Peer Revenue Returns subject to peer review

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Friday 30 January

Computer Vision

CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content

Gyuwon Han, Young Kyun Jang and Chanho Eom

Composed Video Retrieval (CoVR) aims to retrieve a target video from a large gallery using a reference video and a textual query specifying visual modifications. However, existing benchmarks consider only visual changes, ignoring videos that differ in audio despite visual similarity. To address this limitation, we introduce Composed retrieval for Video with its Audio CoVA, a new retrieval task that accounts for both visual and auditory variations. To support this, we construct AV-Comp, a benchmark consisting of video pairs with cross-modal changes and corresponding textual queries that describe the differences. We also propose AVT Compositional Fusion (AVT), which integrates video, audio, and text features by selectively aligning the query to the most relevant modality. AVT outperforms traditional unimodal fusion and serves as a strong baseline for CoVA. Examples from the proposed dataset, including both visual and auditory information, are available at https://perceptualai-lab.github.io/CoVA/.
Read the full abstract

Computer Vision

DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image Generation

Xin Jiang, Jingwen Chen, Yehao Li et al. (+5 more)

Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images. Nevertheless, the potential of Visual Autoregressive (VAR) models, despite their unified architecture and efficient inference, remains underexplored. In this work, we present DreamVAR, a novel framework for subject-driven image synthesis built upon a VAR model that employs next-scale prediction. Technically, multi-scale features of the reference subject are first extracted by a visual tokenizer. Instead of interleaving these conditional features with target image tokens across scales, our DreamVAR pre-fills the full subject feature sequence prior to predicting target image tokens. This design simplifies autoregressive dependencies and mitigates the train-test discrepancy in multi-scale conditioning scenario within the VAR paradigm. DreamVAR further incorporates reinforcement learning to jointly enhance semantic alignment and subject consistency. Extensive experiments demonstrate that DreamVAR achieves superior appearance preservation compared to leading diffusion-based methods.
Read the full abstract

All authors Xin Jiang, Jingwen Chen, Yehao Li, Yingwei Pan, Kezhou Chen, Zechao Li, Ting Yao, Tao Mei

Computer Vision

MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control

Renjie Lu, Xulong Zhang, Xiaoyang Qu et al. (+2 more)

Synthesizing personalized talking faces that uphold and highlight a speaker's unique style while maintaining lip-sync accuracy remains a significant challenge. A primary limitation of existing approaches is the intrinsic confounding of speaker-specific talking style and semantic content within facial motions, which prevents the faithful transfer of a speaker's unique persona to arbitrary speech. In this paper, we propose MirrorTalk, a generative framework based on a conditional diffusion model, combined with a Semantically-Disentangled Style Encoder (SDSE) that can distill pure style representations from a brief reference video. To effectively utilize this representation, we further introduce a hierarchical modulation strategy within the diffusion process. This mechanism guides the synthesis by dynamically balancing the contributions of audio and style features across distinct facial regions, ensuring both precise lip-sync accuracy and expressive full-face dynamics. Extensive experiments demonstrate that MirrorTalk achieves significant improvements over state-of-the-art methods in terms of lip-sync accuracy and personalization preservation.
Read the full abstract

All authors Renjie Lu, Xulong Zhang, Xiaoyang Qu, Jianzong Wang, Shangfei Wang

Computer Vision

PromptMAD: Cross-Modal Prompting for Multi-Class Visual Anomaly Localization

Duncan McCain, Hossein Kashiani and Fatemeh Afghah

Visual anomaly detection in multi-class settings poses significant challenges due to the diversity of object categories, the scarcity of anomalous examples, and the presence of camouflaged defects. In this paper, we propose PromptMAD, a cross-modal prompting framework for unsupervised visual anomaly detection and localization that integrates semantic guidance through vision-language alignment. By leveraging CLIP-encoded text prompts describing both normal and anomalous class-specific characteristics, our method enriches visual reconstruction with semantic context, improving the detection of subtle and textural anomalies. To further address the challenge of class imbalance at the pixel level, we incorporate Focal loss function, which emphasizes hard-to-detect anomalous regions during training. Our architecture also includes a supervised segmentor that fuses multi-scale convolutional features with Transformer-based spatial attention and diffusion iterative refinement, yielding precise and high-resolution anomaly maps. Extensive experiments on the MVTec-AD dataset demonstrate that our method achieves state-of-the-art pixel-level performance, improving mean AUC to 98.35% and AP to 66.54%, while maintaining efficiency across diverse categories.
Read the full abstract

