multimodal approaches that leverage both imaging and textual data. To bridge this critical gap, we introduce the TextBraTS dataset, the first publicly available volume-level multimodal dataset that contains paired MRI volumes and rich textual annotations, derived from the widely adopted BraTS2020 benchmark. Building upon this novel dataset, we propose a novel baseline framework and sequential cross-attention method for text-guided volumetric medical image segmentation. Through extensive experiments with various text-image fusion strategies and templated text formulations, our approach demonstrates significant improvements in brain tumor segmentation accuracy, offering valuable insights into effective multimodal integration techniques. Our dataset, implementation code, and pre-trained models are publicly available at https://github.com/Jupitern52/TextBraTS.
♻ ☆ SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement NeurIPS2025
Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance global coherence with local fidelity, resulting in outputs that lack musicality or suffer from incoherent progression and mismatched lyrics. This paper introduces $\textbf{SongBloom}$, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms. Audio samples are available on our demo page: https://cypress-yang.github.io/SongBloom_demo. The code and model weights have been released on https://github.com/Cypress-Yang/SongBloom .
comment: Submitted to NeurIPS2025
♻ ☆ LAPIG: Language Guided Projector Image Generation with Surface Adaptation and Stylization
We propose LAPIG, a language guided projector image generation method with surface adaptation and stylization. LAPIG consists of a projector-camera system and a target textured projection surface. LAPIG takes the user text prompt as input and aims to transform the surface style using the projector. LAPIG's key challenge is that due to the projector's physical brightness limitation and the surface texture, the viewer's perceived projection may suffer from color saturation and artifacts in both dark and bright regions, such that even with the state-of-the-art projector compensation techniques, the viewer may see clear surface texture-related artifacts. Therefore, how to generate a projector image that follows the user's instruction while also displaying minimum surface artifacts is an open problem. To address this issue, we propose projection surface adaptation (PSA) that can generate compensable surface stylization. We first train two networks to simulate the projector compensation and project-and-capture processes, this allows us to find a satisfactory projector image without real project-and-capture and utilize gradient descent for fast convergence. Then, we design content and saturation losses to guide the projector image generation, such that the generated image shows no clearly perceivable artifacts when projected. Finally, the generated image is projected for visually pleasing surface style morphing effects. The source code and video are available on the project page: https://Yu-chen-Deng.github.io/LAPIG/.
comment: 12 pages, 9 figures
Information Retrieval 8
☆ LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation
Cross-Domain Sequential Recommendation (CDSR) predicts user behavior by leveraging historical interactions across multiple domains, focusing on modeling cross-domain preferences and capturing both intra- and inter-sequence item relationships. We propose LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation (LLM-EMF), a novel and advanced approach that enhances textual information with Large Language Models (LLM) knowledge and significantly improves recommendation performance through the fusion of visual and textual data. Using the frozen CLIP model, we generate image and text embeddings, thereby enriching item representations with multimodal data. A multiple attention mechanism jointly learns both single-domain and cross-domain preferences, effectively capturing and understanding complex user interests across diverse domains. Evaluations conducted on four e-commerce datasets demonstrate that LLM-EMF consistently outperforms existing methods in modeling cross-domain user preferences, thereby highlighting the effectiveness of multimodal data integration and its advantages in enhancing sequential recommendation systems. Our source code will be released.
comment: arXiv admin note: substantial text overlap with arXiv:2504.15085
☆ A GenAI System for Improved FAIR Independent Biological Database Integration
Life sciences research increasingly requires identifying, accessing, and effectively processing data from an ever-evolving array of information sources on the Linked Open Data (LOD) network. This dynamic landscape places a significant burden on researchers, as the quality of query responses depends heavily on the selection and semantic integration of data sources --processes that are often labor-intensive, error-prone, and costly. While the adoption of FAIR (Findable, Accessible, Interoperable, and Reusable) data principles has aimed to address these challenges, barriers to efficient and accurate scientific data processing persist. In this paper, we introduce FAIRBridge, an experimental natural language-based query processing system designed to empower scientists to discover, access, and query biological databases, even when they are not FAIR-compliant. FAIRBridge harnesses the capabilities of AI to interpret query intents, map them to relevant databases described in scientific literature, and generate executable queries via intelligent resource access plans. The system also includes robust tools for mitigating low-quality query processing, ensuring high fidelity and responsiveness in the information delivered. FAIRBridge's autonomous query processing framework enables users to explore alternative data sources, make informed choices at every step, and leverage community-driven crowd curation when needed. By providing a user-friendly, automated hypothesis-testing platform in natural English, FAIRBridge significantly enhances the integration and processing of scientific data, offering researchers a powerful new tool for advancing their inquiries.
♻ ☆ DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation
Generative recommendation is emerging as a powerful paradigm that directly generates item predictions, moving beyond traditional matching-based approaches. However, current methods face two key challenges: token-item misalignment, where uniform token-level modeling ignores item-level granularity that is critical for collaborative signal learning, and semantic-collaborative signal entanglement, where collaborative and semantic signals exhibit distinct distributions yet are fused in a unified embedding space, leading to conflicting optimization objectives that limit the recommendation performance. To address these issues, we propose DiscRec, a novel framework that enables Disentangled Semantic-Collaborative signal modeling with flexible fusion for generative Recommendation. First, DiscRec introduces item-level position embeddings, assigned based on indices within each semantic ID, enabling explicit modeling of item structure in input token sequences. Second, DiscRec employs a dual-branch module to disentangle the two signals at the embedding layer: a semantic branch encodes semantic signals using original token embeddings, while a collaborative branch applies localized attention restricted to tokens within the same item to effectively capture collaborative signals. A gating mechanism subsequently fuses both branches while preserving the model's ability to model sequential dependencies. Extensive experiments on four real-world datasets demonstrate that DiscRec effectively decouples these signals and consistently outperforms state-of-the-art baselines. Our codes are available on https://github.com/Ten-Mao/DiscRec.
comment: Fixed the indentation issue in the abstract that caused rendering errors on arXiv
♻ ☆ BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning
Software bugs require developers to exert significant effort to identify and resolve them, often consuming about one-third of their time. Bug localization, the process of pinpointing the exact source code files that need modification, is crucial in reducing this effort. Existing bug localization tools, typically reliant on deep learning techniques, face limitations in cross-project applicability and effectiveness in multi-language environments. Recent advancements with Large Language Models (LLMs) offer detailed representations for bug localization. However, they encounter challenges with limited context windows and mapping accuracy. To address these issues, we propose BLAZE, an approach that employs dynamic chunking and hard example learning. First, BLAZE dynamically segments source code to minimize continuity loss. Then, BLAZE fine-tunes a GPT-based model using challenging bug cases, in order to enhance cross-project and cross-language bug localization. To support the capability of BLAZE, we create the BEETLEBOX dataset, which comprises 26,321 bugs from 29 large and thriving open-source projects across five different programming languages (Java, C++, Python, Go, and JavaScript). Our evaluations of BLAZE on three benchmark datasets BEETLEBOX, SWE-Bench, and Ye et al. demonstrate substantial improvements compared to six state-of-the-art baselines. Specifically, BLAZE achieves up to an increase of 120% in Top 1 accuracy, 144% in Mean Average Precision (MAP), and 100% in Mean Reciprocal Rank (MRR). An extensive ablation study confirms the contributions of our pipeline components to the overall performance enhancement.
♻ ☆ Leveraging Foundation Models for Content-Based Image Retrieval in Radiology
Content-based image retrieval (CBIR) has the potential to significantly improve diagnostic aid and medical research in radiology. However, current CBIR systems face limitations due to their specialization to certain pathologies, limiting their utility. On the other hand, several vision foundation models have been shown to produce general-purpose visual features. Therefore, in this work, we propose using vision foundation models as powerful and versatile off-the-shelf feature extractors for content-based image retrieval. Our contributions include: (1) benchmarking a diverse set of vision foundation models on an extensive dataset comprising 1.6 million 2D radiological images across four modalities and 161 pathologies; (2) identifying weakly-supervised models, particularly BiomedCLIP, as highly effective, achieving a achieving a P@1 of up to 0.594 (P@3: 0.590, P@5: 0.588, P@10: 0.583), comparable to specialized CBIR systems but without additional training; (3) conducting an in-depth analysis of the impact of index size on retrieval performance; (4) evaluating the quality of embedding spaces generated by different models; and (5) investigating specific challenges associated with retrieving anatomical versus pathological structures. Despite these challenges, our research underscores the vast potential of foundation models for CBIR in radiology, proposing a shift towards versatile, general-purpose medical image retrieval systems that do not require specific tuning. Our code, dataset splits and embeddings are publicly available under https://github.com/MIC-DKFZ/foundation-models-for-cbmir.
♻ ☆ GeAR: Graph-enhanced Agent for Retrieval-augmented Generation ACL 2025
Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers inherently struggle with multi-hop retrieval scenarios. In this paper, we introduce GeAR, a system that advances RAG performance through two key innovations: (i) an efficient graph expansion mechanism that augments any conventional base retriever, such as BM25, and (ii) an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework. Our evaluation demonstrates GeAR's superior retrieval capabilities across three multi-hop question answering datasets. Notably, our system achieves state-of-the-art results with improvements exceeding 10% on the challenging MuSiQue dataset, while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems. The project page is available at https://gear-rag.github.io.
comment: ACL 2025 Findings
♻ ☆ LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference
Large Language Models (LLMs)-based hybrid retrieval uses LLMs to encode queries and documents into low-dimensional dense or high-dimensional sparse vectors. It retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query encoder. Although LLMs significantly enhance retrieval capabilities, serving deeply parameterized LLMs slows down query inference throughput and increases demands for online deployment resources. In this paper, we propose LightRetriever, a novel LLM-based hybrid retriever with extremely lightweight query encoders. Our method retains a full-sized LLM for document encoding, but reduces the workload of query encoding to no more than an embedding lookup. Compared to serving a full-sized LLM on an H800 GPU, our approach achieves over a 1000x speedup for query inference with GPU acceleration, and even a 20x speedup without GPU. Experiments on large-scale retrieval benchmarks demonstrate that our method generalizes well across diverse retrieval tasks, retaining an average of 95% full-sized performance.
♻ ☆ Text2Struct: A Machine Learning Pipeline for Mining Structured Data from Text
Many analysis and prediction tasks require the extraction of structured data from unstructured texts. However, an annotation scheme and a training dataset have not been available for training machine learning models to mine structured data from text without special templates and patterns. To solve it, this paper presents an end-to-end machine learning pipeline, Text2Struct, including a text annotation scheme, training data processing, and machine learning implementation. We formulated the mining problem as the extraction of metrics and units associated with numerals in the text. Text2Struct was trained and evaluated using an annotated text dataset collected from abstracts of medical publications regarding thrombectomy. In terms of prediction performance, a dice coefficient of 0.82 was achieved on the test dataset. By random sampling, most predicted relations between numerals and entities were well matched to the ground-truth annotations. These results show that Text2Struct is viable for the mining of structured data from text without special templates or patterns. It is anticipated to further improve the pipeline by expanding the dataset and investigating other machine learning models. A code demonstration can be found at: https://github.com/zcc861007/Text2Struct
Multimedia 5
☆ Face-Voice Association for Audiovisual Active Speaker Detection in Egocentric Recordings
Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, however, the efficacy of synchronisation-based methods is compromised by occlusions, motion blur, and adverse acoustic conditions. In this work, a novel framework is proposed that exclusively leverages cross-modal face-voice associations to determine speaker activity. An existing face-voice association model is integrated with a transformer-based encoder that aggregates facial identity information by dynamically weighting each frame based on its visual quality. This system is then coupled with a front-end utterance segmentation method, producing a complete ASD system. This work demonstrates that the proposed system, Self-Lifting for audiovisual active speaker detection(SL-ASD), achieves performance comparable to, and in certain cases exceeding, that of parameter-intensive synchronisation-based approaches with significantly fewer learnable parameters, thereby validating the feasibility of substituting strict audiovisual synchronisation modelling with flexible biometric associations in challenging egocentric scenarios.
comment: Accepted to EUSIPCO 2025. 5 pages, 1 figure. To appear in the Proceedings of the 33rd European Signal Processing Conference (EUSIPCO), September 8-12, 2025, Palermo, Italy
Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster MICCAI 2025
With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tokens for medical image segmentation tasks. Specifically, we propose a simple hybrid structure that integrates a pre-trained, frozen LLM layer within the CNN encoder-decoder segmentation framework (LLM4Seg). Surprisingly, this design improves segmentation performance with a minimal increase in trainable parameters across various modalities, including ultrasound, dermoscopy, polypscopy, and CT scans. Our in-depth analysis reveals the potential of transferring LLM's semantic awareness to enhance segmentation tasks, offering both improved global understanding and better local modeling capabilities. The improvement proves robust across different LLMs, validated using LLaMA and DeepSeek.
comment: Accepted by MICCAI 2025. Code: https://github.com/FengheTan9/LLM4Seg
☆ On the Robustness of Human-Object Interaction Detection against Distribution Shift
Human-Object Interaction (HOI) detection has seen substantial advances in recent years. However, existing works focus on the standard setting with ideal images and natural distribution, far from practical scenarios with inevitable distribution shifts. This hampers the practical applicability of HOI detection. In this work, we investigate this issue by benchmarking, analyzing, and enhancing the robustness of HOI detection models under various distribution shifts. We start by proposing a novel automated approach to create the first robustness evaluation benchmark for HOI detection. Subsequently, we evaluate more than 40 existing HOI detection models on this benchmark, showing their insufficiency, analyzing the features of different frameworks, and discussing how the robustness in HOI is different from other tasks. With the insights from such analyses, we propose to improve the robustness of HOI detection methods through: (1) a cross-domain data augmentation integrated with mixup, and (2) a feature fusion strategy with frozen vision foundation models. Both are simple, plug-and-play, and applicable to various methods. Our experimental results demonstrate that the proposed approach significantly increases the robustness of various methods, with benefits on standard benchmarks, too. The dataset and code will be released.
comment: This work has been submitted to the IEEE for possible publication
☆ PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis
Recent advances in large language models (LLMs) have enabled breakthroughs in many multimodal generation tasks, but a significant performance gap still exists in text-to-motion generation, where LLM-based methods lag far behind non-LLM methods. We identify the granularity of motion tokenization as a critical bottleneck: fine-grained tokenization induces local dependency issues, where LLMs overemphasize short-term coherence at the expense of global semantic alignment, while coarse-grained tokenization sacrifices motion details. To resolve this issue, we propose PlanMoGPT, an LLM-based framework integrating progressive planning and flow-enhanced fine-grained motion tokenization. First, our progressive planning mechanism leverages LLMs' autoregressive capabilities to hierarchically generate motion tokens by starting from sparse global plans and iteratively refining them into full sequences. Second, our flow-enhanced tokenizer doubles the downsampling resolution and expands the codebook size by eight times, minimizing detail loss during discretization, while a flow-enhanced decoder recovers motion nuances. Extensive experiments on text-to-motion benchmarks demonstrate that it achieves state-of-the-art performance, improving FID scores by 63.8% (from 0.380 to 0.141) on long-sequence generation while enhancing motion diversity by 49.9% compared to existing methods. The proposed framework successfully resolves the diversity-quality trade-off that plagues current non-LLM approaches, establishing new standards for text-to-motion generation.
comment: 14 pages, 7 figures
♻ ☆ SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation MICCAI 2025
Surgical video generation can enhance medical education and research, but existing methods lack fine-grained motion control and realism. We introduce SurgSora, a framework that generates high-fidelity, motion-controllable surgical videos from a single input frame and user-specified motion cues. Unlike prior approaches that treat objects indiscriminately or rely on ground-truth segmentation masks, SurgSora leverages self-predicted object features and depth information to refine RGB appearance and optical flow for precise video synthesis. It consists of three key modules: (1) the Dual Semantic Injector, which extracts object-specific RGB-D features and segmentation cues to enhance spatial representations; (2) the Decoupled Flow Mapper, which fuses multi-scale optical flow with semantic features for realistic motion dynamics; and (3) the Trajectory Controller, which estimates sparse optical flow and enables user-guided object movement. By conditioning these enriched features within the Stable Video Diffusion, SurgSora achieves state-of-the-art visual authenticity and controllability in advancing surgical video synthesis, as demonstrated by extensive quantitative and qualitative comparisons. Our human evaluation in collaboration with expert surgeons further demonstrates the high realism of SurgSora-generated videos, highlighting the potential of our method for surgical training and education. Our project is available at https://surgsora.github.io/surgsora.github.io.
comment: MICCAI 2025
Information Retrieval 7
☆ Expanding Relevance Judgments for Medical Case-based Retrieval Task with Multimodal LLMs SIGIR 2025
Evaluating Information Retrieval (IR) systems relies on high-quality manual relevance judgments (qrels), which are costly and time-consuming to obtain. While pooling reduces the annotation effort, it results in only partially labeled datasets. Large Language Models (LLMs) offer a promising alternative to reducing reliance on manual judgments, particularly in complex domains like medical case-based retrieval, where relevance assessment requires analyzing both textual and visual information. In this work, we explore using a Multimodal Large Language Model (MLLM) to expand relevance judgments, creating a new dataset of automated judgments. Specifically, we employ Gemini 1.5 Pro on the ImageCLEFmed 2013 case-based retrieval task, simulating human assessment through an iteratively refined, structured prompting strategy that integrates binary scoring, instruction-based evaluation, and few-shot learning. We systematically experimented with various prompt configurations to maximize agreement with human judgments. To evaluate agreement between the MLLM and human judgments, we use Cohen's Kappa, achieving a substantial agreement score of 0.6, comparable to inter-annotator agreement typically observed in multimodal retrieval tasks. Starting from the original 15,028 manual judgments (4.72% relevant) across 35 topics, our MLLM-based approach expanded the dataset by over 37x to 558,653 judgments, increasing relevant annotations to 5,950. On average, each medical case query received 15,398 new annotations, with approximately 99% being non-relevant, reflecting the high sparsity typical in this domain. Our results demonstrate the potential of MLLMs to scale relevance judgment collection, offering a promising direction for supporting retrieval evaluation in medical and multimodal IR tasks.
comment: To appear at the Third Workshop on Large Language Models for Evaluation in Information Retrieval (LLM4Eval 2025), co-located with SIGIR 2025. 9 pages, 2 figures, 5 tables
☆ CARTS: Collaborative Agents for Recommendation Textual Summarization
Current recommendation systems often require some form of textual data summarization, such as generating concise and coherent titles for product carousels or other grouped item displays. While large language models have shown promise in NLP domains for textual summarization, these approaches do not directly apply to recommendation systems, where explanations must be highly relevant to the core features of item sets, adhere to strict word limit constraints. In this paper, we propose CARTS (Collaborative Agents for Recommendation Textual Summarization), a multi-agent LLM framework designed for structured summarization in recommendation systems. CARTS decomposes the task into three stages-Generation Augmented Generation (GAG), refinement circle, and arbitration, where successive agent roles are responsible for extracting salient item features, iteratively refining candidate titles based on relevance and length feedback, and selecting the final title through a collaborative arbitration process. Experiments on large-scale e-commerce data and live A/B testing show that CARTS significantly outperforms single-pass and chain-of-thought LLM baselines, delivering higher title relevance and improved user engagement metrics.
☆ Reinforcing User Interest Evolution in Multi-Scenario Learning for recommender systems
In real-world recommendation systems, users would engage in variety scenarios, such as homepages, search pages, and related recommendation pages. Each of these scenarios would reflect different aspects users focus on. However, the user interests may be inconsistent in different scenarios, due to differences in decision-making processes and preference expression. This variability complicates unified modeling, making multi-scenario learning a significant challenge. To address this, we propose a novel reinforcement learning approach that models user preferences across scenarios by modeling user interest evolution across multiple scenarios. Our method employs Double Q-learning to enhance next-item prediction accuracy and optimizes contrastive learning loss using Q-value to make model performance better. Experimental results demonstrate that our approach surpasses state-of-the-art methods in multi-scenario recommendation tasks. Our work offers a fresh perspective on multi-scenario modeling and highlights promising directions for future research.