Computer Vision

Head-Aware Visual Cropping: Enhancing Fine-Grained VQA with Attention-Guided Subimage

Junfei Xie, Peng Pan and Xulong Zhang

Multimodal Large Language Models (MLLMs) show strong performance in Visual Question Answering (VQA) but remain limited in fine-grained reasoning due to low-resolution inputs and noisy attention aggregation. We propose Head Aware Visual Cropping (HAVC), a training-free method that improves visual grounding by leveraging a selectively refined subset of attention heads. HAVC first filters heads through an OCR-based diagnostic task, ensuring that only those with genuine grounding ability are retained. At inference, these heads are further refined using spatial entropy for stronger spatial concentration and gradient sensitivity for predictive contribution. The fused signals produce a reliable Visual Cropping Guidance Map, which highlights the most task-relevant region and guides the cropping of a subimage subsequently provided to the MLLM together with the image-question pair. Extensive experiments on multiple fine-grained VQA benchmarks demonstrate that HAVC consistently outperforms state-of-the-art cropping strategies, achieving more precise localization, stronger visual grounding, providing a simple yet effective strategy for enhancing precision in MLLMs.
Read the full abstract

Computer Vision

Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector

Wenqiang Zu, Shenghao Xie, Bo Lei et al. (+1 more)

Recent progress in generative modeling has enabled high-quality visual synthesis with diffusion-based frameworks, supporting controllable sampling and large-scale training. Inference-time guidance methods such as classifier-free and representative guidance enhance semantic alignment by modifying sampling dynamics; however, they do not fully exploit unsupervised feature representations. Although such visual representations contain rich semantic structure, their integration during generation is constrained by the absence of ground-truth reference images at inference. This work reveals semantic drift in the early denoising stages of diffusion transformers, where stochasticity results in inconsistent alignment even under identical conditioning. To mitigate this issue, we introduce a guidance scheme using a representation alignment projector that injects representations predicted by a projector into intermediate sampling steps, providing an effective semantic anchor without modifying the model architecture. Experiments on SiTs and REPAs show notable improvements in class-conditional ImageNet synthesis, achieving substantially lower FID scores; for example, REPA-XL/2 improves from 5.9 to 3.3, and the proposed method outperforms representative guidance when applied to SiT models. The approach further yields complementary gains when combined with classifier-free guidance, demonstrating enhanced semantic coherence and visual fidelity. These results establish representation-informed diffusion sampling as a practical strategy for reinforcing semantic preservation and image consistency.
Read the full abstract

All authors Wenqiang Zu, Shenghao Xie, Bo Lei, Lei Ma

Computer Vision · Cross-listed from cs.RO

CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Control

Jiaqi Shi, Xulong Zhang, Xiaoyang Qu et al. (+1 more)

Recent advances in Vision-Language-Action (VLA) models have shown promise for robot control, but their dependence on action supervision limits scalability and generalization. To address this challenge, we introduce CARE, a novel framework designed to train VLA models for robotic task execution. Unlike existing methods that depend on action annotations during pretraining, CARE eliminates the need for explicit action labels by leveraging only video-text pairs. These weakly aligned data sources enable the model to learn continuous latent action representations through a newly designed multi-task pretraining objective. During fine-tuning, a small set of labeled data is used to train the action head for control. Experimental results across various simulation tasks demonstrate CARE's superior success rate, semantic interpretability, and ability to avoid shortcut learning. These results underscore CARE's scalability, interpretability, and effectiveness in robotic control with weak supervision.
Read the full abstract