☆ A novel fast short-time root music method for vibration monitoring of high-speed spindles
Ultra-high-speed spindle bearings challenge traditional vibration monitoring due to broadband noise, non-stationarity, and limited time-frequency resolution. We present a fast Short-Time Root-MUSIC (fSTrM) algorithm that exploits FFT-accelerated Lanczos bidiagonalization to reduce computational complexity from $\mathcal{O}(N^3)$ to $SN\log_2N+S^2(N+S)+M^2(N+M)$ while preserving parametric super-resolution. The method constructs Hankel matrices from 16 ms signal frames and extracts fault frequencies through polynomial rooting on the unit circle. Experimental validation on the Politecnico di Torino bearing dataset demonstrates breakthrough micro-defect detection capabilities. The algorithm reliably identifies 150 $\mu$m defects -- previously undetectable by conventional methods -- providing 72+ hours additional warning time. Compared to STFT and wavelet methods, fSTrM achieves 1.2 Hz frequency resolution (vs. 12.5 Hz), 93\% detection rate at $-$5 dB SNR, and quantifies defect severity through harmonic content analysis. Critically, the algorithm processes each frame in 2.4 ms on embedded ARM Cortex-M7 hardware, enabling real-time deployment. This advancement transforms bearing monitoring from failure prevention to continuous degradation assessment, establishing a new paradigm for predictive maintenance in aerospace and precision machining.
☆ Context-Aware Scientific Knowledge Extraction on Linked Open Data using Large Language Models
The exponential growth of scientific literature challenges researchers extracting and synthesizing knowledge. Traditional search engines return many sources without direct, detailed answers, while general-purpose LLMs may offer concise responses that lack depth or omit current information. LLMs with search capabilities are also limited by context window, yielding short, incomplete answers. This paper introduces WISE (Workflow for Intelligent Scientific Knowledge Extraction), a system addressing these limits by using a structured workflow to extract, refine, and rank query-specific knowledge. WISE uses an LLM-powered, tree-based architecture to refine data, focusing on query-aligned, context-aware, and non-redundant information. Dynamic scoring and ranking prioritize unique contributions from each source, and adaptive stopping criteria minimize processing overhead. WISE delivers detailed, organized answers by systematically exploring and synthesizing knowledge from diverse sources. Experiments on HBB gene-associated diseases demonstrate WISE reduces processed text by over 80% while achieving significantly higher recall over baselines like search engines and other LLM-based approaches. ROUGE and BLEU metrics reveal WISE's output is more unique than other systems, and a novel level-based metric shows it provides more in-depth information. We also explore how the WISE workflow can be adapted for diverse domains like drug discovery, material science, and social science, enabling efficient knowledge extraction and synthesis from unstructured scientific papers and web sources.
♻ ☆ Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5
Given the large number of Hindi speakers worldwide, there is a pressing need for robust and efficient information retrieval systems for Hindi. Despite ongoing research, comprehensive benchmarks for evaluating retrieval models in Hindi are lacking. To address this gap, we introduce the Hindi-BEIR benchmark, comprising 15 datasets across seven distinct tasks. We evaluate state-of-the-art multilingual retrieval models on the Hindi-BEIR benchmark, identifying task and domain-specific challenges that impact Hindi retrieval performance. Building on the insights from these results, we introduce NLLB-E5, a multilingual retrieval model that leverages a zero-shot approach to support Hindi without the need for Hindi training data. We believe our contributions, which include the release of the Hindi-BEIR benchmark and the NLLB-E5 model, will prove to be a valuable resource for researchers and promote advancements in multilingual retrieval models.
comment: arXiv admin note: substantial text overlap with arXiv:2408.09437
♻ ☆ LaPuda: LLM-Enabled Policy-Based Query Optimizer for Multi-modal Data PAKDD 2025
Large language model (LLM) has marked a pivotal moment in the field of machine learning and deep learning. Recently its capability for query planning has been investigated, including both single-modal and multi-modal queries. However, there is no work on the query optimization capability of LLM. As a critical (or could even be the most important) step that significantly impacts the execution performance of the query plan, such analysis and attempts should not be missed. From another aspect, existing query optimizers are usually rule-based or rule-based + cost-based, i.e., they are dependent on manually created rules to complete the query plan rewrite/transformation. Given the fact that modern optimizers include hundreds to thousands of rules, designing a multi-modal query optimizer following a similar way is significantly time-consuming since we will have to enumerate as many multi-modal optimization rules as possible, which has not been well addressed today. In this paper, we investigate the query optimization ability of LLM and use LLM to design LaPuda, a novel LLM and Policy based multi-modal query optimizer. Instead of enumerating specific and detailed rules, LaPuda only needs a few abstract policies to guide LLM in the optimization, by which much time and human effort are saved. Furthermore, to prevent LLM from making mistakes or negative optimization, we borrow the idea of gradient descent and propose a guided cost descent (GCD) algorithm to perform the optimization, such that the optimization can be kept in the correct direction. In our evaluation, our methods consistently outperform the baselines in most cases. For example, the optimized plans generated by our methods result in 1~3x higher execution speed than those by the baselines.
comment: Yifan and Haodi contributed equally to the work, accepted by PAKDD 2025
Multimedia 2
☆ Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
We present Programmable-Room, a framework which interactively generates and edits a 3D room mesh, given natural language instructions. For precise control of a room's each attribute, we decompose the challenging task into simpler steps such as creating plausible 3D coordinates for room meshes, generating panorama images for the texture, constructing 3D meshes by integrating the coordinates and panorama texture images, and arranging furniture. To support the various decomposed tasks with a unified framework, we incorporate visual programming (VP). VP is a method that utilizes a large language model (LLM) to write a Python-like program which is an ordered list of necessary modules for the various tasks given in natural language. We develop most of the modules. Especially, for the texture generating module, we utilize a pretrained large-scale diffusion model to generate panorama images conditioned on text and visual prompts (i.e., layout, depth, and semantic map) simultaneously. Specifically, we enhance the panorama image generation quality by optimizing the training objective with a 1D representation of a panorama scene obtained from bidirectional LSTM. We demonstrate Programmable-Room's flexibility in generating and editing 3D room meshes, and prove our framework's superiority to an existing model quantitatively and qualitatively. Project page is available in https://jihyun0510.github.io/Programmable_Room_Page/.
comment: Accepted by IEEE Transactions on Multimedia
☆ Can Generated Images Serve as a Viable Modality for Text-Centric Multimodal Learning?
A significant ``modality gap" exists between the abundance of text-only data and the increasing power of multimodal models. This work systematically investigates whether images generated on-the-fly by Text-to-Image (T2I) models can serve as a valuable complementary modality for text-centric tasks. Through a comprehensive evaluation framework on text classification, we analyze the impact of critical variables, including T2I model quality, prompt engineering strategies, and multimodal fusion architectures. Our findings demonstrate that this``synthetic perception" can yield significant performance gains, even when augmenting strong large language model baselines. However, we find the effectiveness of this approach is highly conditional, depending critically on the semantic alignment between text and the generated image, the inherent ``visual groundability" of the task, and the generative fidelity of the T2I model. Our work establishes the first rigorous benchmark for this paradigm, providing a clear analysis of its potential and current limitations, and demonstrating its viability as a pathway to enrich language understanding in traditionally unimodal scenarios.
comment: 4 figures,7 tables
Computer Vision and Pattern Recognition 111
☆ VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning
Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions. Current language model-based navigation systems operate on discrete topological graphs, limiting path planning to predefined node connections. We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions, adopting GRPO-based training inspired by DeepSeek-R1. To enable effective training, we first construct the VLN-Ego dataset using a 3D simulator, Habitat, and propose Long-Short Memory Sampling to balance historical and current observations. While large language models can supervise complete textual instructions, they lack fine-grained action-level control. Our framework employs a two-stage training approach: a) Supervised fine-tuning (SFT) to align the model's action sequence text predictions with expert demonstrations, followed by b) Reinforcement fine-tuning (RFT) enhanced with a Time-Decayed Reward (TDR) mechanism that strategically weights multi-step future actions. Experimental results show VLN-R1 achieves strong performance on VLN-CE benchmark. VLN-R1 proves LVLMs can drive embodied navigation and enhance task-specific reasoning through data-efficient, reward-driven post-training.
comment: project page: www.vlnr1.github.io
☆ Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render explicit images, but the heavy image-generation pre-training often hinders the reasoning ability. Inspired by the way humans reason with mental imagery-the internal construction and manipulation of visual cues-we investigate whether VLMs can reason through interleaved multimodal trajectories without producing explicit images. To this end, we present a Machine Mental Imagery framework, dubbed as Mirage, which augments VLM decoding with latent visual tokens alongside ordinary text. Concretely, whenever the model chooses to ``think visually'', it recasts its hidden states as next tokens, thereby continuing a multimodal trajectory without generating pixel-level images. Begin by supervising the latent tokens through distillation from ground-truth image embeddings, we then switch to text-only supervision to make the latent trajectory align tightly with the task objective. A subsequent reinforcement learning stage further enhances the multimodal reasoning capability. Experiments on diverse benchmarks demonstrate that Mirage unlocks stronger multimodal reasoning without explicit image generation.
comment: Project page: https://vlm-mirage.github.io/
☆ Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation
An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. The code and model of InfGen will be released at https://orangesodahub.github.io/InfGen
comment: Preprint. Project page: https://orangesodahub.github.io/InfGen Code: https://github.com/OrangeSodahub/infgen
☆ Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
Articulated objects are common in the real world, yet modeling their structure and motion remains a challenging task for 3D reconstruction methods. In this work, we introduce Part$^{2}$GS, a novel framework for modeling articulated digital twins of multi-part objects with high-fidelity geometry and physically consistent articulation. Part$^{2}$GS leverages a part-aware 3D Gaussian representation that encodes articulated components with learnable attributes, enabling structured, disentangled transformations that preserve high-fidelity geometry. To ensure physically consistent motion, we propose a motion-aware canonical representation guided by physics-based constraints, including contact enforcement, velocity consistency, and vector-field alignment. Furthermore, we introduce a field of repel points to prevent part collisions and maintain stable articulation paths, significantly improving motion coherence over baselines. Extensive evaluations on both synthetic and real-world datasets show that Part$^{2}$GS consistently outperforms state-of-the-art methods by up to 10$\times$ in Chamfer Distance for movable parts.
☆ DreamCube: 3D Panorama Generation via Multi-plane Synchronization
3D panorama synthesis is a promising yet challenging task that demands high-quality and diverse visual appearance and geometry of the generated omnidirectional content. Existing methods leverage rich image priors from pre-trained 2D foundation models to circumvent the scarcity of 3D panoramic data, but the incompatibility between 3D panoramas and 2D single views limits their effectiveness. In this work, we demonstrate that by applying multi-plane synchronization to the operators from 2D foundation models, their capabilities can be seamlessly extended to the omnidirectional domain. Based on this design, we further introduce DreamCube, a multi-plane RGB-D diffusion model for 3D panorama generation, which maximizes the reuse of 2D foundation model priors to achieve diverse appearances and accurate geometry while maintaining multi-view consistency. Extensive experiments demonstrate the effectiveness of our approach in panoramic image generation, panoramic depth estimation, and 3D scene generation.
comment: Project page: https://yukun-huang.github.io/DreamCube/
☆ UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work, we start by analyzing the modality alignment behaviors of task-specific expert models for understanding and generation, as well as current unified models. Our analysis reveals a crucial observation: understanding tasks benefit from a progressively increasing modality alignment across network depth, which helps build up semantic information for better comprehension; In contrast, generation tasks follow a different trend: modality alignment increases in the early layers but decreases in the deep layers to recover spatial details. These divergent alignment patterns create a fundamental conflict in fully shared Transformer backbones, where a uniform representational flow often leads to performance compromises across two tasks. Motivated by this finding, we introduce UniFork, a novel Y-shaped architecture that shares the shallow layers for cross-task representation learning, while employing task-specific branches in deeper layers to avoid task interference. This design effectively balances shared learning and task specialization. Through extensive ablation experiments, we demonstrate that Unifork consistently outperforms conventional fully shared Transformer architectures, and achieves performance on par with or better than task-specific models.
comment: Code: https://github.com/tliby/UniFork
☆ Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
Recent advances in diffusion-based and controllable video generation have enabled high-quality and temporally coherent video synthesis, laying the groundwork for immersive interactive gaming experiences. However, current methods face limitations in dynamics, generality, long-term consistency, and efficiency, which limit the ability to create various gameplay videos. To address these gaps, we introduce Hunyuan-GameCraft, a novel framework for high-dynamic interactive video generation in game environments. To achieve fine-grained action control, we unify standard keyboard and mouse inputs into a shared camera representation space, facilitating smooth interpolation between various camera and movement operations. Then we propose a hybrid history-conditioned training strategy that extends video sequences autoregressively while preserving game scene information. Additionally, to enhance inference efficiency and playability, we achieve model distillation to reduce computational overhead while maintaining consistency across long temporal sequences, making it suitable for real-time deployment in complex interactive environments. The model is trained on a large-scale dataset comprising over one million gameplay recordings across over 100 AAA games, ensuring broad coverage and diversity, then fine-tuned on a carefully annotated synthetic dataset to enhance precision and control. The curated game scene data significantly improves the visual fidelity, realism and action controllability. Extensive experiments demonstrate that Hunyuan-GameCraft significantly outperforms existing models, advancing the realism and playability of interactive game video generation.
comment: Project page: https://hunyuan-gamecraft.github.io/
☆ Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
Generating large-scale demonstrations for dexterous hand manipulation remains challenging, and several approaches have been proposed in recent years to address this. Among them, generative models have emerged as a promising paradigm, enabling the efficient creation of diverse and physically plausible demonstrations. In this paper, we introduce Dex1B, a large-scale, diverse, and high-quality demonstration dataset produced with generative models. The dataset contains one billion demonstrations for two fundamental tasks: grasping and articulation. To construct it, we propose a generative model that integrates geometric constraints to improve feasibility and applies additional conditions to enhance diversity. We validate the model on both established and newly introduced simulation benchmarks, where it significantly outperforms prior state-of-the-art methods. Furthermore, we demonstrate its effectiveness and robustness through real-world robot experiments. Our project page is at https://jianglongye.com/dex1b
comment: Accepted to RSS 2025. Project page: https://jianglongye.com/dex1b
☆ Facial Landmark Visualization and Emotion Recognition Through Neural Networks
Emotion recognition from facial images is a crucial task in human-computer interaction, enabling machines to learn human emotions through facial expressions. Previous studies have shown that facial images can be used to train deep learning models; however, most of these studies do not include a through dataset analysis. Visualizing facial landmarks can be challenging when extracting meaningful dataset insights; to address this issue, we propose facial landmark box plots, a visualization technique designed to identify outliers in facial datasets. Additionally, we compare two sets of facial landmark features: (i) the landmarks' absolute positions and (ii) their displacements from a neutral expression to the peak of an emotional expression. Our results indicate that a neural network achieves better performance than a random forest classifier.
comment: Best paper Award COMIA 2025
☆ YASMOT: Yet another stereo image multi-object tracker
There now exists many popular object detectors based on deep learning that can analyze images and extract locations and class labels for occurrences of objects. For image time series (i.e., video or sequences of stills), tracking objects over time and preserving object identity can help to improve object detection performance, and is necessary for many downstream tasks, including classifying and predicting behaviors, and estimating total abundances. Here we present yasmot, a lightweight and flexible object tracker that can process the output from popular object detectors and track objects over time from either monoscopic or stereoscopic camera configurations. In addition, it includes functionality to generate consensus detections from ensembles of object detectors.
comment: 5 pages
☆ Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Generative Adversarial Networks (GAN) have shown potential in expanding limited medical imaging datasets. This study explores how different ratios of GAN-generated and real brain tumor MRI images impact the performance of a CNN in classifying healthy vs. tumorous scans. A DCGAN was used to create synthetic images which were mixed with real ones at various ratios to train a custom CNN. The CNN was then evaluated on a separate real-world test set. Our results indicate that the model maintains high sensitivity and precision in tumor classification, even when trained predominantly on synthetic data. When only a small portion of GAN data was added, such as 900 real images and 100 GAN images, the model achieved excellent performance, with test accuracy reaching 95.2%, and precision, recall, and F1-score all exceeding 95%. However, as the proportion of GAN images increased further, performance gradually declined. This study suggests that while GANs are useful for augmenting limited datasets especially when real data is scarce, too much synthetic data can introduce artifacts that affect the model's ability to generalize to real world cases.
comment: This papaer has been submitted to The 18th International Conference on Brain Informatics (BI'25), Italy
☆ Co-Seg++: Mutual Prompt-Guided Collaborative Learning for Versatile Medical Segmentation
Medical image analysis is critical yet challenged by the need of jointly segmenting organs or tissues, and numerous instances for anatomical structures and tumor microenvironment analysis. Existing studies typically formulated different segmentation tasks in isolation, which overlooks the fundamental interdependencies between these tasks, leading to suboptimal segmentation performance and insufficient medical image understanding. To address this issue, we propose a Co-Seg++ framework for versatile medical segmentation. Specifically, we introduce a novel co-segmentation paradigm, allowing semantic and instance segmentation tasks to mutually enhance each other. We first devise a spatio-temporal prompt encoder (STP-Encoder) to capture long-range spatial and temporal relationships between segmentation regions and image embeddings as prior spatial constraints. Moreover, we devise a multi-task collaborative decoder (MTC-Decoder) that leverages cross-guidance to strengthen the contextual consistency of both tasks, jointly computing semantic and instance segmentation masks. Extensive experiments on diverse CT and histopathology datasets demonstrate that the proposed Co-Seg++ outperforms state-of-the-arts in the semantic, instance, and panoptic segmentation of dental anatomical structures, histopathology tissues, and nuclei instances. The source code is available at https://github.com/xq141839/Co-Seg-Plus.
comment: Under Review
☆ Do We Need Large VLMs for Spotting Soccer Actions?
Traditional video-based tasks like soccer action spotting rely heavily on visual inputs, often requiring complex and computationally expensive models to process dense video data. In this work, we propose a shift from this video-centric approach to a text-based task, making it lightweight and scalable by utilizing Large Language Models (LLMs) instead of Vision-Language Models (VLMs). We posit that expert commentary, which provides rich, fine-grained descriptions and contextual cues such as excitement and tactical insights, contains enough information to reliably spot key actions in a match. To demonstrate this, we use the SoccerNet Echoes dataset, which provides timestamped commentary, and employ a system of three LLMs acting as judges specializing in outcome, excitement, and tactics. Each LLM evaluates sliding windows of commentary to identify actions like goals, cards, and substitutions, generating accurate timestamps for these events. Our experiments show that this language-centric approach performs effectively in detecting critical match events, providing a lightweight and training-free alternative to traditional video-based methods for action spotting.
comment: 5 pages, 2 figures
☆ MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification
Deep learning models have made significant advances in histological prediction tasks in recent years. However, for adaptation in clinical practice, their lack of robustness to varying conditions such as staining, scanner, hospital, and demographics is still a limiting factor: if trained on overrepresented subpopulations, models regularly struggle with less frequent patterns, leading to shortcut learning and biased predictions. Large-scale foundation models have not fully eliminated this issue. Therefore, we propose a novel approach explicitly modeling such metadata into a Metadata-guided generative Diffusion model framework (MeDi). MeDi allows for a targeted augmentation of underrepresented subpopulations with synthetic data, which balances limited training data and mitigates biases in downstream models. We experimentally show that MeDi generates high-quality histopathology images for unseen subpopulations in TCGA, boosts the overall fidelity of the generated images, and enables improvements in performance for downstream classifiers on datasets with subpopulation shifts. Our work is a proof-of-concept towards better mitigating data biases with generative models.