All authors Jiaqi Shi, Xulong Zhang, Xiaoyang Qu, Jianzong Wang

Computer Vision

ScribbleSense: Generative Scribble-Based Texture Editing with Intent Prediction

Yudi Zhang, Yeming Geng and Lei Zhang

Interactive 3D model texture editing presents enhanced opportunities for creating 3D assets, with freehand drawing style offering the most intuitive experience. However, existing methods primarily support sketch-based interactions for outlining, while the utilization of coarse-grained scribble-based interaction remains limited. Furthermore, current methodologies often encounter challenges due to the abstract nature of scribble instructions, which can result in ambiguous editing intentions and unclear target semantic locations. To address these issues, we propose ScribbleSense, an editing method that combines multimodal large language models (MLLMs) and image generation models to effectively resolve these challenges. We leverage the visual capabilities of MLLMs to predict the editing intent behind the scribbles. Once the semantic intent of the scribble is discerned, we employ globally generated images to extract local texture details, thereby anchoring local semantics and alleviating ambiguities concerning the target semantic locations. Experimental results indicate that our method effectively leverages the strengths of MLLMs, achieving state-of-the-art interactive editing performance for scribble-based texture editing.
Read the full abstract

Computer Vision

Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework

Shiyu Liu, Xinyi Wen, Zhibin Lan et al. (+2 more)

Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models generate descriptions of non-existent objects, compromising their reliability. Previous work attributes this to LVLMs' over-reliance on language priors and attempts to mitigate it through logits calibration. However, they still lack a thorough analysis of the over-reliance. To gain a deeper understanding of over-reliance, we conduct a series of preliminary experiments, indicating that as the generation length increases, LVLMs' over-reliance on language priors leads to inflated probability of hallucinated object tokens, consequently exacerbating object hallucination. To circumvent this issue, we propose Language-Prior-Free Verification to enable LVLMs to faithfully verify the confidence of object existence. Based on this, we propose a novel training-free Self-Validation Framework to counter the over-reliance trap. It first validates objects' existence in sampled candidate captions and further mitigates object hallucination via caption selection or aggregation. Experiment results demonstrate that our framework mitigates object hallucination significantly in image captioning task (e.g., 65.6% improvement on CHAIRI metric with LLaVA-v1.5-7B), surpassing the previous SOTA methods. This result highlights a novel path towards mitigating hallucination by unlocking the inherent potential within LVLMs themselves.
Read the full abstract

All authors Shiyu Liu, Xinyi Wen, Zhibin Lan, Ante Wang, Jinsong Su

Computer Vision · Cross-listed from cs.RO

High-Definition 5MP Stereo Vision Sensing for Robotics

Leaf Jiang, Matthew Holzel, Bernhard Kaplan et al. (+4 more)

High-resolution (5MP+) stereo vision systems are essential for advancing robotic capabilities, enabling operation over longer ranges and generating significantly denser and accurate 3D point clouds. However, realizing the full potential of high-angular-resolution sensors requires a commensurately higher level of calibration accuracy and faster processing – requirements often unmet by conventional methods. This study addresses that critical gap by processing 5MP camera imagery using a novel, advanced frame-to-frame calibration and stereo matching methodology designed to achieve both high accuracy and speed. Furthermore, we introduce a new approach to evaluate real-time performance by comparing real-time disparity maps with ground-truth disparity maps derived from more computationally intensive stereo matching algorithms. Crucially, the research demonstrates that high-pixel-count cameras yield high-quality point clouds only through the implementation of high-accuracy calibration.
Read the full abstract

All authors Leaf Jiang, Matthew Holzel, Bernhard Kaplan, Hsiou-Yuan Liu, Sabyasachi Paul, Karen Rankin, Piotr Swierczynski

Computer Vision · Cross-listed from cs.LG

Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance

Jing Jia, Wei Yuan, Sifan Liu et al. (+2 more)

Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown signal. In practice, one often must use a mismatched or low-fidelity diffusion prior. Surprisingly, these weak priors often perform nearly as well as full-strength, in-domain baselines. We study when and why inverse solvers are robust to weak diffusion priors. Through extensive experiments, we find that weak priors succeed when measurements are highly informative (e.g., many observed pixels), and we identify regimes where they fail. To explain this behavior, we combine Bayesian-consistency theory with local-correlation analysis: the theory gives conditions under which high-dimensional measurements make the posterior concentrate near the true signal, while the correlation analysis shows that weak and stronger natural-image priors can share similar local spatial structure. These results provide a principled justification on when weak diffusion priors can be used reliably. Code is available at https://github.com/jjia131/weak-diffusion-priors-inverse-problem.
Read the full abstract