☆ On the Theory of Conditional Feature Alignment for Unsupervised Domain-Adaptive Counting
Object counting models suffer when deployed across domains with differing density variety, since density shifts are inherently task-relevant and violate standard domain adaptation assumptions. To address this, we propose a theoretical framework of conditional feature alignment. We first formalize the notion of conditional divergence by partitioning each domain into subsets (e.g., object vs. background) and measuring divergences per condition. We then derive a joint error bound showing that, under discrete label spaces treated as condition sets, aligning distributions conditionally leads to tighter bounds on the combined source-target decision error than unconditional alignment. These insights motivate a general conditional adaptation principle: by preserving task-relevant variations while filtering out nuisance shifts, one can achieve superior cross-domain generalization for counting. We provide both defining conditional divergence then proving its benefit in lowering joint error and a practical adaptation strategy that preserves task-relevant information in unsupervised domain-adaptive counting. We demonstrate the effectiveness of our approach through extensive experiments on multiple counting datasets with varying density distributions. The results show that our method outperforms existing unsupervised domain adaptation methods, empirically validating the theoretical insights on conditional feature alignment.
comment: 18 pages, 5 figures, 8 tables
☆ Semi-Supervised Multi-Modal Medical Image Segmentation for Complex Situations MICCAI 2025
Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve the accuracy of medical image segmentation by providing complementary information. However, they face challenges in achieving significant improvements under semi-supervised conditions due to the challenge of effectively leveraging unlabeled data. There is a significant need to create an effective and reliable multi-modal learning strategy for leveraging unlabeled data in semi-supervised segmentation. To address these issues, we propose a novel semi-supervised multi-modal medical image segmentation approach, which leverages complementary multi-modal information to enhance performance with limited labeled data. Our approach employs a multi-stage multi-modal fusion and enhancement strategy to fully utilize complementary multi-modal information, while reducing feature discrepancies and enhancing feature sharing and alignment. Furthermore, we effectively introduce contrastive mutual learning to constrain prediction consistency across modalities, thereby facilitating the robustness of segmentation results in semi-supervised tasks. Experimental results on two multi-modal datasets demonstrate the superior performance and robustness of the proposed framework, establishing its valuable potential for solving medical image segmentation tasks in complex scenarios.
comment: 10 pages, 2 figures, accepted at MICCAI 2025
☆ Dynamic Watermark Generation for Digital Images using Perimeter Gated SPAD Imager PUFs SC
Digital image watermarks as a security feature can be derived from the imager's physically unclonable functions (PUFs) by utilizing the manufacturing variations, i.e., the dark signal non-uniformity (DSNU). While a few demonstrations focused on the CMOS image sensors (CIS) and active pixel sensors (APS), single photon avalanche diode (SPAD) imagers have never been investigated for this purpose. In this work, we have proposed a novel watermarking technique using perimeter gated SPAD (pgSPAD) imagers. We utilized the DSNU of three 64 x 64 pgSPAD imager chips, fabricated in a 0.35 {\mu}m standard CMOS process and analyzed the simulated watermarks for standard test images from publicly available database. Our observation shows that both source identification and tamper detection can be achieved using the proposed source-scene-specific dynamic watermarks with a controllable sensitivity-robustness trade-off.
comment: 5 pages, 7 figures, accepted at MWSCAS 2025 Conference
☆ Robust Training with Data Augmentation for Medical Imaging Classification
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.
☆ RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking IROS 2025
We introduce a robust framework, RGBTrack, for real-time 6D pose estimation and tracking that operates solely on RGB data, thereby eliminating the need for depth input for such dynamic and precise object pose tracking tasks. Building on the FoundationPose architecture, we devise a novel binary search strategy combined with a render-and-compare mechanism to efficiently infer depth and generate robust pose hypotheses from true-scale CAD models. To maintain stable tracking in dynamic scenarios, including rapid movements and occlusions, RGBTrack integrates state-of-the-art 2D object tracking (XMem) with a Kalman filter and a state machine for proactive object pose recovery. In addition, RGBTrack's scale recovery module dynamically adapts CAD models of unknown scale using an initial depth estimate, enabling seamless integration with modern generative reconstruction techniques. Extensive evaluations on benchmark datasets demonstrate that RGBTrack's novel depth-free approach achieves competitive accuracy and real-time performance, making it a promising practical solution candidate for application areas including robotics, augmented reality, and computer vision. The source code for our implementation will be made publicly available at https://github.com/GreatenAnoymous/RGBTrack.git.
comment: Accepted to IROS 2025
☆ MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance, medical diagnosis requires precise reasoning over structured clinical tables, while financial forecasting depends on interpreting plot-based data to make informed predictions. To tackle this challenge, we introduce MEXA, a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse and distinct domains. MEXA dynamically selects expert models based on the input modality and the task-specific reasoning demands (i.e., skills). Each expert model, specialized in a modality task pair, generates interpretable textual reasoning outputs. MEXA then aggregates and reasons over these outputs using a Large Reasoning Model (LRM) to produce the final answer. This modular design allows flexible and transparent multimodal reasoning across diverse domains without additional training overhead. We extensively evaluate our approach on diverse multimodal benchmarks, including Video Reasoning, Audio Reasoning, 3D Understanding, and Medical QA. MEXA consistently delivers performance improvements over strong multimodal baselines, highlighting the effectiveness and broad applicability of our expert-driven selection and aggregation in diverse multimodal reasoning tasks.
comment: The first two authors contributed equally; Github link: https://github.com/Yui010206/MEXA
☆ Monocular One-Shot Metric-Depth Alignment for RGB-Based Robot Grasping IROS 2025
Accurate 6D object pose estimation is a prerequisite for successfully completing robotic prehensile and non-prehensile manipulation tasks. At present, 6D pose estimation for robotic manipulation generally relies on depth sensors based on, e.g., structured light, time-of-flight, and stereo-vision, which can be expensive, produce noisy output (as compared with RGB cameras), and fail to handle transparent objects. On the other hand, state-of-the-art monocular depth estimation models (MDEMs) provide only affine-invariant depths up to an unknown scale and shift. Metric MDEMs achieve some successful zero-shot results on public datasets, but fail to generalize. We propose a novel framework, Monocular One-shot Metric-depth Alignment (MOMA), to recover metric depth from a single RGB image, through a one-shot adaptation building on MDEM techniques. MOMA performs scale-rotation-shift alignments during camera calibration, guided by sparse ground-truth depth points, enabling accurate depth estimation without additional data collection or model retraining on the testing setup. MOMA supports fine-tuning the MDEM on transparent objects, demonstrating strong generalization capabilities. Real-world experiments on tabletop 2-finger grasping and suction-based bin-picking applications show MOMA achieves high success rates in diverse tasks, confirming its effectiveness.
comment: Accepted to IROS 2025
☆ Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion
We present Assembler, a scalable and generalizable framework for 3D part assembly that reconstructs complete objects from input part meshes and a reference image. Unlike prior approaches that mostly rely on deterministic part pose prediction and category-specific training, Assembler is designed to handle diverse, in-the-wild objects with varying part counts, geometries, and structures. It addresses the core challenges of scaling to general 3D part assembly through innovations in task formulation, representation, and data. First, Assembler casts part assembly as a generative problem and employs diffusion models to sample plausible configurations, effectively capturing ambiguities arising from symmetry, repeated parts, and multiple valid assemblies. Second, we introduce a novel shape-centric representation based on sparse anchor point clouds, enabling scalable generation in Euclidean space rather than SE(3) pose prediction. Third, we construct a large-scale dataset of over 320K diverse part-object assemblies using a synthesis and filtering pipeline built on existing 3D shape repositories. Assembler achieves state-of-the-art performance on PartNet and is the first to demonstrate high-quality assembly for complex, real-world objects. Based on Assembler, we further introduce an interesting part-aware 3D modeling system that generates high-resolution, editable objects from images, demonstrating potential for interactive and compositional design. Project page: https://assembler3d.github.io
comment: Technical Report. Project page: https://assembler3d.github.io
☆ Relaxed syntax modeling in Transformers for future-proof license plate recognition
Effective license plate recognition systems are required to be resilient to constant change, as new license plates are released into traffic daily. While Transformer-based networks excel in their recognition at first sight, we observe significant performance drop over time which proves them unsuitable for tense production environments. Indeed, such systems obtain state-of-the-art results on plates whose syntax is seen during training. Yet, we show they perform similarly to random guessing on future plates where legible characters are wrongly recognized due to a shift in their syntax. After highlighting the flows of positional and contextual information in Transformer encoder-decoders, we identify several causes for their over-reliance on past syntax. Following, we devise architectural cut-offs and replacements which we integrate into SaLT, an attempt at a Syntax-Less Transformer for syntax-agnostic modeling of license plate representations. Experiments on both real and synthetic datasets show that our approach reaches top accuracy on past syntax and most importantly nearly maintains performance on future license plates. We further demonstrate the robustness of our architecture enhancements by way of various ablations.
☆ Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance
Uncovering which features' combinations high-level visual units encode is critical to understand how images are transformed into representations that support recognition. While existing feature visualization approaches typically infer a unit's most exciting images, this is insufficient to reveal the manifold of transformations under which responses remain invariant, which is key to generalization in vision. Here we introduce Stretch-and-Squeeze (SnS), an unbiased, model-agnostic, and gradient-free framework to systematically characterize a unit's invariance landscape and its vulnerability to adversarial perturbations in both biological and artificial visual systems. SnS frames these transformations as bi-objective optimization problems. To probe invariance, SnS seeks image perturbations that maximally alter the representation of a reference stimulus in a given processing stage while preserving unit activation. To probe adversarial sensitivity, SnS seeks perturbations that minimally alter the stimulus while suppressing unit activation. Applied to convolutional neural networks (CNNs), SnS revealed image variations that were further from a reference image in pixel-space than those produced by affine transformations, while more strongly preserving the target unit's response. The discovered invariant images differed dramatically depending on the choice of image representation used for optimization: pixel-level changes primarily affected luminance and contrast, while stretching mid- and late-layer CNN representations altered texture and pose respectively. Notably, the invariant images from robust networks were more recognizable by human subjects than those from standard networks, supporting the higher fidelity of robust CNNs as models of the visual system.
comment: 21 pages, 9 figures
☆ Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns
The training of real-world super-resolution reconstruction models heavily relies on datasets that reflect real-world degradation patterns. Extracting and modeling degradation patterns for super-resolution reconstruction using only real-world low-resolution (LR) images remains a challenging task. When synthesizing datasets to simulate real-world degradation, relying solely on degradation extraction methods fails to capture both blur and diverse noise characteristics across varying LR distributions, as well as more implicit degradations such as color gamut shifts. Conversely, domain translation alone cannot accurately approximate real-world blur characteristics due to the significant degradation domain gap between synthetic and real data. To address these challenges, we propose a novel TripleGAN framework comprising two strategically designed components: The FirstGAN primarily focuses on narrowing the domain gap in blur characteristics, while the SecondGAN performs domain-specific translation to approximate target-domain blur properties and learn additional degradation patterns. The ThirdGAN is trained on pseudo-real data generated by the FirstGAN and SecondGAN to reconstruct real-world LR images. Extensive experiments on the RealSR and DRealSR datasets demonstrate that our method exhibits clear advantages in quantitative metrics while maintaining sharp reconstructions without over-smoothing artifacts. The proposed framework effectively learns real-world degradation patterns from LR observations and synthesizes aligned datasets with corresponding degradation characteristics, thereby enabling the trained network to achieve superior performance in reconstructing high-quality SR images from real-world LR inputs.
☆ A Synthetic Benchmark for Collaborative 3D Semantic Occupancy Prediction in V2X Autonomous Driving
3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, the perception capability of a single vehicle is inherently constrained by occlusion, restricted sensor range, and narrow viewpoints. To address these limitations, collaborative perception enables the exchange of complementary information, thereby enhancing the completeness and accuracy. In the absence of a dedicated dataset for collaborative 3D semantic occupancy prediction, we augment an existing collaborative perception dataset by replaying it in CARLA with a high-resolution semantic voxel sensor to provide dense and comprehensive occupancy annotations. In addition, we establish benchmarks with varying prediction ranges designed to systematically assess the impact of spatial extent on collaborative prediction. We further develop a baseline model that performs inter-agent feature fusion via spatial alignment and attention aggregation. Experimental results demonstrate that our baseline model consistently outperforms single-agent models, with increasing gains observed as the prediction range expands.
☆ Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments
Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA methods typically rely on large vision-language models and require full access to source-domain data during adaptation, limiting their applicability. In this work, we propose Prmpt2Adpt, a lightweight and efficient zero-shot domain adaptation framework built around a teacher-student paradigm guided by prompt-based feature alignment. At the core of our method is a distilled and fine-tuned CLIP model, used as the frozen backbone of a Faster R-CNN teacher. A small set of low-level source features is aligned to the target domain semantics-specified only through a natural language prompt-via Prompt-driven Instance Normalization (PIN). These semantically steered features are used to briefly fine-tune the detection head of the teacher model. The adapted teacher then generates high-quality pseudo-labels, which guide the on-the-fly adaptation of a compact student model. Experiments on the MDS-A dataset demonstrate that Prmpt2Adpt achieves competitive detection performance compared to state-of-the-art methods, while delivering up to 7x faster adaptation and 5x faster inference speed using few source images-making it a practical and scalable solution for real-time adaptation in low-resource domains.
☆ ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds
The segmentation of forest LiDAR 3D point clouds, including both individual tree and semantic segmentation, is fundamental for advancing forest management and ecological research. However, current approaches often struggle with the complexity and variability of natural forest environments. We present ForestFormer3D, a new unified and end-to-end framework designed for precise individual tree and semantic segmentation. ForestFormer3D incorporates ISA-guided query point selection, a score-based block merging strategy during inference, and a one-to-many association mechanism for effective training. By combining these new components, our model achieves state-of-the-art performance for individual tree segmentation on the newly introduced FOR-instanceV2 dataset, which spans diverse forest types and regions. Additionally, ForestFormer3D generalizes well to unseen test sets (Wytham woods and LAUTx), showcasing its robustness across different forest conditions and sensor modalities. The FOR-instanceV2 dataset and the ForestFormer3D code will be released soon.
☆ Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs
Multimodal large language models (MLLMs) have begun to demonstrate robust reasoning capabilities on general tasks, yet their application in the medical domain remains in its early stages. Constructing chain-of-thought (CoT) training data is essential for bolstering the reasoning abilities of medical MLLMs. However, existing approaches exhibit a deficiency in offering a comprehensive framework for searching and evaluating effective reasoning paths towards critical diagnosis. To address this challenge, we propose Mentor-Intern Collaborative Search (MICS), a novel reasoning-path searching scheme to generate rigorous and effective medical CoT data. MICS first leverages mentor models to initialize the reasoning, one step at a time, then prompts each intern model to continue the thinking along those initiated paths, and finally selects the optimal reasoning path according to the overall reasoning performance of multiple intern models. The reasoning performance is determined by an MICS-Score, which assesses the quality of generated reasoning paths. Eventually, we construct MMRP, a multi-task medical reasoning dataset with ranked difficulty, and Chiron-o1, a new medical MLLM devised via a curriculum learning strategy, with robust visual question-answering and generalizable reasoning capabilities. Extensive experiments demonstrate that Chiron-o1, trained on our CoT dataset constructed using MICS, achieves state-of-the-art performance across a list of medical visual question answering and reasoning benchmarks. Codes are available at GitHub - manglu097/Chiron-o1: Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs
☆ Reversing Flow for Image Restoration CVPR2025
Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restoration, including diffusion and score-based models, often treat the degradation process as a stochastic transformation, which introduces inefficiency and complexity. In this work, we propose ResFlow, a novel image restoration framework that models the degradation process as a deterministic path using continuous normalizing flows. ResFlow augments the degradation process with an auxiliary process that disambiguates the uncertainty in HQ prediction to enable reversible modeling of the degradation process. ResFlow adopts entropy-preserving flow paths and learns the augmented degradation flow by matching the velocity field. ResFlow significantly improves the performance and speed of image restoration, completing the task in fewer than four sampling steps. Extensive experiments demonstrate that ResFlow achieves state-of-the-art results across various image restoration benchmarks, offering a practical and efficient solution for real-world applications.
comment: CVPR2025 Final Version; Corresponding Author: Bing Li
☆ Visual-Instructed Degradation Diffusion for All-in-One Image Restoration CVPR2025
Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose \textbf{Defusion}, a novel all-in-one image restoration framework that utilizes visual instruction-guided degradation diffusion. Unlike existing methods that rely on task-specific models or ambiguous text-based priors, Defusion constructs explicit \textbf{visual instructions} that align with the visual degradation patterns. These instructions are grounded by applying degradations to standardized visual elements, capturing intrinsic degradation features while agnostic to image semantics. Defusion then uses these visual instructions to guide a diffusion-based model that operates directly in the degradation space, where it reconstructs high-quality images by denoising the degradation effects with enhanced stability and generalizability. Comprehensive experiments demonstrate that Defusion outperforms state-of-the-art methods across diverse image restoration tasks, including complex and real-world degradations.
comment: CVPR2025 Final Version; Corresponding Author: Bing Li
☆ LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models ICML 2025
Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from robustness benchmarks to quantify progress. While various benchmark datasets such as ImageNet-C were proposed in the ImageNet era, most ImageNet-C corruption types are no longer OOD relative to today's large, web-scraped datasets, which already contain common corruptions such as blur or JPEG compression artifacts. Consequently, these benchmarks are no longer well-suited for evaluating OOD robustness in the era of web-scale datasets. Indeed, recent models show saturating scores on ImageNet-era OOD benchmarks, indicating that it is unclear whether models trained on web-scale datasets truly become better at OOD generalization or whether they have simply been exposed to the test distortions during training. To address this, we introduce LAION-C as a benchmark alternative for ImageNet-C. LAION-C consists of six novel distortion types specifically designed to be OOD, even for web-scale datasets such as LAION. In a comprehensive evaluation of state-of-the-art models, we find that the LAION-C dataset poses significant challenges to contemporary models, including MLLMs such as Gemini and GPT-4o. We additionally conducted a psychophysical experiment to evaluate the difficulty of our corruptions for human observers, enabling a comparison of models to lab-quality human robustness data. We observe a paradigm shift in OOD generalization: from humans outperforming models, to the best models now matching or outperforming the best human observers.
comment: ICML 2025 camera ready version
☆ LunarLoc: Segment-Based Global Localization on the Moon
Global localization is necessary for autonomous operations on the lunar surface where traditional Earth-based navigation infrastructure, such as GPS, is unavailable. As NASA advances toward sustained lunar presence under the Artemis program, autonomous operations will be an essential component of tasks such as robotic exploration and infrastructure deployment. Tasks such as excavation and transport of regolith require precise pose estimation, but proposed approaches such as visual-inertial odometry (VIO) accumulate odometry drift over long traverses. Precise pose estimation is particularly important for upcoming missions such as the ISRU Pilot Excavator (IPEx) that rely on autonomous agents to operate over extended timescales and varied terrain. To help overcome odometry drift over long traverses, we propose LunarLoc, an approach to global localization that leverages instance segmentation for zero-shot extraction of boulder landmarks from onboard stereo imagery. Segment detections are used to construct a graph-based representation of the terrain, which is then aligned with a reference map of the environment captured during a previous session using graph-theoretic data association. This method enables accurate and drift-free global localization in visually ambiguous settings. LunarLoc achieves sub-cm level accuracy in multi-session global localization experiments, significantly outperforming the state of the art in lunar global localization. To encourage the development of further methods for global localization on the Moon, we release our datasets publicly with a playback module: https://github.com/mit-acl/lunarloc-data.
☆ PET Tracer Separation Using Conditional Diffusion Transformer with Multi-latent Space Learning
In clinical practice, single-radiotracer positron emission tomography (PET) is commonly used for imaging. Although multi-tracer PET imaging can provide supplementary information of radiotracers that are sensitive to physiological function changes, enabling a more comprehensive characterization of physiological and pathological states, the gamma-photon pairs generated by positron annihilation reactions of different tracers in PET imaging have the same energy, making it difficult to distinguish the tracer signals. In this study, a multi-latent space guided texture conditional diffusion transformer model (MS-CDT) is proposed for PET tracer separation. To the best of our knowledge, this is the first attempt to use texture condition and multi-latent space for tracer separation in PET imaging. The proposed model integrates diffusion and transformer architectures into a unified optimization framework, with the novel addition of texture masks as conditional inputs to enhance image details. By leveraging multi-latent space prior derived from different tracers, the model captures multi-level feature representations, aiming to balance computational efficiency and detail preservation. The texture masks, serving as conditional guidance, help the model focus on salient structural patterns, thereby improving the extraction and utilization of fine-grained image textures. When combined with the diffusion transformer backbone, this conditioning mechanism contributes to more accurate and robust tracer separation. To evaluate its effectiveness, the proposed MS-CDT is compared with several advanced methods on two types of 3D PET datasets: brain and chest scans. Experimental results indicate that MS-CDT achieved competitive performance in terms of image quality and preservation of clinically relevant information. Code is available at: https://github.com/yqx7150/MS-CDT.