All authors Jing Jia, Wei Yuan, Sifan Liu, Liyue Shen, Guanyang Wang

Thursday 29 January

Computer Vision · Cross-listed from cs.AI

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

Yuqi Xiong, Chunyi Peng, Zhipeng Xu et al. (+6 more)

Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend the perceptual capabilities of VLMs, typically by explicitly separating visual perception from subsequent reasoning processes. However, this decoupled design can lead to unnecessary loss of visual information, particularly when image-based operations such as cropping are applied. In this paper, we propose Lang2Act, which enables fine-grained visual perception and reasoning through self-emergent linguistic toolchains. Rather than invoking fixed external engines, Lang2Act collects self-emergent actions as linguistic tools and leverages them to enhance the visual perception capabilities of VLMs. To support this mechanism, we design a two-stage Reinforcement Learning (RL)-based training framework. Specifically, the first stage optimizes VLMs to self-explore high-quality actions for constructing a reusable linguistic toolbox, and the second stage further optimizes VLMs to exploit these linguistic tools for downstream reasoning effectively. Experimental results demonstrate the effectiveness of Lang2Act in substantially enhancing the visual perception capabilities of VLMs, achieving performance improvements of over 4%. All code and data are available at https://github.com/NEUIR/Lang2Act.
Read the full abstract

All authors Yuqi Xiong, Chunyi Peng, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu

Computer Vision

YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation

Ranjan Sapkota and Manoj Karkee

This paper presents YOLOE-26, a unified framework that integrates the deployment-optimized YOLO26(or YOLOv26) architecture with the open-vocabulary learning paradigm of YOLOE for real-time open-vocabulary instance segmentation. Building on the NMS-free, end-to-end design of YOLOv26, the proposed approach preserves the hallmark efficiency and determinism of the YOLO family while extending its capabilities beyond closed-set recognition. YOLOE-26 employs a convolutional backbone with PAN/FPN-style multi-scale feature aggregation, followed by end-to-end regression and instance segmentation heads. A key architectural contribution is the replacement of fixed class logits with an object embedding head, which formulates classification as similarity matching against prompt embeddings derived from text descriptions, visual examples, or a built-in vocabulary. To enable efficient open-vocabulary reasoning, the framework incorporates Re-Parameterizable Region-Text Alignment (RepRTA) for zero-overhead text prompting, a Semantic-Activated Visual Prompt Encoder (SAVPE) for example-guided segmentation, and Lazy Region Prompt Contrast for prompt-free inference. All prompting modalities operate within a unified object embedding space, allowing seamless switching between text-prompted, visual-prompted, and fully autonomous segmentation. Extensive experiments demonstrate consistent scaling behavior and favorable accuracy-efficiency trade-offs across model sizes in both prompted and prompt-free settings. The training strategy leverages large-scale detection and grounding datasets with multi-task optimization and remains fully compatible with the Ultralytics ecosystem for training, validation, and deployment. Overall, YOLOE-26 provides a practical and scalable solution for real-time open-vocabulary instance segmentation in dynamic, real-world environments.
Read the full abstract

Computer Vision

Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders

Laura Cif, Diane Demailly, Gabriella A. Horvàth et al. (+15 more)

Hyperkinetic movement disorders (HMDs) such as dystonia, tremor, chorea, myoclonus, and tics are disabling motor manifestations across childhood and adulthood. Their fluctuating, intermittent, and frequently co-occurring expressions hinder clinical recognition and longitudinal monitoring, which remain largely subjective and vulnerable to inter-rater variability. Objective and scalable methods to distinguish overlapping HMD phenotypes from routine clinical videos are still lacking. Here, we developed a pose-based machine-learning framework that converts standard outpatient videos into anatomically meaningful keypoint time series and computes kinematic descriptors spanning statistical, temporal, spectral, and higher-order irregularity-complexity features.
Read the full abstract

All authors Laura Cif, Diane Demailly, Gabriella A. Horvàth, Juan Dario Ortigoza Escobar, Nathalie Dorison, Mayté Castro Jiménez, Cécile A. Hubsch, Thomas Wirth, Gun-Marie Hariz, Sophie Huby, Morgan Dornadic, Zohra Souei, Muhammad Mushhood Ur Rehman, Simone Hemm, Mehdi Boulayme, Eduardo M. Moraud, Jocelyne Bloch, Xavier Vasques