☆ AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fr\'echet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon.
☆ With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You
Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment including zero-shot classification and cross-modal retrieval. However, existing models typically rely on millions of paired multimodal samples, which are prohibitively expensive or infeasible to obtain in many domains. In this work, we explore the feasibility of building multimodal models with limited amount of paired data by aligning pretrained unimodal foundation models. We show that high-quality alignment is possible with as few as tens of thousands of paired samples$\unicode{x2013}$less than $1\%$ of the data typically used in the field. To achieve this, we introduce STRUCTURE, an effective regularization technique that preserves the neighborhood geometry of the latent space of unimodal encoders. Additionally, we show that aligning last layers is often suboptimal and demonstrate the benefits of aligning the layers with the highest representational similarity across modalities. These two components can be readily incorporated into existing alignment methods, yielding substantial gains across 24 zero-shot image classification and retrieval benchmarks, with average relative improvement of $51.6\%$ in classification and $91.8\%$ in retrieval tasks. Our results highlight the effectiveness and broad applicability of our framework for limited-sample multimodal learning and offer a promising path forward for resource-constrained domains.
☆ From Lab to Factory: Pitfalls and Guidelines for Self-/Unsupervised Defect Detection on Low-Quality Industrial Images ECML
The detection and localization of quality-related problems in industrially mass-produced products has historically relied on manual inspection, which is costly and error-prone. Machine learning has the potential to replace manual handling. As such, the desire is to facilitate an unsupervised (or self-supervised) approach, as it is often impossible to specify all conceivable defects ahead of time. A plethora of prior works have demonstrated the aptitude of common reconstruction-, embedding-, and synthesis-based methods in laboratory settings. However, in practice, we observe that most methods do not handle low data quality well or exude low robustness in unfavorable, but typical real-world settings. For practitioners it may be very difficult to identify the actual underlying problem when such methods underperform. Worse, often-reported metrics (e.g., AUROC) are rarely suitable in practice and may give misleading results. In our setting, we attempt to identify subtle anomalies on the surface of blasted forged metal parts, using rather low-quality RGB imagery only, which is a common industrial setting. We specifically evaluate two types of state-of-the-art models that allow us to identify and improve quality issues in production data, without having to obtain new data. Our contribution is to provide guardrails for practitioners that allow them to identify problems related to, e.g., (lack of) robustness or invariance, in either the chosen model or the data reliably in similar scenarios. Furthermore, we exemplify common pitfalls in and shortcomings of likelihood-based approaches and outline a framework for proper empirical risk estimation that is more suitable for real-world scenarios.
comment: 18 pages, 7 figures, 1 table. Camera-ready version for the 2025 conference European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD '25)
☆ ParkFormer: A Transformer-Based Parking Policy with Goal Embedding and Pedestrian-Aware Control
Autonomous parking plays a vital role in intelligent vehicle systems, particularly in constrained urban environments where high-precision control is required. While traditional rule-based parking systems struggle with environmental uncertainties and lack adaptability in crowded or dynamic scenes, human drivers demonstrate the ability to park intuitively without explicit modeling. Inspired by this observation, we propose a Transformer-based end-to-end framework for autonomous parking that learns from expert demonstrations. The network takes as input surround-view camera images, goal-point representations, ego vehicle motion, and pedestrian trajectories. It outputs discrete control sequences including throttle, braking, steering, and gear selection. A novel cross-attention module integrates BEV features with target points, and a GRU-based pedestrian predictor enhances safety by modeling dynamic obstacles. We validate our method on the CARLA 0.9.14 simulator in both vertical and parallel parking scenarios. Experiments show our model achieves a high success rate of 96.57\%, with average positional and orientation errors of 0.21 meters and 0.41 degrees, respectively. The ablation studies further demonstrate the effectiveness of key modules such as pedestrian prediction and goal-point attention fusion. The code and dataset will be released at: https://github.com/little-snail-f/ParkFormer.
☆ Controllable and Expressive One-Shot Video Head Swapping
In this paper, we propose a novel diffusion-based multi-condition controllable framework for video head swapping, which seamlessly transplant a human head from a static image into a dynamic video, while preserving the original body and background of target video, and further allowing to tweak head expressions and movements during swapping as needed. Existing face-swapping methods mainly focus on localized facial replacement neglecting holistic head morphology, while head-swapping approaches struggling with hairstyle diversity and complex backgrounds, and none of these methods allow users to modify the transplanted head expressions after swapping. To tackle these challenges, our method incorporates several innovative strategies through a unified latent diffusion paradigm. 1) Identity-preserving context fusion: We propose a shape-agnostic mask strategy to explicitly disentangle foreground head identity features from background/body contexts, combining hair enhancement strategy to achieve robust holistic head identity preservation across diverse hair types and complex backgrounds. 2) Expression-aware landmark retargeting and editing: We propose a disentangled 3DMM-driven retargeting module that decouples identity, expression, and head poses, minimizing the impact of original expressions in input images and supporting expression editing. While a scale-aware retargeting strategy is further employed to minimize cross-identity expression distortion for higher transfer precision. Experimental results demonstrate that our method excels in seamless background integration while preserving the identity of the source portrait, as well as showcasing superior expression transfer capabilities applicable to both real and virtual characters.
comment: Project page: https://humanaigc.github.io/SwapAnyHead/
☆ Camera Calibration via Circular Patterns: A Comprehensive Framework with Measurement Uncertainty and Unbiased Projection Model
Camera calibration using planar targets has been widely favored, and two types of control points have been mainly considered as measurements: the corners of the checkerboard and the centroid of circles. Since a centroid is derived from numerous pixels, the circular pattern provides more precise measurements than the checkerboard. However, the existing projection model of circle centroids is biased under lens distortion, resulting in low performance. To surmount this limitation, we propose an unbiased projection model of the circular pattern and demonstrate its superior accuracy compared to the checkerboard. Complementing this, we introduce uncertainty into circular patterns to enhance calibration robustness and completeness. Defining centroid uncertainty improves the performance of calibration components, including pattern detection, optimization, and evaluation metrics. We also provide guidelines for performing good camera calibration based on the evaluation metric. The core concept of this approach is to model the boundary points of a two-dimensional shape as a Markov random field, considering its connectivity. The shape distribution is propagated to the centroid uncertainty through an appropriate shape representation based on the Green theorem. Consequently, the resulting framework achieves marked gains in calibration accuracy and robustness. The complete source code and demonstration video are available at https://github.com/chaehyeonsong/discocal.
☆ Beyond Blur: A Fluid Perspective on Generative Diffusion Models
We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward pass formulates image corruption via a physically motivated PDE that couples directional advection with isotropic diffusion and Gaussian noise, controlled by dimensionless numbers (Peclet, Fourier). We implement this PDE numerically through a GPU-accelerated custom Lattice Boltzmann solver for fast evaluation. To induce realistic turbulence, we generate stochastic velocity fields that introduce coherent motion and capture multi-scale mixing. In the generative process, a neural network learns to reverse the advection-diffusion operator thus constituting a novel generative model. We discuss how previous methods emerge as specific cases of our operator, demonstrating that our framework generalizes prior PDE-based corruption techniques. We illustrate how advection improves the diversity and quality of the generated images while keeping the overall color palette unaffected. This work bridges fluid dynamics, dimensionless PDE theory, and deep generative modeling, offering a fresh perspective on physically informed image corruption processes for diffusion-based synthesis.
comment: 11 pages, 8 figures, pre-print, supplementary pseudocode in appendix
☆ AnyTraverse: An off-road traversability framework with VLM and human operator in the loop
Off-road traversability segmentation enables autonomous navigation with applications in search-and-rescue, military operations, wildlife exploration, and agriculture. Current frameworks struggle due to significant variations in unstructured environments and uncertain scene changes, and are not adaptive to be used for different robot types. We present AnyTraverse, a framework combining natural language-based prompts with human-operator assistance to determine navigable regions for diverse robotic vehicles. The system segments scenes for a given set of prompts and calls the operator only when encountering previously unexplored scenery or unknown class not part of the prompt in its region-of-interest, thus reducing active supervision load while adapting to varying outdoor scenes. Our zero-shot learning approach eliminates the need for extensive data collection or retraining. Our experimental validation includes testing on RELLIS-3D, Freiburg Forest, and RUGD datasets and demonstrate real-world deployment on multiple robot platforms. The results show that AnyTraverse performs better than GA-NAV and Off-seg while offering a vehicle-agnostic approach to off-road traversability that balances automation with targeted human supervision.
Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots
Robust and accurate ball detection is a critical component for autonomous humanoid soccer robots, particularly in dynamic and challenging environments such as RoboCup outdoor fields. However, traditional supervised approaches require extensive manual annotation, which is costly and time-intensive. To overcome this problem, we present a self-supervised learning framework for domain-adaptive feature extraction to enhance ball detection performance. The proposed approach leverages a general-purpose pretrained model to generate pseudo-labels, which are then used in a suite of self-supervised pretext tasks -- including colorization, edge detection, and triplet loss -- to learn robust visual features without relying on manual annotations. Additionally, a model-agnostic meta-learning (MAML) strategy is incorporated to ensure rapid adaptation to new deployment scenarios with minimal supervision. A new dataset comprising 10,000 labeled images from outdoor RoboCup SPL matches is introduced, used to validate the method, and made available to the community. Experimental results demonstrate that the proposed pipeline outperforms baseline models in terms of accuracy, F1 score, and IoU, while also exhibiting faster convergence.
☆ Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection IJCAI 2025
The proliferation of generative models has raised serious concerns about visual content forgery. Existing deepfake detection methods primarily target either image-level classification or pixel-wise localization. While some achieve high accuracy, they often suffer from limited generalization across manipulation types or rely on complex architectures. In this paper, we propose Loupe, a lightweight yet effective framework for joint deepfake detection and localization. Loupe integrates a patch-aware classifier and a segmentation module with conditional queries, allowing simultaneous global authenticity classification and fine-grained mask prediction. To enhance robustness against distribution shifts of test set, Loupe introduces a pseudo-label-guided test-time adaptation mechanism by leveraging patch-level predictions to supervise the segmentation head. Extensive experiments on the DDL dataset demonstrate that Loupe achieves state-of-the-art performance, securing the first place in the IJCAI 2025 Deepfake Detection and Localization Challenge with an overall score of 0.846. Our results validate the effectiveness of the proposed patch-level fusion and conditional query design in improving both classification accuracy and spatial localization under diverse forgery patterns. The code is available at https://github.com/Kamichanw/Loupe.
comment: 6 pages, 2 figures, accepted by IJCAI 2025 workshop
☆ FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling, enabling both accurate content understanding and flexible editing. However, current approaches treat "what to see" and "how to edit" separately: they either perform isolated object segmentation or utilize segmentation masks merely as conditional prompts for local edit generation tasks, often relying on multiple disjointed models. To bridge these gaps, we introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework. FOCUS employs a dual-branch visual encoder to simultaneously capture global semantic context and fine-grained spatial details. In addition, we leverage a MoVQGAN-based visual tokenizer to produce discrete visual tokens that enhance generation quality. To enable accurate and controllable image editing, we propose a progressive multi-stage training pipeline, where segmentation masks are jointly optimized and used as spatial condition prompts to guide the diffusion decoder. This strategy aligns visual encoding, segmentation, and generation modules, effectively bridging segmentation-aware perception with fine-grained visual synthesis. Extensive experiments across three core tasks, including multimodal understanding, referring segmentation accuracy, and controllable image generation, demonstrate that FOCUS achieves strong performance by jointly optimizing visual perception and generative capabilities.
☆ Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes
Humans exhibit a remarkable ability to recognize co-visibility-the overlapping regions visible in multiple images-even when these images are sparsely distributed across a complex scene. This capability is foundational in 3D vision and robotic perception. Despite significant progress in vision learning, it remains unclear whether current vision models have reached human-level proficiency in co-visibility analysis. In this work, we introduce the Co-Visibility reasONing (Co-VisiON) benchmark, designed to directly evaluate co-visibility reasoning on sparse image sets across over 1000 indoor scenarios. Our experiments reveal that while co-visibility is typically treated as a low-level feature matching task, it poses a significant challenge for existing vision models under sparse conditions. Notably, a proprietary vision-language model outperforms all purely vision-based approaches, with all models lagging substantially behind human performance. This gap underscores the need for more than basic pairwise vision processing-it calls for a comprehensive spatial understanding through high-level reasoning across multiple views. Inspired by human visual cognition, we propose a novel multi-view baseline, Covis, which achieves top performance among pure vision models and narrows the gap to the proprietary VLM. We hope our benchmark and findings will spur further advancements in developing vision models capable of robust, high-level reasoning in challenging, sparse environments. Our dataset and source code can be found at: https://ai4ce.github.io/CoVISION
☆ Temperature calibration of surface emissivities with an improved thermal image enhancement network
Infrared thermography faces persistent challenges in temperature accuracy due to material emissivity variations, where existing methods often neglect the joint optimization of radiometric calibration and image degradation. This study introduces a physically guided neural framework that unifies temperature correction and image enhancement through a symmetric skip-CNN architecture and an emissivity-aware attention module. The pre-processing stage segments the ROIs of the image and and initially corrected the firing rate. A novel dual-constrained loss function strengthens the statistical consistency between the target and reference regions through mean-variance alignment and histogram matching based on Kullback-Leibler dispersion. The method works by dynamically fusing thermal radiation features and spatial context, and the model suppresses emissivity artifacts while recovering structural details. After validating the industrial blower system under different conditions, the improved network realizes the dynamic fusion of thermal radiation characteristics and spatial background, with accurate calibration results in various industrial conditions.
☆ Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation
Synthetic video generation is progressing very rapidly. The latest models can produce very realistic high-resolution videos that are virtually indistinguishable from real ones. Although several video forensic detectors have been recently proposed, they often exhibit poor generalization, which limits their applicability in a real-world scenario. Our key insight to overcome this issue is to guide the detector towards seeing what really matters. In fact, a well-designed forensic classifier should focus on identifying intrinsic low-level artifacts introduced by a generative architecture rather than relying on high-level semantic flaws that characterize a specific model. In this work, first, we study different generative architectures, searching and identifying discriminative features that are unbiased, robust to impairments, and shared across models. Then, we introduce a novel forensic-oriented data augmentation strategy based on the wavelet decomposition and replace specific frequency-related bands to drive the model to exploit more relevant forensic cues. Our novel training paradigm improves the generalizability of AI-generated video detectors, without the need for complex algorithms and large datasets that include multiple synthetic generators. To evaluate our approach, we train the detector using data from a single generative model and test it against videos produced by a wide range of other models. Despite its simplicity, our method achieves a significant accuracy improvement over state-of-the-art detectors and obtains excellent results even on very recent generative models, such as NOVA and FLUX. Code and data will be made publicly available.
☆ PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model
Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques. In this paper, we propose PQCAD-DM, a novel hybrid compression framework combining Progressive Quantization (PQ) and Calibration-Assisted Distillation (CAD) to address these challenges. PQ employs a two-stage quantization with adaptive bit-width transitions guided by a momentum-based mechanism, reducing excessive weight perturbations in low-precision. CAD leverages full-precision calibration datasets during distillation, enabling the student to match full-precision performance even with a quantized teacher. As a result, PQCAD-DM achieves a balance between computational efficiency and generative quality, halving inference time while maintaining competitive performance. Extensive experiments validate PQCAD-DM's superior generative capabilities and efficiency across diverse datasets, outperforming fixed-bit quantization methods.
comment: 10 pages, 6 figures
☆ Infrared and Visible Image Fusion Based on Implicit Neural Representations
Infrared and visible light image fusion aims to combine the strengths of both modalities to generate images that are rich in information and fulfill visual or computational requirements. This paper proposes an image fusion method based on Implicit Neural Representations (INR), referred to as INRFuse. This method parameterizes a continuous function through a neural network to implicitly represent the multimodal information of the image, breaking through the traditional reliance on discrete pixels or explicit features. The normalized spatial coordinates of the infrared and visible light images serve as inputs, and multi-layer perceptrons is utilized to adaptively fuse the features of both modalities, resulting in the output of the fused image. By designing multiple loss functions, the method jointly optimizes the similarity between the fused image and the original images, effectively preserving the thermal radiation information of the infrared image while maintaining the texture details of the visible light image. Furthermore, the resolution-independent characteristic of INR allows for the direct fusion of images with varying resolutions and achieves super-resolution reconstruction through high-density coordinate queries. Experimental results indicate that INRFuse outperforms existing methods in both subjective visual quality and objective evaluation metrics, producing fused images with clear structures, natural details, and rich information without the necessity for a training dataset.
☆ Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box jailbreak methods primarily rely on adversarial textual prompts or image perturbations, yet these approaches are highly detectable by standard content filtering systems and exhibit low query and computational efficiency. In this work, we present Cross-modal Adversarial Multimodal Obfuscation (CAMO), a novel black-box jailbreak attack framework that decomposes malicious prompts into semantically benign visual and textual fragments. By leveraging LVLMs' cross-modal reasoning abilities, CAMO covertly reconstructs harmful instructions through multi-step reasoning, evading conventional detection mechanisms. Our approach supports adjustable reasoning complexity and requires significantly fewer queries than prior attacks, enabling both stealth and efficiency. Comprehensive evaluations conducted on leading LVLMs validate CAMO's effectiveness, showcasing robust performance and strong cross-model transferability. These results underscore significant vulnerabilities in current built-in safety mechanisms, emphasizing an urgent need for advanced, alignment-aware security and safety solutions in vision-language systems.
comment: 15 pages, 9 figures
☆ Class Agnostic Instance-level Descriptor for Visual Instance Search
Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance level feature representation. Supervised or weakly supervised object detection methods are not among the options due to their poor performance on the unknown object categories. In this paper, based on the feature set output from self-supervised ViT, the instance level region discovery is modeled as detecting the compact feature subsets in a hierarchical fashion. The hierarchical decomposition results in a hierarchy of feature subsets. The non-leaf nodes and leaf nodes on the hierarchy correspond to the various instance regions in an image of different semantic scales. The hierarchical decomposition well addresses the problem of object embedding and occlusions, which are widely observed in the real scenarios. The features derived from the nodes on the hierarchy make up a comprehensive representation for the latent instances in the image. Our instance-level descriptor remains effective on both the known and unknown object categories. Empirical studies on three instance search benchmarks show that it outperforms state-of-the-art methods considerably.
☆ Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention
With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure.However, a key challenge for forgery detection is generalising to diffusion models not seen during training. In this paper, we address this problem by focusing on image noise. We observe that images from different diffusion models share similar noise patterns, distinct from genuine images. Building upon this insight, we introduce a novel Noise-Aware Self-Attention (NASA) module that focuses on noise regions to capture anomalous patterns. To implement a SOTA detection model, we incorporate NASA into Swin Transformer, forming an novel detection architecture NASA-Swin. Additionally, we employ a cross-modality fusion embedding to combine RGB and noise images, along with a channel mask strategy to enhance feature learning from both modalities. Extensive experiments demonstrate the effectiveness of our approach in enhancing detection capabilities for diffusion-generated images. When encountering unseen generation methods, our approach achieves the state-of-the-art performance.Our code is available at https://github.com/WeinanGuan/NASA-Swin.
comment: Accepted by TIFS 2025. Our code is availabel at https://github.com/WeinanGuan/NASA-Swin
☆ Uncertainty-Aware Variational Information Pursuit for Interpretable Medical Image Analysis
In medical imaging, AI decision-support systems must balance accuracy and interpretability to build user trust and support effective clinical decision-making. Recently, Variational Information Pursuit (V-IP) and its variants have emerged as interpretable-by-design modeling techniques, aiming to explain AI decisions in terms of human-understandable, clinically relevant concepts. However, existing V-IP methods overlook instance-level uncertainties in query-answer generation, which can arise from model limitations (epistemic uncertainty) or variability in expert responses (aleatoric uncertainty). This paper introduces Uncertainty-Aware V-IP (UAV-IP), a novel framework that integrates uncertainty quantification into the V-IP process. We evaluate UAV-IP across four medical imaging datasets, PH2, Derm7pt, BrEaST, and SkinCon, demonstrating an average AUC improvement of approximately 3.2% while generating 20% more concise explanations compared to baseline V-IP, without sacrificing informativeness. These findings highlight the importance of uncertainty-aware reasoning in interpretable by design models for robust and reliable medical decision-making.
☆ Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection
Unmanned aerial vehicle (UAV) object detection plays a vital role in applications such as environmental monitoring and urban security. To improve robustness, recent studies have explored multimodal detection by fusing visible (RGB) and infrared (IR) imagery. However, due to UAV platform motion and asynchronous imaging, spatial misalignment frequently occurs between modalities, leading to weak alignment. This introduces two major challenges: semantic inconsistency at corresponding spatial locations and modality conflict during feature fusion. Existing methods often address these issues in isolation, limiting their effectiveness. In this paper, we propose Cross-modal Offset-guided Dynamic Alignment and Fusion (CoDAF), a unified framework that jointly tackles both challenges in weakly aligned UAV-based object detection. CoDAF comprises two novel modules: the Offset-guided Semantic Alignment (OSA), which estimates attention-based spatial offsets and uses deformable convolution guided by a shared semantic space to align features more precisely; and the Dynamic Attention-guided Fusion Module (DAFM), which adaptively balances modality contributions through gating and refines fused features via spatial-channel dual attention. By integrating alignment and fusion in a unified design, CoDAF enables robust UAV object detection. Experiments on standard benchmarks validate the effectiveness of our approach, with CoDAF achieving a mAP of 78.6% on the DroneVehicle dataset.
☆ 3DeepRep: 3D Deep Low-rank Tensor Representation for Hyperspectral Image Inpainting
Recent approaches based on transform-based tensor nuclear norm (TNN) have demonstrated notable effectiveness in hyperspectral image (HSI) inpainting by leveraging low-rank structures in latent representations. Recent developments incorporate deep transforms to improve low-rank tensor representation; however, existing approaches typically restrict the transform to the spectral mode, neglecting low-rank properties along other tensor modes. In this paper, we propose a novel 3-directional deep low-rank tensor representation (3DeepRep) model, which performs deep nonlinear transforms along all three modes of the HSI tensor. To enforce low-rankness, the model minimizes the nuclear norms of mode-i frontal slices in the corresponding latent space for each direction (i=1,2,3), forming a 3-directional TNN regularization. The outputs from the three directional branches are subsequently fused via a learnable aggregation module to produce the final result. An efficient gradient-based optimization algorithm is developed to solve the model in a self-supervised manner. Extensive experiments on real-world HSI datasets demonstrate that the proposed method achieves superior inpainting performance compared to existing state-of-the-art techniques, both qualitatively and quantitatively.
☆ TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion
Infrared and visible image fusion (IVF) aims to combine complementary information from both image modalities, producing more informative and comprehensive outputs. Recently, text-guided IVF has shown great potential due to its flexibility and versatility. However, the effective integration and utilization of textual semantic information remains insufficiently studied. To tackle these challenges, we introduce textual semantics at two levels: the mask semantic level and the text semantic level, both derived from textual descriptions extracted by large Vision-Language Models (VLMs). Building on this, we propose Textual Semantic Guidance for infrared and visible image fusion, termed TeSG, which guides the image synthesis process in a way that is optimized for downstream tasks such as detection and segmentation. Specifically, TeSG consists of three core components: a Semantic Information Generator (SIG), a Mask-Guided Cross-Attention (MGCA) module, and a Text-Driven Attentional Fusion (TDAF) module. The SIG generates mask and text semantics based on textual descriptions. The MGCA module performs initial attention-based fusion of visual features from both infrared and visible images, guided by mask semantics. Finally, the TDAF module refines the fusion process with gated attention driven by text semantics. Extensive experiments demonstrate the competitiveness of our approach, particularly in terms of performance on downstream tasks, compared to existing state-of-the-art methods.
comment: 11 pages, 6 figures
☆ Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement ICMR 2025
While existing Generalized Category Discovery (GCD) models have achieved significant success, their performance with limited labeled samples and a small number of known categories remains largely unexplored. In this work, we introduce the task of Few-shot Generalized Category Discovery (FSGCD), aiming to achieve competitive performance in GCD tasks under conditions of known information scarcity. To tackle this challenge, we propose a decision boundary enhancement framework with affinity-based retrieval. Our framework is designed to learn the decision boundaries of known categories and transfer these boundaries to unknown categories. First, we use a decision boundary pre-training module to mitigate the overfitting of pre-trained information on known category boundaries and improve the learning of these decision boundaries using labeled samples. Second, we implement a two-stage retrieval-guided decision boundary optimization strategy. Specifically, this strategy further enhances the severely limited known boundaries by using affinity-retrieved pseudo-labeled samples. Then, these refined boundaries are applied to unknown clusters via guidance from affinity-based feature retrieval. Experimental results demonstrate that our proposed method outperforms existing methods on six public GCD benchmarks under the FSGCD setting. The codes are available at: https://github.com/Ryh1218/FSGCD
comment: Accepted by ICMR 2025
☆ Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition
Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that humans use to constitute an understanding of objects, human-object interactions, and activities - that have not been fully exploited. In this paper, we introduce a framework incorporating language-driven common sense priors to identify cluttered video action sequences from monocular views that are often heavily occluded. We propose: (1) A video context summary component that generates candidate objects, activities, and the interactions between objects and activities; (2) A description generation module that describes the current scene given the context and infers subsequent activities, through auxiliary prompts and common sense reasoning; (3) A multi-modal activity recognition head that combines visual and textual cues to recognize video actions. We demonstrate the effectiveness of our approach on the challenging Action Genome and Charades datasets.
☆ LaVi: Efficient Large Vision-Language Models via Internal Feature Modulation
Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or introduce severe long-context computational burden, severely limiting scalability and efficiency. In this paper, we rethink multimodal integration and present LaVi, a novel LVLM that enables seamless and efficient vision-language fusion through internal feature modulation within the Large Language Models (LLMs). Unlike dominant LVLMs that rely on visual token concatenation, LaVi bypasses long-context expansion by introducing a lightweight and adaptive transformation, which incorporates visual context by injecting token-wise vision-conditioned deltas into the affine parameters of layer normalization. This mechanism directly modulates linguistic hidden states based on visual input, ensuring precise vision-language alignment while preserving the LLM's linguistic priors and drastically reducing computational costs. Extensive evaluations across 15 image and video benchmarks demonstrate that LaVi not only achieves state-of-the-art multimodal performance but also dramatically enhances efficiency. Compared to LLaVA-OV-7B, LaVi reduces FLOPs by 94.0%, improves inference speed by 3.1 times, and cuts memory usage in half - establishing LaVi as a scalable and practical solution for real-time multimodal reasoning. The code and models will be released soon.
☆ DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
Stereo Depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help reveal vulnerabilities before deployment. Previous work has shown that repeating optimized textures can effectively mislead stereo depth estimation in digital settings. However, our research reveals that these naively repeated texture structures perform poorly in physical-world implementations, i.e., when deployed as patches, limiting their practical utility for testing stereo depth estimation systems. In this work, for the first time, we discover that introducing regular intervals between repeated textures, creating a striped structure, significantly enhances the patch attack effectiveness. Through extensive experimentation, we analyze how variations of this novel structure influence the performance. Based on these insights, we develop a novel stereo depth attack that jointly optimizes both the striped structure and texture elements. Our generated adversarial patches can be inserted into any scenes and successfully attack state-of-the-art stereo depth estimation methods, i.e., RAFT-Stereo and STTR. Most critically, our patch can also attack commercial RGB-D cameras (Intel RealSense) in real-world conditions, demonstrating their practical relevance for security assessment of stereo systems.
☆ How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions
Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted towards synthetic training captions. While this setup is generally believed to produce more capable models, current literature does not provide any insights into its design choices. This study closes this gap by systematically investigating how different synthetic captioning strategies impact the downstream performance of text-to-image models. Our experiments demonstrate that dense, high-quality captions enhance text alignment but may introduce trade-offs in output aesthetics and diversity. Conversely, captions of randomized lengths yield balanced improvements across aesthetics and alignment without compromising sample diversity. We also demonstrate that varying caption distributions introduce significant shifts in the output bias of a trained model. Our findings underscore the importance of caption design in achieving optimal model performance and provide practical insights for more effective training data strategies in text-to-image generation.
☆ Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge
CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, the computational overhead of a large number of parameters and large-scale pre-training poses challenges of pre-training a different scale of CLIP. Learngene extracts the generalizable components termed as learngene from an ancestry model and initializes diverse descendant models with it. Previous Learngene paradigms fail to handle the generalizable knowledge in multimodal scenarios. In this paper, we put forward the idea of utilizing a multimodal block to extract the multimodal generalizable knowledge, which inspires us to propose MM-LG (Multimodal Learngene), a novel framework designed to extract and leverage generalizable components from CLIP. Specifically, we first establish multimodal and unimodal blocks to extract the multimodal and unimodal generalizable knowledge in a weighted-sum manner. Subsequently, we employ these components to numerically initialize descendant models of varying scales and modalities. Extensive experiments demonstrate MM-LG's effectiveness, which achieves performance gains over existing learngene approaches (e.g.,+3.1% on Oxford-IIIT PET and +4.13% on Flickr30k) and comparable or superior results to the pre-training and fine-tuning paradigm (e.g.,+1.9% on Oxford-IIIT PET and +3.65% on Flickr30k). Notably, MM-LG requires only around 25% of the parameter storage while reducing around 2.8 times pre-training costs for diverse model scales compared to the pre-training and fine-tuning paradigm, making it particularly suitable for efficient deployment across diverse downstream tasks.
♻ ☆ Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence
AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the Embodied Web Agents task environments, a unified simulation platform that tightly integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the Embodied Web Agents Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation - all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access. All datasets, codes and websites are publicly available at our project page https://embodied-web-agent.github.io/.
♻ ☆ Sekai: A Video Dataset towards World Exploration
Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well-suited for world exploration training as they suffer from some limitations: limited locations, short duration, static scenes, and a lack of annotations about exploration and the world. In this paper, we introduce Sekai (meaning ``world'' in Japanese), a high-quality first-person view worldwide video dataset with rich annotations for world exploration. It consists of over 5,000 hours of walking or drone view (FPV and UVA) videos from over 100 countries and regions across 750 cities. We develop an efficient and effective toolbox to collect, pre-process and annotate videos with location, scene, weather, crowd density, captions, and camera trajectories. Experiments demonstrate the quality of the dataset. And, we use a subset to train an interactive video world exploration model, named YUME (meaning ``dream'' in Japanese). We believe Sekai will benefit the area of video generation and world exploration, and motivate valuable applications. The project page is https://lixsp11.github.io/sekai-project/.
comment: 12 pages, 6 figures
♻ ☆ One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL.
♻ ☆ Show-o2: Improved Native Unified Multimodal Models
This paper presents improved native unified multimodal models, \emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at https://github.com/showlab/Show-o.
comment: Technical report. (v2: update references and tables)
♻ ☆ Privacy-Preserving Chest X-ray Classification in Latent Space with Homomorphically Encrypted Neural Inference
Medical imaging data contain sensitive patient information requiring strong privacy protection. Many analytical setups require data to be sent to a server for inference purposes. Homomorphic encryption (HE) provides a solution by allowing computations to be performed on encrypted data without revealing the original information. However, HE inference is computationally expensive, particularly for large images (e.g., chest X-rays). In this study, we propose an HE inference framework for medical images that uses VQGAN to compress images into latent representations, thereby significantly reducing the computational burden while preserving image quality. We approximate the activation functions with lower-degree polynomials to balance the accuracy and efficiency in compliance with HE requirements. We observed that a downsampling factor of eight for compression achieved an optimal balance between performance and computational cost. We further adapted the squeeze and excitation module, which is known to improve traditional CNNs, to enhance the HE framework. Our method was tested on two chest X-ray datasets for multi-label classification tasks using vanilla CNN backbones. Although HE inference remains relatively slow and introduces minor performance differences compared with unencrypted inference, our approach shows strong potential for practical use in medical images
comment: 11 pages, 5 figures
♻ ☆ SynPo: Boosting Training-Free Few-Shot Medical Segmentation via High-Quality Negative Prompts MICCAI 2025
The advent of Large Vision Models (LVMs) offers new opportunities for few-shot medical image segmentation. However, existing training-free methods based on LVMs fail to effectively utilize negative prompts, leading to poor performance on low-contrast medical images. To address this issue, we propose SynPo, a training-free few-shot method based on LVMs (e.g., SAM), with the core insight: improving the quality of negative prompts. To select point prompts in a more reliable confidence map, we design a novel Confidence Map Synergy Module by combining the strengths of DINOv2 and SAM. Based on the confidence map, we select the top-k pixels as the positive points set and choose the negative points set using a Gaussian distribution, followed by independent K-means clustering for both sets. Then, these selected points are leveraged as high-quality prompts for SAM to get the segmentation results. Extensive experiments demonstrate that SynPo achieves performance comparable to state-of-the-art training-based few-shot methods.
comment: MICCAI 2025 Early Accept. Project Page: https://liu-yufei.github.io/synpo-project-page/
♻ ☆ BreastDCEDL: Curating a Comprehensive DCE-MRI Dataset and developing a Transformer Implementation for Breast Cancer Treatment Response Prediction
Breast cancer remains a leading cause of cancer-related mortality worldwide, making early detection and accurate treatment response monitoring critical priorities. We present BreastDCEDL, a curated, deep learning-ready dataset comprising pre-treatment 3D Dynamic Contrast-Enhanced MRI (DCE-MRI) scans from 2,070 breast cancer patients drawn from the I-SPY1, I-SPY2, and Duke cohorts, all sourced from The Cancer Imaging Archive. The raw DICOM imaging data were rigorously converted into standardized 3D NIfTI volumes with preserved signal integrity, accompanied by unified tumor annotations and harmonized clinical metadata including pathologic complete response (pCR), hormone receptor (HR), and HER2 status. Although DCE-MRI provides essential diagnostic information and deep learning offers tremendous potential for analyzing such complex data, progress has been limited by lack of accessible, public, multicenter datasets. BreastDCEDL addresses this gap by enabling development of advanced models, including state-of-the-art transformer architectures that require substantial training data. To demonstrate its capacity for robust modeling, we developed the first transformer-based model for breast DCE-MRI, leveraging Vision Transformer (ViT) architecture trained on RGB-fused images from three contrast phases (pre-contrast, early post-contrast, and late post-contrast). Our ViT model achieved state-of-the-art pCR prediction performance in HR+/HER2- patients (AUC 0.94, accuracy 0.93). BreastDCEDL includes predefined benchmark splits, offering a framework for reproducible research and enabling clinically meaningful modeling in breast cancer imaging.
♻ ☆ AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual grounding from aerial views. Compared to traditional VG, AerialVG poses new challenges, \emph{e.g.}, appearance-based grounding is insufficient to distinguish among multiple visually similar objects, and positional relations should be emphasized. Besides, existing VG models struggle when applied to aerial imagery, where high-resolution images cause significant difficulties. To address these challenges, we introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects. Particularly, each annotation in AerialVG dataset contains multiple target objects annotated with relative spatial relations, requiring models to perform comprehensive spatial reasoning. Furthermore, we propose an innovative model especially for the AerialVG task, where a Hierarchical Cross-Attention is devised to focus on target regions, and a Relation-Aware Grounding module is designed to infer positional relations. Experimental results validate the effectiveness of our dataset and method, highlighting the importance of spatial reasoning in aerial visual grounding. The code and dataset will be released.
comment: 8 pages, 6 figures
♻ ☆ Improving Surgical Risk Prediction Through Integrating Automated Body Composition Analysis: a Retrospective Trial on Colectomy Surgery
Objective: To evaluate whether preoperative body composition metrics automatically extracted from CT scans can predict postoperative outcomes after colectomy, either alone or combined with clinical variables or existing risk predictors. Main outcomes and measures: The primary outcome was the predictive performance for 1-year all-cause mortality following colectomy. A Cox proportional hazards model with 1-year follow-up was used, and performance was evaluated using the concordance index (C-index) and Integrated Brier Score (IBS). Secondary outcomes included postoperative complications, unplanned readmission, blood transfusion, and severe infection, assessed using AUC and Brier Score from logistic regression. Odds ratios (OR) described associations between individual CT-derived body composition metrics and outcomes. Over 300 features were extracted from preoperative CTs across multiple vertebral levels, including skeletal muscle area, density, fat areas, and inter-tissue metrics. NSQIP scores were available for all surgeries after 2012.
comment: 32 pages, 5 figures
♻ ☆ MSCA-Net:Multi-Scale Context Aggregation Network for Infrared Small Target Detection
In complex environments, detecting tiny infrared targets has always been challenging because of the low contrast and high noise levels inherent in infrared images. These factors often lead to the loss of crucial details during feature extraction. Moreover, existing detection methods have limitations in adequately integrating global and local information, which constrains the efficiency and accuracy of infrared small target detection. To address these challenges, this paper proposes a network architecture named MSCA-Net, which integrates three key components: Multi-Scale Enhanced Dilated Attention mechanism (MSEDA), Positional Convolutional Block Attention Module (PCBAM), and Channel Aggregation Feature Fusion Block (CAB). Specifically, MSEDA employs a multi-scale feature fusion attention mechanism to adaptively aggregate information across different scales, enriching feature representation. PCBAM captures the correlation between global and local features through a correlation matrix-based strategy, enabling deep feature interaction. Moreover, CAB enhances the representation of critical features by assigning greater weights to them, integrating both low-level and high-level information, and thereby improving the models detection performance in complex backgrounds. The experimental results demonstrate that MSCA-Net achieves strong small target detection performance in complex backgrounds. Specifically, it attains mIoU scores of 78.43%, 94.56%, and 67.08% on the NUAA-SIRST, NUDT-SIRST, and IRTSD-1K datasets, respectively, underscoring its effectiveness and strong potential for real-world applications.
♻ ☆ Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting ICML
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian primitives based on scene characteristics, making it challenging to balance reconstruction quality and efficiency. Inspired by human perception, we propose scene-adaptive perceptual densification for Gaussian Splatting (Perceptual-GS), a novel framework that integrates perceptual sensitivity into the 3DGS training process to address this challenge. We first introduce a perception-aware representation that models human visual sensitivity while constraining the number of Gaussian primitives. Building on this foundation, we develop a perceptual sensitivity-adaptive distribution to allocate finer Gaussian granularity to visually critical regions, enhancing reconstruction quality and robustness. Extensive evaluations on multiple datasets, including BungeeNeRF for large-scale scenes, demonstrate that Perceptual-GS achieves state-of-the-art performance in reconstruction quality, efficiency, and robustness. The code is publicly available at: https://github.com/eezkni/Perceptual-GS
comment: Accepted to International Conference on Machine Learning (ICML) 2025
♻ ☆ Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-aware LiDAR generator with NeRF-based rendering and adaptive sampling. Both modalities are directly coupled through a shared latent space, enabling coherent evolution across visual and geometric domains. To guide the generation with structured semantics, we introduce DataCrafter, a captioning module built on vision-language models that provides scene-level and instance-level supervision. Extensive experiments on the nuScenes benchmark demonstrate that Genesis achieves state-of-the-art performance across video and LiDAR metrics (FVD 16.95, FID 4.24, Chamfer 0.611), and benefits downstream tasks including segmentation and 3D detection, validating the semantic fidelity and practical utility of the generated data.