Computer Vision

See Without Decoding: Motion-Vector-Based Tracking in Compressed Video

Axel Duché, Clément Chatelain and Gilles Gasso

We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding. Using motion vectors and transform coefficients from compressed data, our deep model propagates object bounding boxes across frames, achieving a computational speed-up of order up to 3.7 with only a slight 4% mAP@0.5 drop vs RGB baseline on MOTS15/17/20 datasets. These results highlight codec-domain motion modeling efficiency for real-time analytics in large monitoring systems.
Read the full abstract

Computer Vision

Real-Time Human Activity Recognition on Edge Microcontrollers: Dynamic Hierarchical Inference with Multi-Spectral Sensor Fusion

Boyu Li, Kuangji Zuo, Lincong Li et al. (+1 more)

The demand for accurate on-device pattern recognition in edge applications is intensifying, yet existing approaches struggle to reconcile accuracy with computational constraints. To address this challenge, a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules, namely the Hierarchical Parallel Pseudo-image Enhancement Fusion Network (HPPI-Net), is proposed for real-time, on-device Human Activity Recognition (HAR). Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy while utilizing only 22.3 KiB of RAM and 439.5 KiB of ROM after optimization. HPPI-Net employs a two-layer architecture. The first layer extracts preliminary features using Fast Fourier Transform (FFT) spectrograms, while the second layer selectively activates either a dedicated module for stationary activity recognition or a parallel LSTM-MobileNet network (PLMN) for dynamic states. PLMN fuses FFT, Wavelet, and Gabor spectrograms through three parallel LSTM encoders and refines the concatenated features using Efficient Channel Attention (ECA) and Depthwise Separable Convolution (DSC), thereby offering channel-level interpretability while substantially reducing multiply-accumulate operations. Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%. These results demonstrate that HPPI-Net achieves a favorable accuracy-efficiency trade-off and provides explainable predictions, establishing a practical solution for wearable, industrial, and smart home HAR on memory-constrained edge platforms.
Read the full abstract

All authors Boyu Li, Kuangji Zuo, Lincong Li, Yonghui Wu

Computer Vision

Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency

Alexander Blezinger, Wolfgang Nejdl and Ming Tang

Foundation models pretrained on large-scale histopathology data have found great success in various fields of computational pathology, but their impact on regressive biomarker prediction remains underexplored. In this work, we systematically evaluate histopathological foundation models for regression-based tasks, demonstrated through the prediction of homologous recombination deficiency (HRD) score - a critical biomarker for personalized cancer treatment. Within multiple instance learning frameworks, we extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models, and evaluate their impact compared to contrastive learning-based features. Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts from two public medical data collections. Extensive experiments demonstrate that models trained on foundation model features consistently outperform the baseline in terms of predictive accuracy and generalization capabilities while exhibiting systematic differences among the foundation models. Additionally, we propose a distribution-based upsampling strategy to mitigate target imbalance in these datasets, significantly improving the recall and balanced accuracy for underrepresented but clinically important patient populations. Furthermore, we investigate the impact of different sampling strategies and instance bagsizes by ablation studies. Our results highlight the benefits of large-scale histopathological pretraining for more precise and transferable regressive biomarker prediction, showcasing its potential to advance AI-driven precision oncology.
Read the full abstract

Computer Vision

SDCM: Simulated Densifying and Compensatory Modeling Fusion for Radar-Vision 3-D Object Detection in Internet of Vehicles

Shucong Li, Xiaoluo Zhou, Yuqian He et al. (+1 more)