♻ ☆ DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding ICCV 2025
Despite LiDAR (Light Detection and Ranging) being an effective privacy-preserving alternative to RGB cameras to perceive human activities, it remains largely underexplored in the context of multi-modal contrastive pre-training for human activity understanding (e.g., human activity recognition (HAR), retrieval, or person re-identification (RE-ID)). To close this gap, our work explores learning the correspondence between LiDAR point clouds, human skeleton poses, IMU data, and text in a joint embedding space. More specifically, we present DeSPITE, a Deep Skeleton-Pointcloud-IMU-Text Embedding model, which effectively learns a joint embedding space across these four modalities. At the heart of our empirical exploration, we have combined the existing LIPD and Babel datasets, which enabled us to synchronize data of all four modalities, allowing us to explore the learning of a new joint embedding space. Our experiments demonstrate novel human activity understanding tasks for point cloud sequences enabled through DeSPITE, including Skeleton<->Pointcloud<->IMU matching, retrieval, and temporal moment retrieval. Furthermore, we show that DeSPITE is an effective pre-training strategy for point cloud HAR through experiments in MSR-Action3D and HMPEAR.
comment: This work is currently under review at ICCV 2025
♻ ☆ Decoupled Classifier-Free Guidance for Counterfactual Diffusion Models
Counterfactual image generation aims to simulate realistic visual outcomes under specific causal interventions. Diffusion models have recently emerged as a powerful tool for this task, combining DDIM inversion with conditional generation via classifier-free guidance (CFG). However, standard CFG applies a single global weight across all conditioning variables, which can lead to poor identity preservation and spurious attribute changes - a phenomenon known as attribute amplification. To address this, we propose Decoupled Classifier-Free Guidance (DCFG), a flexible and model-agnostic framework that introduces group-wise conditioning control. DCFG builds on an attribute-split embedding strategy that disentangles semantic inputs, enabling selective guidance on user-defined attribute groups. For counterfactual generation, we partition attributes into intervened and invariant sets based on a causal graph and apply distinct guidance to each. Experiments on CelebA-HQ, MIMIC-CXR, and EMBED show that DCFG improves intervention fidelity, mitigates unintended changes, and enhances reversibility, enabling more faithful and interpretable counterfactual image generation.
♻ ☆ Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Dataset
This paper introduces the Raw Natural Image Noise Dataset (RawNIND), a diverse collection of paired raw images designed to support the development of denoising models that generalize across sensors, image development workflows, and styles. Two denoising methods are proposed: one operates directly on raw Bayer data, leveraging computational efficiency, while the other processes linear RGB images for improved generalization to different sensors, with both preserving flexibility for subsequent development. Both methods outperform traditional approaches which rely on developed images. Additionally, the integration of denoising and compression at the raw data level significantly enhances rate-distortion performance and computational efficiency. These findings suggest a paradigm shift toward raw data workflows for efficient and flexible image processing.
♻ ☆ Efficient Online Inference of Vision Transformers by Training-Free Tokenization
The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to runtime, making them ill-suited for online (real-time) inference, where a prediction is made on any new input as it comes in. We introduce the $\textbf{Visual Word Tokenizer}$ (VWT), a training-free method for reducing energy costs while retaining performance and runtime. The VWT groups visual subwords (image patches) that are frequently used into visual words while infrequent ones remain intact. To do so, $\textit{intra}$-image or $\textit{inter}$-image statistics are leveraged to identify similar visual concepts for sequence compression. Experimentally, we demonstrate a reduction in wattage of up to 25% with only a 20% increase in runtime at most. Comparative approaches of 8-bit quantization and token merging achieve a lower or similar energy efficiency but exact a higher toll on runtime (up to 100% or more). Our results indicate that VWTs are well-suited for efficient online inference with a marginal compromise on performance.
♻ ☆ SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments
We introduce Shakti, a 2.5 billion parameter language model specifically optimized for resource-constrained environments such as edge devices, including smartphones, wearables, and IoT systems. Shakti combines high-performance NLP with optimized efficiency and precision, making it ideal for real-time AI applications where computational resources and memory are limited. With support for vernacular languages and domain-specific tasks, Shakti excels in industries such as healthcare, finance, and customer service. Benchmark evaluations demonstrate that Shakti performs competitively against larger models while maintaining low latency and on-device efficiency, positioning it as a leading solution for edge AI.
comment: Paper in pdf format is 11 pages and contains 4 tables
♻ ☆ SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
Recent advancements in 3D robotic manipulation have improved grasping of everyday objects, but transparent and specular materials remain challenging due to depth sensing limitations. While several 3D reconstruction and depth completion approaches address these challenges, they suffer from setup complexity or limited observation information utilization. To address this, leveraging the power of single view 3D object reconstruction approaches, we propose a training free framework SR3D that enables robotic grasping of transparent and specular objects from a single view observation. Specifically, given single view RGB and depth images, SR3D first uses the external visual models to generate 3D reconstructed object mesh based on RGB image. Then, the key idea is to determine the 3D object's pose and scale to accurately localize the reconstructed object back into its original depth corrupted 3D scene. Therefore, we propose view matching and keypoint matching mechanisms,which leverage both the 2D and 3D's inherent semantic and geometric information in the observation to determine the object's 3D state within the scene, thereby reconstructing an accurate 3D depth map for effective grasp detection. Experiments in both simulation and real world show the reconstruction effectiveness of SR3D.
♻ ☆ Collaborative Perception Datasets for Autonomous Driving: A Review
Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://github.com/frankwnb/Collaborative-Perception-Datasets-for-Autonomous-Driving.
comment: 18pages, 7figures, journal
♻ ☆ Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures CVPR 2025
Real-time free-view human rendering from sparse-view RGB inputs is a challenging task due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods leverage 2D CNNs operating in texture space to learn rendering primitives. However, they either jointly learn geometry and appearance, or completely ignore sparse image information for geometry estimation, significantly harming visual quality and robustness to unseen body poses. To address these issues, we present Double Unprojected Textures, which at the core disentangles coarse geometric deformation estimation from appearance synthesis, enabling robust and photorealistic 4K rendering in real-time. Specifically, we first introduce a novel image-conditioned template deformation network, which estimates the coarse deformation of the human template from a first unprojected texture. This updated geometry is then used to apply a second and more accurate texture unprojection. The resulting texture map has fewer artifacts and better alignment with input views, which benefits our learning of finer-level geometry and appearance represented by Gaussian splats. We validate the effectiveness and efficiency of the proposed method in quantitative and qualitative experiments, which significantly surpasses other state-of-the-art methods. Project page: https://vcai.mpi-inf.mpg.de/projects/DUT/
comment: Accepted at CVPR 2025, Project page: https://vcai.mpi-inf.mpg.de/projects/DUT/
♻ ☆ Deep Learning based Visually Rich Document Content Understanding: A Survey
Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting information from VRDs rely heavily on expert knowledge and manual annotation, making them labor-intensive and inefficient. Recent advances in deep learning have transformed this landscape by enabling multimodal models that integrate vision, language, and layout features through pretraining, significantly improving information extraction performance. This survey presents a comprehensive overview of deep learning-based frameworks for VRD Content Understanding (VRD-CU). We categorize existing methods based on their modeling strategies and downstream tasks, and provide a comparative analysis of key components, including feature representation, fusion techniques, model architectures, and pretraining objectives. Additionally, we highlight the strengths and limitations of each approach and discuss their suitability for different applications. The paper concludes with a discussion of current challenges and emerging trends, offering guidance for future research and practical deployment in real-world scenarios.
comment: Work in Progress
♻ ☆ Generalized Category Discovery under the Long-Tailed Distribution
This paper addresses the problem of Generalized Category Discovery (GCD) under a long-tailed distribution, which involves discovering novel categories in an unlabelled dataset using knowledge from a set of labelled categories. Existing works assume a uniform distribution for both datasets, but real-world data often exhibits a long-tailed distribution, where a few categories contain most examples, while others have only a few. While the long-tailed distribution is well-studied in supervised and semi-supervised settings, it remains unexplored in the GCD context. We identify two challenges in this setting - balancing classifier learning and estimating category numbers - and propose a framework based on confident sample selection and density-based clustering to tackle them. Our experiments on both long-tailed and conventional GCD datasets demonstrate the effectiveness of our method.
♻ ☆ GenLit: Reformulating Single-Image Relighting as Video Generation
Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics. This problem has traditionally been addressed using inverse rendering techniques, which involve explicit 3D asset reconstruction and costly ray-tracing simulations. Meanwhile, recent advancements in visual foundation models suggest that a new paradigm could soon be possible -- one that replaces explicit physical models with networks that are trained on large amounts of image and video data. In this paper, we exploit the physical world understanding of a video diffusion model, particularly Stable Video Diffusion, to relight a single image. We introduce GenLit, a framework that distills the ability of a graphics engine to perform light manipulation into a video-generation model, enabling users to directly insert and manipulate a point light in the 3D world within a given image, and generate results directly as a video sequence. We find that a model fine-tuned on only a small synthetic dataset generalizes to real-world scenes, enabling single-image relighting with plausible and convincing shadows. Our results highlight the ability of video foundation models to capture rich information about lighting, material, and, shape and our findings indicate that such models, with minimal training, can be used to perform relighting without explicit asset reconstruction or complex ray tracing. Project page: https://genlit.is.tue.mpg.de/.
♻ ☆ Training Multi-Layer Binary Neural Networks With Local Binary Error Signals
Binary Neural Networks (BNNs) significantly reduce computational complexity and memory usage in machine and deep learning by representing weights and activations with just one bit. However, most existing training algorithms for BNNs rely on quantization-aware floating-point Stochastic Gradient Descent (SGD), limiting the full exploitation of binary operations to the inference phase only. In this work, we propose, for the first time, a fully binary and gradient-free training algorithm for multi-layer BNNs, eliminating the need for back-propagated floating-point gradients. Specifically, the proposed algorithm relies on local binary error signals and binary weight updates, employing integer-valued hidden weights that serve as a synaptic metaplasticity mechanism, thereby enhancing its neurobiological plausibility. Our proposed solution enables the training of binary multi-layer perceptrons by using exclusively XNOR, Popcount, and increment/decrement operations. Experimental results on multi-class classification benchmarks show test accuracy improvements of up to +35.47% over the only existing fully binary single-layer state-of-the-art solution. Compared to full-precision SGD, our solution improves test accuracy by up to +35.30% under the same total memory demand, while also reducing computational cost by two to three orders of magnitude in terms of the total number of Boolean gates. The proposed algorithm is made available to the scientific community as a public repository.
♻ ☆ ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation ACL 2024
Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard data filtering approaches succeed in removing mismatched text-image pairs, but permit semantically related but highly abstract or subjective text. These approaches lack the fine-grained ability to isolate the most concrete samples that provide the strongest signal for learning in a noisy dataset. In this work, we propose a new metric, image caption concreteness, that evaluates caption text without an image reference to measure its concreteness and relevancy for use in multimodal learning. Our approach leverages strong foundation models for measuring visual-semantic information loss in multimodal representations. We demonstrate that this strongly correlates with human evaluation of concreteness in both single-word and sentence-level texts. Moreover, we show that curation using ICC complements existing approaches: It succeeds in selecting the highest quality samples from multimodal web-scale datasets to allow for efficient training in resource-constrained settings.
comment: Accepted to ACL 2024 (Finding). For Project webpage, see https://moranyanuka.github.io/icc/
♻ ☆ 360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos
Visual object tracking and segmentation in omnidirectional videos are challenging due to the wide field-of-view and large spherical distortion brought by 360{\deg} images. To alleviate these problems, we introduce a novel representation, extended bounding field-of-view (eBFoV), for target localization and use it as the foundation of a general 360 tracking framework which is applicable for both omnidirectional visual object tracking and segmentation tasks. Building upon our previous work on omnidirectional visual object tracking (360VOT), we propose a comprehensive dataset and benchmark that incorporates a new component called omnidirectional video object segmentation (360VOS). The 360VOS dataset includes 290 sequences accompanied by dense pixel-wise masks and covers a broader range of target categories. To support both the development and evaluation of algorithms in this domain, we divide the dataset into a training subset with 170 sequences and a testing subset with 120 sequences. Furthermore, we tailor evaluation metrics for both omnidirectional tracking and segmentation to ensure rigorous assessment. Through extensive experiments, we benchmark state-of-the-art approaches and demonstrate the effectiveness of our proposed 360 tracking framework and training dataset. Homepage: https://360vots.hkustvgd.com/
comment: arXiv admin note: substantial text overlap with arXiv:2307.14630
♻ ☆ Bridging Domain Gaps in Agricultural Image Analysis: A Comprehensive Review From Shallow Adaptation to Deep Learning
With the growing application of computer vision in agriculture, image analysis has become essential for tasks such as crop health monitoring and pest detection. However, significant domain shifts caused by environmental variations, different crop types, and diverse data acquisition methods hinder model generalization across regions, seasons, and complex agricultural settings. This paper investigates how Domain Adaptation (DA) techniques can address these challenges by improving cross-domain transferability in agricultural image analysis. Given the limited availability of labeled data, weak model adaptability, and dynamic field conditions, DA has emerged as a promising solution. The review systematically summarizes recent advances in DA for agricultural imagery, focusing on applications such as crop health monitoring, pest detection, and fruit recognition, where DA methods have enhanced performance across diverse domains. DA approaches are categorized into shallow and deep learning methods, including supervised, semi-supervised, and unsupervised strategies, with particular attention to adversarial learning-based techniques that have demonstrated strong potential in complex scenarios. In addition, the paper reviews key public agricultural image datasets, evaluating their strengths and limitations in DA research. Overall, this work offers a comprehensive framework and critical insights to guide future research and development of domain adaptation in agricultural vision tasks.
♻ ☆ More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability often comes with increased hallucination: as generations become longer, models tend to drift away from image-grounded content and rely more heavily on language priors. Attention analysis shows that longer reasoning chains lead to reduced focus on visual inputs, which contributes to hallucination. To systematically study this phenomenon, we introduce RH-AUC, a metric that quantifies how a model's perception accuracy changes with reasoning length, allowing us to evaluate whether the model preserves visual grounding during reasoning. We also release RH-Bench, a diagnostic benchmark that spans a variety of multimodal tasks, designed to assess the trade-off between reasoning ability and hallucination. Our analysis reveals that (i) larger models typically achieve a better balance between reasoning and perception, and (ii) this balance is influenced more by the types and domains of training data than by its overall volume. These findings underscore the importance of evaluation frameworks that jointly consider both reasoning quality and perceptual fidelity.
♻ ☆ When and How Does CLIP Enable Domain and Compositional Generalization? ICML 2025
The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely unseen domain when trained on a diverse mixture of domains (domain generalization)? Can it generalize to unseen classes within partially seen domains (compositional generalization)? What factors affect such generalization? To answer these questions, we trained CLIP models on systematically constructed training distributions with controlled domain diversity and object class exposure. Our experiments show that domain diversity is essential for both domain and compositional generalization, yet compositional generalization can be surprisingly weaker than domain generalization when the training distribution contains a suboptimal subset of the test domain. Through data-centric and mechanistic analyses, we find that successful generalization requires the learning of sufficiently shared representations in intermediate layers and circuits.
comment: ICML 2025 (Spotlight)
♻ ☆ Cost-effective Instruction Learning for Pathology Vision and Language Analysis
The advent of vision-language models fosters the interactive conversations between AI-enabled models and humans. Yet applying these models into clinics must deal with daunting challenges around large-scale training data, financial, and computational resources. Here we propose a cost-effective instruction learning framework for conversational pathology named as CLOVER. CLOVER only trains a lightweight module and uses instruction tuning while freezing the parameters of the large language model. Instead of using costly GPT-4, we propose well-designed prompts on GPT-3.5 for building generation-based instructions, emphasizing the utility of pathological knowledge derived from the Internet source. To augment the use of instructions, we construct a high-quality set of template-based instructions in the context of digital pathology. From two benchmark datasets, our findings reveal the strength of hybrid-form instructions in the visual question-answer in pathology. Extensive results show the cost-effectiveness of CLOVER in answering both open-ended and closed-ended questions, where CLOVER outperforms strong baselines that possess 37 times more training parameters and use instruction data generated from GPT-4. Through the instruction tuning, CLOVER exhibits robustness of few-shot learning in the external clinical dataset. These findings demonstrate that cost-effective modeling of CLOVER could accelerate the adoption of rapid conversational applications in the landscape of digital pathology.
♻ ☆ Memory-enhanced Retrieval Augmentation for Long Video Understanding
Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to compression and brute-force downsampling. While retrieval-augmented generation (RAG) methods mitigate this issue, their applicability is limited due to explicit query dependency. To overcome this challenge, we introduce a novel memory-enhanced RAG-based approach called MemVid, which is inspired by the cognitive memory of human beings. Our approach operates in four basic steps: 1) memorizing holistic video information, 2) reasoning about the task's information needs based on memory, 3) retrieving critical moments based on the information needs, and 4) focusing on the retrieved moments to produce the final answer. To enhance the system's memory-grounded reasoning capabilities while achieving optimal end-to-end performance, we propose a curriculum learning strategy. This approach begins with supervised learning on well-annotated reasoning results, then progressively explores and reinforces more plausible reasoning outcomes through reinforcement learning. We perform extensive evaluations on popular LVU benchmarks, including MLVU, VideoMME and LVBench. In our experiments, MemVid demonstrates superior efficiency and effectiveness compared to both LVLMs and RAG methods.
♻ ☆ IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domain
Recently, the rapid advancements of vision-language models, such as CLIP, leads to significant progress in zero-/few-shot anomaly detection (ZFSAD) tasks. However, most existing CLIP-based ZFSAD methods commonly assume prior knowledge of categories and rely on carefully crafted prompts tailored to specific scenarios. While such meticulously designed text prompts effectively capture semantic information in the textual space, they fall short of distinguishing normal and anomalous instances within the joint embedding space. Moreover, these ZFSAD methods are predominantly explored in industrial scenarios, with few efforts conducted to medical tasks. To this end, we propose an innovative framework for ZFSAD tasks in medical domain, denoted as IQE-CLIP. We reveal that query embeddings, which incorporate both textual and instance-aware visual information, are better indicators for abnormalities. Specifically, we first introduce class-based prompting tokens and learnable prompting tokens for better adaptation of CLIP to the medical domain. Then, we design an instance-aware query module (IQM) to extract region-level contextual information from both text prompts and visual features, enabling the generation of query embeddings that are more sensitive to anomalies. Extensive experiments conducted on six medical datasets demonstrate that IQE-CLIP achieves state-of-the-art performance on both zero-shot and few-shot tasks. We release our code and data at https://github.com/hongh0/IQE-CLIP/.
♻ ☆ A CLIP-Powered Framework for Robust and Generalizable Data Selection ICLR 2025
Large-scale datasets have been pivotal to the advancements of deep learning models in recent years, but training on such large datasets invariably incurs substantial storage and computational overhead. Meanwhile, real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance. Data selection has shown promise in identifying the most representative samples from the entire dataset, which aims to minimize the performance gap with reduced training costs. Existing works typically rely on single-modality information to assign importance scores for individual samples, which may lead to inaccurate assessments, especially when dealing with noisy or corrupted samples. To address this limitation, we propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection. Specifically, our framework consists of three key modules-dataset adaptation, sample scoring, and selection optimization-that together harness extensive pre-trained multimodal knowledge to comprehensively assess sample influence and optimize the selection results through multi-objective optimization. Extensive experiments demonstrate that our approach consistently outperforms existing state-of-the-art baselines on various benchmark datasets. Notably, our method effectively removes noisy or damaged samples from the dataset, enabling it to achieve even higher performance with less data. This indicates that it is not only a way to accelerate training but can also improve overall data quality.
comment: ICLR 2025 Spotlight
♻ ☆ Efficient Depth-Guided Urban View Synthesis ECCV2024
Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images and extensive computation resources. To mitigate this shortcoming, we introduce a new method called Efficient Depth-Guided Urban View Synthesis (EDUS) for fast feed-forward inference and efficient per-scene fine-tuning. Different from prior generalizable methods that infer geometry based on feature matching, EDUS leverages noisy predicted geometric priors as guidance to enable generalizable urban view synthesis from sparse input images. The geometric priors allow us to apply our generalizable model directly in the 3D space, gaining robustness across various sparsity levels. Through comprehensive experiments on the KITTI-360 and Waymo datasets, we demonstrate promising generalization abilities on novel street scenes. Moreover, our results indicate that EDUS achieves state-of-the-art performance in sparse view settings when combined with fast test-time optimization.
comment: ECCV2024, Project page: https://xdimlab.github.io/EDUS/
♻ ☆ Medical Artificial Intelligence for Early Detection of Lung Cancer: A Survey
Lung cancer remains one of the leading causes of morbidity and mortality worldwide, making early diagnosis critical for improving therapeutic outcomes and patient prognosis. Computer-aided diagnosis systems, which analyze computed tomography images, have proven effective in detecting and classifying pulmonary nodules, significantly enhancing the detection rate of early-stage lung cancer. Although traditional machine learning algorithms have been valuable, they exhibit limitations in handling complex sample data. The recent emergence of deep learning has revolutionized medical image analysis, driving substantial advancements in this field. This review focuses on recent progress in deep learning for pulmonary nodule detection, segmentation, and classification. Traditional machine learning methods, such as support vector machines and k-nearest neighbors, have shown limitations, paving the way for advanced approaches like Convolutional Neural Networks, Recurrent Neural Networks, and Generative Adversarial Networks. The integration of ensemble models and novel techniques is also discussed, emphasizing the latest developments in lung cancer diagnosis. Deep learning algorithms, combined with various analytical techniques, have markedly improved the accuracy and efficiency of pulmonary nodule analysis, surpassing traditional methods, particularly in nodule classification. Although challenges remain, continuous technological advancements are expected to further strengthen the role of deep learning in medical diagnostics, especially for early lung cancer detection and diagnosis. A comprehensive list of lung cancer detection models reviewed in this work is available at https://github.com/CaiGuoHui123/Awesome-Lung-Cancer-Detection.
comment: Accepted to Engineering Applications of Artificial Intelligence
♻ ☆ Label-guided Facial Retouching Reversion ICME2025
With the popularity of social media platforms and retouching tools, more people are beautifying their facial photos, posing challenges for fields requiring photo authenticity. To address this issue, some work has proposed makeup removal methods, but they cannot revert images involving geometric deformations caused by retouching. To tackle the problem of facial retouching reversion, we propose a framework, dubbed Re-Face, which consists of three components: a facial retouching detector, an image reversion model named FaceR, and a color correction module called Hierarchical Adaptive Instance Normalization (H-AdaIN). FaceR can utilize labels generated by the facial retouching detector as guidance to revert the retouched facial images. Then, color correction is performed using H-AdaIN to address the issue of color shift. Extensive experiments demonstrate the effectiveness of our framework and each module.
comment: ICME2025 Oral
♻ ☆ DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training quantization (PTQ) reduces model size and speeds up inference, it often degrades performance, especially in low-bit settings. We identify two key reasons for the performance degradation: 1) existing quantization methods fail to align with the power-law distribution of post-Softmax activations, and 2) reparameterizing post-LayerNorm activations leads to a performance drop due to the significant influence of outliers in the scaling factors. To address these challenges, we propose DopQ-ViT, a Distribution-friendly and Outlier-aware Post-training Quantization method for ViTs. First, DopQ-ViT introduces the Tan Quantizer (TanQ), which better preserves the power-law distribution of post-Softmax activations by focusing more on values near 1. Second, DopQ-ViT presents the MAD-guided Optimal Scaling Factor (MOSF), which selects the optimal scaling factor without introducing additional calculations. Extensive experiments across various ViT models and quantization settings demonstrate that DopQ-ViT, with the help of TanQ and MOSF, outperforms previous PTQ methods on both classification and detection tasks.
♻ ☆ MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension EMNLP 2024
Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer visual/linguistic knowledge by full fine-tuning. However, full fine-tuning the entire backbone not only breaks the rich prior knowledge embedded in the pre-training, but also incurs significant computational costs. Motivated by the recent emergence of Parameter-Efficient Transfer Learning (PETL) methods, we aim to solve the REC task in an effective and efficient manner. Directly applying these PETL methods to the REC task is inappropriate, as they lack the specific-domain abilities for precise local visual perception and visual-language alignment. Therefore, we propose a novel framework of Multimodal Prior-guided Parameter Efficient Tuning, namely MaPPER. Specifically, MaPPER comprises Dynamic Prior Adapters guided by an aligned prior, and Local Convolution Adapters to extract precise local semantics for better visual perception. Moreover, the Prior-Guided Text module is proposed to further utilize the prior for facilitating the cross-modal alignment. Experimental results on three widely-used benchmarks demonstrate that MaPPER achieves the best accuracy compared to the full fine-tuning and other PETL methods with only 1.41% tunable backbone parameters. Our code is available at https://github.com/liuting20/MaPPER.
comment: EMNLP 2024 main
♻ ☆ LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, limiting flexibility for specific edits. First-frame-guided editing provides control over the first frame, but lacks flexibility over subsequent frames. To address this, we propose a mask-based LoRA (Low-Rank Adaptation) tuning method that adapts pretrained Image-to-Video (I2V) models for flexible video editing. Our approach preserves background regions while enabling controllable edits propagation. This solution offers efficient and adaptable video editing without altering the model architecture. To better steer this process, we incorporate additional references, such as alternate viewpoints or representative scene states, which serve as visual anchors for how content should unfold. We address the control challenge using a mask-driven LoRA tuning strategy that adapts a pre-trained image-to-video model to the editing context. The model must learn from two distinct sources: the input video provides spatial structure and motion cues, while reference images offer appearance guidance. A spatial mask enables region-specific learning by dynamically modulating what the model attends to, ensuring that each area draws from the appropriate source. Experimental results show our method achieves superior video editing performance compared to state-of-the-art methods. Project Page: https://cjeen.github.io/LoraEditPaper
comment: 12 pages
♻ ☆ Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
Out-of-Distribution (OOD) detection is essential for the trustworthiness of AI systems. Methods using prior information (i.e., subspace-based methods) have shown effective performance by extracting information geometry to detect OOD data with a more appropriate distance metric. However, these methods fail to address the geometry distorted by ill-distributed samples, due to the limitation of statically extracting information geometry from the training distribution. In this paper, we argue that the influence of ill-distributed samples can be corrected by dynamically adjusting the prior geometry in response to new data. Based on this insight, we propose a novel approach that dynamically updates the prior covariance matrix using real-time input features, refining its information. Specifically, we reduce the covariance along the direction of real-time input features and constrain adjustments to the residual space, thus preserving essential data characteristics and avoiding effects on unintended directions in the principal space. We evaluate our method on two pre-trained models for the CIFAR dataset and five pre-trained models for ImageNet-1k, including the self-supervised DINO model. Extensive experiments demonstrate that our approach significantly enhances OOD detection across various models. The code is released at https://github.com/workerbcd/ooddcc.
♻ ☆ Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach
Data augmentation is widely applied and has shown its benefits in different machine learning tasks. However, as recently observed, it may have an unfair effect in multi-class classification. While data augmentation generally improves the overall performance (and therefore is beneficial for many classes), it can actually be detrimental for other classes, which can be problematic in some application domains. In this paper, to counteract this phenomenon, we propose CLAM, a CLAss-dependent Multiplicative-weights method. To derive it, we first formulate the training of a classifier as a non-linear optimization problem that aims at simultaneously maximizing the individual class performances and balancing them. By rewriting this optimization problem as an adversarial two-player game, we propose a novel multiplicative weight algorithm, for which we prove the convergence. Interestingly, our formulation also reveals that the class-dependent effects of data augmentation is not due to data augmentation only, but is in fact a general phenomenon. Our empirical results over six datasets demonstrate that the performance of learned classifiers is indeed more fairly distributed over classes, with only limited impact on the average accuracy.
♻ ☆ Cross-Modal Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition
LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent point cloud density, induced by ego-motion dynamics and environmental disturbances during repeated traversals, leads to descriptor instability, and (2) Representation fragility stems from reliance on single-level geometric abstractions that lack discriminative power in structurally complex scenarios. To address these limitations, we propose a novel framework that redefines 3D place recognition through density-agnostic geometric reasoning. Specifically, we introduce an implicit 3D representation based on elastic points, which is immune to the interference of original scene point cloud density and achieves the characteristic of uniform distribution. Subsequently, we derive the occupancy grid and normal vector information of the scene from this implicit representation. Finally, with the aid of these two types of information, we obtain descriptors that fuse geometric information from both bird's-eye view (capturing macro-level spatial layouts) and 3D segment (encoding micro-scale surface geometries) perspectives. We conducted extensive experiments on numerous datasets (KITTI, KITTI-360, MulRan, NCLT) across diverse environments. The experimental results demonstrate that our method achieves state-of-the-art performance. Moreover, our approach strikes an optimal balance between accuracy, runtime, and memory optimization for historical maps, showcasing excellent Resilient and scalability. Our code will be open-sourced in the future.
♻ ☆ Demographics-Informed Neural Network for Multi-Modal Spatiotemporal forecasting of Urban Growth and Travel Patterns Using Satellite Imagery
This study presents a novel demographics informed deep learning framework designed to forecast urban spatial transformations by jointly modeling geographic satellite imagery, socio-demographics, and travel behavior dynamics. The proposed model employs an encoder-decoder architecture with temporal gated residual connections, integrating satellite imagery and demographic data to accurately forecast future spatial transformations. The study also introduces a demographics prediction component which ensures that predicted satellite imagery are consistent with demographic features, significantly enhancing physiological realism and socioeconomic accuracy. The framework is enhanced by a proposed multi-objective loss function complemented by a semantic loss function that balances visual realism with temporal coherence. The experimental results from this study demonstrate the superior performance of the proposed model compared to state-of-the-art models, achieving higher structural similarity (SSIM: 0.8342) and significantly improved demographic consistency (Demo-loss: 0.14 versus 0.95 and 0.96 for baseline models). Additionally, the study validates co-evolutionary theories of urban development, demonstrating quantifiable bidirectional influences between built environment characteristics and population patterns. The study also contributes a comprehensive multimodal dataset pairing satellite imagery sequences (2012-2023) with corresponding demographic and travel behavior attributes, addressing existing gaps in urban and transportation planning resources by explicitly connecting physical landscape evolution with socio-demographic patterns.
♻ ☆ NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)
In March 2020, Neural Radiance Field (NeRF) revolutionized Computer Vision, allowing for implicit, neural network-based scene representation and novel view synthesis. NeRF models have found diverse applications in robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, and more. In August 2023, Gaussian Splatting, a direct competitor to the NeRF-based framework, was proposed, gaining tremendous momentum and overtaking NeRF-based research in terms of interest as the dominant framework for novel view synthesis. We present a comprehensive survey of NeRF papers from the past five years (2020-2025). These include papers from the pre-Gaussian Splatting era, where NeRF dominated the field for novel view synthesis and 3D implicit and hybrid representation neural field learning. We also include works from the post-Gaussian Splatting era where NeRF and implicit/hybrid neural fields found more niche applications. Our survey is organized into architecture and application-based taxonomies in the pre-Gaussian Splatting era, as well as a categorization of active research areas for NeRF, neural field, and implicit/hybrid neural representation methods. We provide an introduction to the theory of NeRF and its training via differentiable volume rendering. We also present a benchmark comparison of the performance and speed of classical NeRF, implicit and hybrid neural representation, and neural field models, and an overview of key datasets.
comment: Updated Post-Gaussian Splatting
♻ ☆ Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning
3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation. However, this approach heavily relies on labor-intensive and time-consuming fully annotated ground-truth labels, particularly for 3D volumes. To overcome this limitation, we propose a novel probabilistic-aware weakly supervised learning pipeline, specifically designed for 3D medical imaging. Our pipeline integrates three innovative components: a Probability-based Pseudo Label Generation technique for synthesizing dense segmentation masks from sparse annotations, a Probabilistic Multi-head Self-Attention network for robust feature extraction within our Probabilistic Transformer Network, and a Probability-informed Segmentation Loss Function to enhance training with annotation confidence. Demonstrating significant advances, our approach not only rivals the performance of fully supervised methods but also surpasses existing weakly supervised methods in CT and MRI datasets, achieving up to 18.1% improvement in Dice scores for certain organs. The code is available at https://github.com/runminjiang/PW4MedSeg.
♻ ☆ CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis
Cryo-electron microscopy (cryo-EM) offers near-atomic resolution imaging of macromolecules, but developing robust models for downstream analysis is hindered by the scarcity of high-quality annotated data. While synthetic data generation has emerged as a potential solution, existing methods often fail to capture both the structural diversity of biological specimens and the complex, spatially varying noise inherent in cryo-EM imaging. To overcome these limitations, we propose CryoCCD, a synthesis framework that integrates biophysical modeling with generative techniques. Specifically, CryoCCD produces multi-scale cryo-EM micrographs that reflect realistic biophysical variability through compositional heterogeneity, cellular context, and physics-informed imaging. To generate realistic noise, we employ a conditional diffusion model, enhanced by cycle consistency to preserve structural fidelity and mask-aware contrastive learning to capture spatially adaptive noise patterns. Extensive experiments show that CryoCCD generates structurally accurate micrographs and enhances performance in downstream tasks, outperforming state-of-the-art baselines in both particle picking and reconstruction.
♻ ☆ Event Cameras Meet SPADs for High-Speed, Low-Bandwidth Imaging
Traditional cameras face a trade-off between low-light performance and high-speed imaging: longer exposure times to capture sufficient light results in motion blur, whereas shorter exposures result in Poisson-corrupted noisy images. While burst photography techniques help mitigate this tradeoff, conventional cameras are fundamentally limited in their sensor noise characteristics. Event cameras and single-photon avalanche diode (SPAD) sensors have emerged as promising alternatives to conventional cameras due to their desirable properties. SPADs are capable of single-photon sensitivity with microsecond temporal resolution, and event cameras can measure brightness changes up to 1 MHz with low bandwidth requirements. We show that these properties are complementary, and can help achieve low-light, high-speed image reconstruction with low bandwidth requirements. We introduce a sensor fusion framework to combine SPADs with event cameras to improves the reconstruction of high-speed, low-light scenes while reducing the high bandwidth cost associated with using every SPAD frame. Our evaluation, on both synthetic and real sensor data, demonstrates significant enhancements ( > 5 dB PSNR) in reconstructing low-light scenes at high temporal resolution (100 kHz) compared to conventional cameras. Event-SPAD fusion shows great promise for real-world applications, such as robotics or medical imaging.
comment: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
♻ ☆ SD++: Enhancing Standard Definition Maps by Incorporating Road Knowledge using LLMs
High-definition maps (HD maps) are detailed and informative maps capturing lane centerlines and road elements. Although very useful for autonomous driving, HD maps are costly to build and maintain. Furthermore, access to these high-quality maps is usually limited to the firms that build them. On the other hand, standard definition (SD) maps provide road centerlines with an accuracy of a few meters. In this paper, we explore the possibility of enhancing SD maps by incorporating information from road manuals using LLMs. We develop SD++, an end-to-end pipeline to enhance SD maps with location-dependent road information obtained from a road manual. We suggest and compare several ways of using LLMs for such a task. Furthermore, we show the generalization ability of SD++ by showing results from both California and Japan.
comment: 7 pages, 8 figures, 1 table, Accepted at IEEE Intelligent Vehicles Symposium 2025
Information Retrieval 19
☆ Towards AI Search Paradigm
In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-making. The paradigm employs a modular architecture of four LLM-powered agents (Master, Planner, Executor and Writer) that dynamically adapt to the full spectrum of information needs, from simple factual queries to complex multi-stage reasoning tasks. These agents collaborate dynamically through coordinated workflows to evaluate query complexity, decompose problems into executable plans, and orchestrate tool usage, task execution, and content synthesis. We systematically present key methodologies for realizing this paradigm, including task planning and tool integration, execution strategies, aligned and robust retrieval-augmented generation, and efficient LLM inference, spanning both algorithmic techniques and infrastructure-level optimizations. By providing an in-depth guide to these foundational components, this work aims to inform the development of trustworthy, adaptive, and scalable AI search systems.
☆ Universal Music Representations? Evaluating Foundation Models on World Music Corpora
Foundation models have revolutionized music information retrieval, but questions remain about their ability to generalize across diverse musical traditions. This paper presents a comprehensive evaluation of five state-of-the-art audio foundation models across six musical corpora spanning Western popular, Greek, Turkish, and Indian classical traditions. We employ three complementary methodologies to investigate these models' cross-cultural capabilities: probing to assess inherent representations, targeted supervised fine-tuning of 1-2 layers, and multi-label few-shot learning for low-resource scenarios. Our analysis shows varying cross-cultural generalization, with larger models typically outperforming on non-Western music, though results decline for culturally distant traditions. Notably, our approaches achieve state-of-the-art performance on five out of six evaluated datasets, demonstrating the effectiveness of foundation models for world music understanding. We also find that our targeted fine-tuning approach does not consistently outperform probing across all settings, suggesting foundation models already encode substantial musical knowledge. Our evaluation framework and benchmarking results contribute to understanding how far current models are from achieving universal music representations while establishing metrics for future progress.
comment: Accepted at ISMIR 2025
☆ PersonalAI: Towards digital twins in the graph form
The challenge of personalizing language models, specifically the ability to account for a user's history during interactions, is of significant interest. Despite recent advancements in large language models (LLMs) and Retrieval Augmented Generation that have enhanced the factual base of LLMs, the task of retaining extensive personal information and using it to generate personalized responses remains pertinent. To address this, we propose utilizing external memory in the form of knowledge graphs, which are constructed and updated by the LLM itself. We have expanded upon ideas of AriGraph architecture and for the first time introduced a combined graph featuring both standard edges and two types of hyperedges. Experiments conducted on the TriviaQA, HotpotQA and DiaASQ benchmarks indicates that this approach aids in making the process of graph construction and knowledge extraction unified and robust. Furthermore, we augmented the DiaASQ benchmark by incorporating parameters such as time into dialogues and introducing contradictory statements made by the same speaker at different times. Despite these modifications, the performance of the question-answering system remained robust, demonstrating the proposed architecture's ability to maintain and utilize temporal dependencies.
☆ RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering SIGIR 2025
We present RAGentA, a multi-agent retrieval-augmented generation (RAG) framework for attributed question answering (QA). With the goal of trustworthy answer generation, RAGentA focuses on optimizing answer correctness, defined by coverage and relevance to the question and faithfulness, which measures the extent to which answers are grounded in retrieved documents. RAGentA uses a multi-agent architecture that iteratively filters retrieved documents, generates attributed answers with in-line citations, and verifies completeness through dynamic refinement. Central to the framework is a hybrid retrieval strategy that combines sparse and dense methods, improving Recall@20 by 12.5% compared to the best single retrieval model, resulting in more correct and well-supported answers. Evaluated on a synthetic QA dataset derived from the FineWeb index, RAGentA outperforms standard RAG baselines, achieving gains of 1.09% in correctness and 10.72% in faithfulness. These results demonstrate the effectiveness of the multi-agent architecture and hybrid retrieval in advancing trustworthy QA.
comment: Accepted at SIGIR 2025
☆ Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation SIGIR'25
Sequential recommendation, a critical task in recommendation systems, predicts the next user action based on the understanding of the user's historical behaviors. Conventional studies mainly focus on cross-behavior modeling with self-attention based methods while neglecting comprehensive user interest modeling for more dimensions. In this study, we propose a novel sequential recommendation model, Pyramid Mixer, which leverages the MLP-Mixer architecture to achieve efficient and complete modeling of user interests. Our method learns comprehensive user interests via cross-behavior and cross-feature user sequence modeling. The mixer layers are stacked in a pyramid way for cross-period user temporal interest learning. Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a +0.106% improvement in user stay duration and a +0.0113% increase in user active days in the online A/B test. The Pyramid Mixer has been successfully deployed on the industrial platform, demonstrating its scalability and impact in real-world applications.
comment: Accepted by SIGIR'25
☆ Multi-Objective Recommendation in the Era of Generative AI: A Survey of Recent Progress and Future Prospects
With the recent progress in generative artificial intelligence (Generative AI), particularly in the development of large language models, recommendation systems are evolving to become more versatile. Unlike traditional techniques, generative AI not only learns patterns and representations from complex data but also enables content generation, data synthesis, and personalized experiences. This generative capability plays a crucial role in the field of recommendation systems, helping to address the issue of data sparsity and improving the overall performance of recommendation systems. Numerous studies on generative AI have already emerged in the field of recommendation systems. Meanwhile, the current requirements for recommendation systems have surpassed the single utility of accuracy, leading to a proliferation of multi-objective research that considers various goals in recommendation systems. However, to the best of our knowledge, there remains a lack of comprehensive studies on multi-objective recommendation systems based on generative AI technologies, leaving a significant gap in the literature. Therefore, we investigate the existing research on multi-objective recommendation systems involving generative AI to bridge this gap. We compile current research on multi-objective recommendation systems based on generative techniques, categorizing them by objectives. Additionally, we summarize relevant evaluation metrics and commonly used datasets, concluding with an analysis of the challenges and future directions in this domain.
comment: 21 pages
☆ eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing
We introduce eSapiens, a unified question-answering system designed for enterprise settings, which bridges structured databases and unstructured textual corpora via a dual-module architecture. The system combines a Text-to-SQL planner with a hybrid Retrieval-Augmented Generation (RAG) pipeline, enabling natural language access to both relational data and free-form documents. To enhance answer faithfulness, the RAG module integrates dense and sparse retrieval, commercial reranking, and a citation verification loop that ensures grounding consistency. We evaluate eSapiens on the RAGTruth benchmark across five leading large language models (LLMs), analyzing performance across key dimensions such as completeness, hallucination, and context utilization. Results demonstrate that eSapiens outperforms a FAISS baseline in contextual relevance and generation quality, with optional strict-grounding controls for high-stakes scenarios. This work provides a deployable framework for robust, citation-aware question answering in real-world enterprise applications.
☆ A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation
Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recommendation systems, this approach becomes increasingly cumbersome due to the redundancy and sheer scale of the token space. To overcome these limitations, recent research has explored the use of semantic tokens as an alternative to ID tokens, which typically leveraged reconstruction-based strategies, like RQ-VAE, to quantize content embeddings and significantly reduce the embedding size. However, reconstructive quantization aims for the precise reconstruction of each item embedding independently, which conflicts with the goal of generative retrieval tasks focusing more on differentiating among items. Moreover, multi-modal side information of items, such as descriptive text and images, geographical knowledge in location-based recommendation services, has been shown to be effective in improving recommendations by providing richer contexts for interactions. Nevertheless, effectively integrating such complementary knowledge into existing generative recommendation frameworks remains challenging. To overcome these challenges, we propose a novel unsupervised deep quantization exclusively based on contrastive learning, named SimCIT (a Simple Contrastive Item Tokenization framework). Specifically, different from existing reconstruction-based strategies, SimCIT propose to use a learnable residual quantization module to align with the signals from different modalities of the items, which combines multi-modal knowledge alignment and semantic tokenization in a mutually beneficial contrastive learning framework. Extensive experiments across public datasets and a large-scale industrial dataset from various domains demonstrate SimCIT's effectiveness in LLM-based generative recommendation.
comment: 12 pages,7 figures
☆ Mapping the Evolution of Research Contributions using KnoVo
This paper presents KnoVo (Knowledge Evolution), an intelligent framework designed for quantifying and analyzing the evolution of research novelty in the scientific literature. Moving beyond traditional citation analysis, which primarily measures impact, KnoVo determines a paper's novelty relative to both prior and subsequent work within its multilayered citation network. Given a target paper's abstract, KnoVo utilizes Large Language Models (LLMs) to dynamically extract dimensions of comparison (e.g., methodology, application, dataset). The target paper is then compared to related publications along these same extracted dimensions. This comparative analysis, inspired by tournament selection, yields quantitative novelty scores reflecting the relative improvement, equivalence, or inferiority of the target paper in specific aspects. By aggregating these scores and visualizing their progression, for instance, through dynamic evolution graphs and comparative radar charts, KnoVo facilitates researchers not only to assess originality and identify similar work, but also to track knowledge evolution along specific research dimensions, uncover research gaps, and explore cross-disciplinary connections. We demonstrate these capabilities through a detailed analysis of 20 diverse papers from multiple scientific fields and report on the performance of various open-source LLMs within the KnoVo framework.
☆ PreQRAG -- Classify and Rewrite for Enhanced RAG SIGIR 2025
This paper presents the submission of the UDInfo team to the SIGIR 2025 LiveRAG Challenge. We introduce PreQRAG, a Retrieval Augmented Generation (RAG) architecture designed to improve retrieval and generation quality through targeted question preprocessing. PreQRAG incorporates a pipeline that first classifies each input question as either single-document or multi-document type. For single-document questions, we employ question rewriting techniques to improve retrieval precision and generation relevance. For multi-document questions, we decompose complex queries into focused sub-questions that can be processed more effectively by downstream components. This classification and rewriting strategy improves the RAG performance. Experimental evaluation of the LiveRAG Challenge dataset demonstrates the effectiveness of our question-type-aware architecture, with PreQRAG achieving the preliminary second place in Session 2 of the LiveRAG challenge.
comment: 7 pages, SIGIR 2025 LiveRAG
☆ From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge
Efficient and accurate extraction of key information from 2D engineering drawings is essential for advancing digital manufacturing workflows. Such information includes geometric dimensioning and tolerancing (GD&T), measures, material specifications, and textual annotations. Manual extraction is slow and labor-intensive, while generic OCR models often fail due to complex layouts, engineering symbols, and rotated text, leading to incomplete and unreliable outputs. These limitations result in incomplete and unreliable outputs. To address these challenges, we propose a hybrid vision-language framework that integrates a rotation-aware object detection model (YOLOv11-obb) with a transformer-based vision-language parser. Our structured pipeline applies YOLOv11-OBB to localize annotations and extract oriented bounding box (OBB) patches, which are then parsed into structured outputs using a fine-tuned, lightweight vision-language model (VLM). We curate a dataset of 1,367 2D mechanical drawings annotated across nine key categories. YOLOv11-OBB is trained on this dataset to detect OBBs and extract annotation patches. These are parsed using two open-source VLMs: Donut and Florence-2. Both models are lightweight and well-suited for specialized industrial tasks under limited computational overhead. Following fine-tuning of both models on the curated dataset of image patches paired with structured annotation labels, a comparative experiment is conducted to evaluate parsing performance across four key metrics. Donut outperforms Florence-2, achieving 88.5% precision, 99.2% recall, and a 93.5% F1-score, with a hallucination rate of 11.5%. Finally, a case study demonstrates how the extracted structured information supports downstream manufacturing tasks such as process and tool selection, showcasing the practical utility of the proposed framework in modernizing 2D drawing interpretation.
comment: Preprint submitted to Elsevier
♻ ☆ Refining music sample identification with a self-supervised graph neural network
Automatic sample identification (ASID), the detection and identification of portions of audio recordings that have been reused in new musical works, is an essential but challenging task in the field of audio query-based retrieval. While a related task, audio fingerprinting, has made significant progress in accurately retrieving musical content under "real world" (noisy, reverberant) conditions, ASID systems struggle to identify samples that have undergone musical modifications. Thus, a system robust to common music production transformations such as time-stretching, pitch-shifting, effects processing, and underlying or overlaying music is an important open challenge. In this work, we propose a lightweight and scalable encoding architecture employing a Graph Neural Network within a contrastive learning framework. Our model uses only 9% of the trainable parameters compared to the current state-of-the-art system while achieving comparable performance, reaching a mean average precision (mAP) of 44.2%. To enhance retrieval quality, we introduce a two-stage approach consisting of an initial coarse similarity search for candidate selection, followed by a cross-attention classifier that rejects irrelevant matches and refines the ranking of retrieved candidates - an essential capability absent in prior models. In addition, because queries in real-world applications are often short in duration, we benchmark our system for short queries using new fine-grained annotations for the Sample100 dataset, which we publish as part of this work.
comment: Accepted at International Conference for Music Information Retrieval (ISMIR) 2025
♻ ☆ ScholarSearch: Benchmarking Scholar Searching Ability of LLMs
Large Language Models (LLMs)' search capabilities have garnered significant attention. Existing benchmarks, such as OpenAI's BrowseComp, primarily focus on general search scenarios and fail to adequately address the specific demands of academic search. These demands include deeper literature tracing and organization, professional support for academic databases, the ability to navigate long-tail academic knowledge, and ensuring academic rigor. Here, we proposed ScholarSearch, the first dataset specifically designed to evaluate the complex information retrieval capabilities of Large Language Models (LLMs) in academic research. ScholarSearch possesses the following key characteristics: Academic Practicality, where question content closely mirrors real academic learning and research environments, avoiding deliberately misleading models; High Difficulty, with answers that are challenging for single models (e.g., Grok DeepSearch or Gemini Deep Research) to provide directly, often requiring at least three deep searches to derive; Concise Evaluation, where limiting conditions ensure answers are as unique as possible, accompanied by clear sources and brief solution explanations, greatly facilitating subsequent audit and verification, surpassing the current lack of analyzed search datasets both domestically and internationally; and Broad Coverage, as the dataset spans at least 15 different academic disciplines. Through ScholarSearch, we expect to more precisely measure and promote the performance improvement of LLMs in complex academic information retrieval tasks. The data is available at: https://huggingface.co/datasets/PKU-DS-LAB/ScholarSearch
♻ ☆ PromptDSI: Prompt-based Rehearsal-free Instance-wise Incremental Learning for Document Retrieval ECML
Differentiable Search Index (DSI) utilizes pre-trained language models to perform indexing and document retrieval via end-to-end learning without relying on external indexes. However, DSI requires full re-training to index new documents, causing significant computational inefficiencies. Continual learning (CL) offers a solution by enabling the model to incrementally update without full re-training. Existing CL solutions in document retrieval rely on memory buffers or generative models for rehearsal, which is infeasible when accessing previous training data is restricted due to privacy concerns. To this end, we introduce PromptDSI, a prompt-based, rehearsal-free continual learning approach for document retrieval. PromptDSI follows the Prompt-based Continual Learning (PCL) framework, using learnable prompts to efficiently index new documents without accessing previous documents or queries. To improve retrieval latency, we remove the initial forward pass of PCL, which otherwise greatly increases training and inference time, with a negligible trade-off in performance. Additionally, we introduce a novel topic-aware prompt pool that employs neural topic embeddings as fixed keys, eliminating the instability of prompt key optimization while maintaining competitive performance with existing PCL prompt pools. In a challenging rehearsal-free continual learning setup, we demonstrate that PromptDSI variants outperform rehearsal-based baselines, match the strong cache-based baseline in mitigating forgetting, and significantly improving retrieval performance on new corpora.
comment: ECML PKDD 2025 Research track. Camera-ready version. Code is available at https://github.com/LouisDo2108/PromptDSI
♻ ☆ Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry
Compound AI applications chain together subcomponents such as generative language models, document retrievers, and embedding models. Applying traditional systems optimizations such as parallelism and pipelining in compound AI systems is difficult because each component has different constraints in terms of the granularity and type of data that it ingests. New data is often generated during intermediate computations, and text streams may be split into smaller, independent fragments (such as documents to sentences) which may then be re-aggregated at later parts of the computation. Due to this complexity, existing systems to serve compound AI queries do not fully take advantage of parallelism and pipelining opportunities. We present Alto, a framework that automatically optimizes execution of compound AI queries through streaming and parallelism. Bento introduces a new abstraction called nested ancestry, a metadata hierarchy that allows the system to correctly track partial outputs and aggregate data across the heterogeneous constraints of the components of compound AI applications. This metadata is automatically inferred from the programming model, allowing developers to express complex dataflow patterns without needing to reason manually about the details of routing and aggregation. Implementations of four applications in Alto outperform or match implementations in LangGraph, a popular existing AI programming framework. Alto implementations match or improve latency by between 10-30%.
♻ ☆ From Collapse to Stability: A Knowledge-Driven Ensemble Framework for Scaling Up Click-Through Rate Prediction Models
Click-through rate (CTR) prediction plays a crucial role in modern recommender systems. While many existing methods utilize ensemble networks to improve CTR model performance, they typically restrict the ensemble to only two or three sub-networks. Whether increasing the number of sub-networks consistently enhances CTR model performance to align with scaling laws remains unclear. In this paper, we investigate larger ensemble networks and find three inherent limitations in commonly used ensemble methods: (1) performance degradation as the number of sub-networks increases; (2) sharp declines and high variance in sub-network performance; and (3) significant discrepancies between sub-network and ensemble predictions. Meanwhile, we analyze the underlying causes of these limitations from the perspective of dimensional collapse: the collapse within sub-networks becomes increasingly severe as the number of sub-networks grows, leading to a lower knowledge abundance. In this paper, we employ knowledge transfer methods, such as Knowledge Distillation (KD) and Deep Mutual Learning (DML), to address the aforementioned limitations. We find that KD enables CTR models to better follow scaling laws, while DML reduces variance among sub-networks and minimizes discrepancies with ensemble predictions. Furthermore, by combining KD and DML, we propose a model-agnostic and hyperparameter-free Knowledge-Driven Ensemble Framework (KDEF) for CTR Prediction.
♻ ☆ MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
Scaling law has been extensively validated in many domains such as natural language processing and computer vision. In the recommendation system, recent work has adopted generative recommendations to achieve scalability, but their generative approaches require abandoning the carefully constructed cross features of traditional recommendation models. We found that this approach significantly degrades model performance, and scaling up cannot compensate for it at all. In this paper, we propose MTGR (Meituan Generative Recommendation) to address this issue. MTGR is modeling based on the HSTU architecture and can retain the original deep learning recommendation model (DLRM) features, including cross features. Additionally, MTGR achieves training and inference acceleration through user-level compression to ensure efficient scaling. We also propose Group-Layer Normalization (GLN) to enhance the performance of encoding within different semantic spaces and the dynamic masking strategy to avoid information leakage. We further optimize the training frameworks, enabling support for our models with 10 to 100 times computational complexity compared to the DLRM, without significant cost increases. MTGR achieved 65x FLOPs for single-sample forward inference compared to the DLRM model, resulting in the largest gain in nearly two years both offline and online. This breakthrough was successfully deployed on Meituan, the world's largest food delivery platform, where it has been handling the main traffic.
♻ ☆ GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender Systems
Traditional Point-of-Interest (POI) recommendation systems often lack transparency, interpretability, and scrutability due to their reliance on dense vector-based user embeddings. Furthermore, the cold-start problem -- where systems have insufficient data for new users -- limits their ability to generate accurate recommendations. Existing methods often address this by leveraging similar trajectories from other users, but this approach can be computationally expensive and increases the context length for LLM-based methods, making them difficult to scale. To address these limitations, we propose a method that generates natural language (NL) user profiles from large-scale, location-based social network (LBSN) check-ins, utilizing robust personality assessments and behavioral theories. These NL profiles capture user preferences, routines, and behaviors, improving POI prediction accuracy while offering enhanced transparency. By incorporating NL profiles as system prompts to LLMs, our approach reduces reliance on extensive historical data, while remaining flexible, easily updated, and computationally efficient. Our method is not only competitive with other LLM-based methods but is also more scalable for real-world POI recommender systems. Results demonstrate that our approach consistently outperforms baseline methods, offering a more interpretable and resource-efficient solution for POI recommendation systems. Our source code is available at: https://github.com/w11wo/GenUP/.
♻ ☆ Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins ICTIR'25
Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive training regime involving knowledge distillation from a teacher model and batch-sampling. Instead of relying on a teacher model, we contribute a novel parameter-free loss function for self-supervision that exploits the pre-trained language modeling capabilities of the encoder model as a training signal, eliminating the need for batch sampling by performing implicit hard negative mining. We investigate the capabilities of our proposed approach through extensive experiments, demonstrating that self-distillation can match the effectiveness of teacher distillation using only 13.5% of the data, while offering a speedup in training time between 3x and 15x compared to parametrized losses. All code and data is made openly available.
comment: 9 Pages, 5 Tables, 6 Figures; published at ICTIR'25
Multimedia 6
☆ The Hidden Cost of an Image: Quantifying the Energy Consumption of AI Image Generation
With the growing adoption of AI image generation, in conjunction with the ever-increasing environmental resources demanded by AI, we are urged to answer a fundamental question: What is the environmental impact hidden behind each image we generate? In this research, we present a comprehensive empirical experiment designed to assess the energy consumption of AI image generation. Our experiment compares 17 state-of-the-art image generation models by considering multiple factors that could affect their energy consumption, such as model quantization, image resolution, and prompt length. Additionally, we consider established image quality metrics to study potential trade-offs between energy consumption and generated image quality. Results show that image generation models vary drastically in terms of the energy they consume, with up to a 46x difference. Image resolution affects energy consumption inconsistently, ranging from a 1.3x to 4.7x increase when doubling resolution. U-Net-based models tend to consume less than Transformer-based one. Model quantization instead results to deteriorate the energy efficiency of most models, while prompt length and content have no statistically significant impact. Improving image quality does not always come at the cost of a higher energy consumption, with some of the models producing the highest quality images also being among the most energy efficient ones.
☆ Class Agnostic Instance-level Descriptor for Visual Instance Search
Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance level feature representation. Supervised or weakly supervised object detection methods are not among the options due to their poor performance on the unknown object categories. In this paper, based on the feature set output from self-supervised ViT, the instance level region discovery is modeled as detecting the compact feature subsets in a hierarchical fashion. The hierarchical decomposition results in a hierarchy of feature subsets. The non-leaf nodes and leaf nodes on the hierarchy correspond to the various instance regions in an image of different semantic scales. The hierarchical decomposition well addresses the problem of object embedding and occlusions, which are widely observed in the real scenarios. The features derived from the nodes on the hierarchy make up a comprehensive representation for the latent instances in the image. Our instance-level descriptor remains effective on both the known and unknown object categories. Empirical studies on three instance search benchmarks show that it outperforms state-of-the-art methods considerably.
☆ Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Training
In few-shot classification tasks (so-called episodes), a small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples. Metric-based models typically operate by computing similarities between query and support embeddings within a learned metric space, followed by nearest-neighbor classification. However, these labeled support samples are often underutilized--they are only used for similarity comparison, despite their potential to fine-tune and adapt the metric space itself to the classes in the current episode. To address this, we propose a series of simple yet effective episode-specific, during-inference fine-tuning methods for metric-based models, including Rotational Division Fine-Tuning (RDFT) and its two variants, Iterative Division Fine-Tuning (IDFT) and Augmented Division Fine-Tuning (ADFT). These methods construct pseudo support-query pairs from the given support set to enable fine-tuning even for non-parametric models. Nevertheless, the severely limited amount of data in each task poses a substantial risk of overfitting when applying such fine-tuning strategies. To mitigate this, we further propose to train the metric-based model within an optimization-based meta-learning framework. With the combined efforts of episode-specific fine-tuning and optimization-based meta-training, metric-based models are equipped with the ability to rapidly adapt to the limited support samples during inference while avoiding overfitting. We validate our approach on three audio datasets from diverse domains, namely ESC-50 (environmental sounds), Speech Commands V2 (spoken keywords), and Medley-solos-DB (musical instrument). Experimental results demonstrate that our approach consistently improves performance for all evaluated metric-based models (especially for attention-based models) and generalizes well across different audio domains.
☆ Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM
Cognitive impairment (CI) is of growing public health concern, and early detection is vital for effective intervention. Speech has gained attention as a non-invasive and easily collectible biomarker for assessing cognitive decline. Traditional CI detection methods typically rely on supervised models trained on acoustic and linguistic features extracted from speech, which often require manual annotation and may not generalise well across datasets and languages. In this work, we propose the first zero-shot speech-based CI detection method using the Qwen2- Audio AudioLLM, a model capable of processing both audio and text inputs. By designing prompt-based instructions, we guide the model in classifying speech samples as indicative of normal cognition or cognitive impairment. We evaluate our approach on two datasets: one in English and another multilingual, spanning different cognitive assessment tasks. Our results show that the zero-shot AudioLLM approach achieves performance comparable to supervised methods and exhibits promising generalizability and consistency across languages, tasks, and datasets.
♻ ☆ Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence
AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the Embodied Web Agents task environments, a unified simulation platform that tightly integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the Embodied Web Agents Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation - all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access. All datasets, codes and websites are publicly available at our project page https://embodied-web-agent.github.io/.
♻ ☆ Memory-enhanced Retrieval Augmentation for Long Video Understanding
Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to compression and brute-force downsampling. While retrieval-augmented generation (RAG) methods mitigate this issue, their applicability is limited due to explicit query dependency. To overcome this challenge, we introduce a novel memory-enhanced RAG-based approach called MemVid, which is inspired by the cognitive memory of human beings. Our approach operates in four basic steps: 1) memorizing holistic video information, 2) reasoning about the task's information needs based on memory, 3) retrieving critical moments based on the information needs, and 4) focusing on the retrieved moments to produce the final answer. To enhance the system's memory-grounded reasoning capabilities while achieving optimal end-to-end performance, we propose a curriculum learning strategy. This approach begins with supervised learning on well-annotated reasoning results, then progressively explores and reinforces more plausible reasoning outcomes through reinforcement learning. We perform extensive evaluations on popular LVU benchmarks, including MLVU, VideoMME and LVBench. In our experiments, MemVid demonstrates superior efficiency and effectiveness compared to both LVLMs and RAG methods.