3-D object detection based on 4-D radar-vision is an important part in Internet of Vehicles (IoV). However, there are two challenges which need to be faced. First, the 4-D radar point clouds are sparse, leading to poor 3-D representation. Second, vision datas exhibit representation degradation under low-light, long distance detection and dense occlusion scenes, which provides unreliable texture information during fusion stage. To address these issues, a framework named SDCM is proposed, which contains Simulated Densifying and Compensatory Modeling Fusion for radar-vision 3-D object detection in IoV. Firstly, considering point generation based on Gaussian simulation of key points obtained from 3-D Kernel Density Estimation (3-D KDE), and outline generation based on curvature simulation, Simulated Densifying (SimDen) module is designed to generate dense radar point clouds. Secondly, considering that radar data could provide more real time information than vision data, due to the all-weather property of 4-D radar. Radar Compensatory Mapping (RCM) module is designed to reduce the affects of vision datas' representation degradation. Thirdly, considering that feature tensor difference values contain the effective information of every modality, which could be extracted and modeled for heterogeneity reduction and modalities interaction, Mamba Modeling Interactive Fusion (MMIF) module is designed for reducing heterogeneous and achieving interactive Fusion. Experiment results on the VoD, TJ4DRadSet and Astyx HiRes 2019 dataset show that SDCM achieves best performance with lower parameter quantity and faster inference speed. Our code will be available.
Read the full abstract

All authors Shucong Li, Xiaoluo Zhou, Yuqian He, Zhenyu Liu

Computer Vision

Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields

Shiqian Li, Ruihong Shen, Junfeng Ni et al. (+3 more)

Predicting physical dynamics from raw visual data remains a major challenge in AI. While recent video generation models have achieved impressive visual quality, they still cannot consistently generate physically plausible videos due to a lack of modeling of physical laws. Recent approaches combining 3D Gaussian splatting and physics engines can produce physically plausible videos, but are hindered by high computational costs in both reconstruction and simulation, and often lack robustness in complex real-world scenarios. To address these issues, we introduce Neural Gaussian Force Field (NGFF), an end-to-end neural framework that integrates 3D Gaussian perception with physics-based dynamic modeling to generate interactive, physically realistic 4D videos from multi-view RGB inputs, achieving two orders of magnitude faster than prior Gaussian simulators. To support training, we also present GSCollision, a 4D Gaussian dataset featuring diverse materials, multi-object interactions, and complex scenes, totaling over 640k rendered physical videos (~4 TB). Evaluations on synthetic and real 3D scenarios show NGFF's strong generalization and robustness in physical reasoning, advancing video prediction towards physics-grounded world models.
Read the full abstract

All authors Shiqian Li, Ruihong Shen, Junfeng Ni, Chang Pan, Chi Zhang, Yixin Zhu

Computer Vision

DensiThAI, A Multi-View Deep Learning Framework for Breast Density Estimation using Infrared Images

Siva Teja Kakileti and Geetha Manjunath

Breast tissue density is a key biomarker of breast cancer risk and a major factor affecting mammographic sensitivity. However, density assessment currently relies almost exclusively on X-ray mammography, an ionizing imaging modality. This study investigates the feasibility of estimating breast density using artificial intelligence over infrared thermal images, offering a non-ionizing imaging approach. The underlying hypothesis is that fibroglandular and adipose tissues exhibit distinct thermophysical and physiological properties, leading to subtle but spatially coherent temperature variations on the breast surface. In this paper, we propose DensiThAI, a multi-view deep learning framework for breast density classification from thermal images. The framework was evaluated on a multi-center dataset of 3,500 women using mammography-derived density labels as reference. Using five standard thermal views, DensiThAI achieved a mean AUROC of 0.73 across 10 random splits, with statistically significant separation between density classes across all splits (p << 0.05). Consistent performance across age cohorts supports the potential of thermal imaging as a non-ionizing approach for breast density assessment with implications for improved patient experience and workflow optimization.
Read the full abstract

Computer Vision

Scalable Analytic Classifiers with Associative Drift Compensation for Class-Incremental Learning of Vision Transformers

Xuan Rao, Mingming Ha, Bo Zhao et al. (+2 more)

Class-incremental learning (CIL) with Vision Transformers (ViTs) faces a major computational bottleneck during the classifier reconstruction phase, where most existing methods rely on costly iterative stochastic gradient descent (SGD). We observe that analytic Regularized Gaussian Discriminant Analysis (RGDA) provides a Bayes-optimal alternative with accuracy comparable to SGD-based classifiers; however, its quadratic inference complexity limits its use in large-scale CIL scenarios. To overcome this, we propose Low-Rank Factorized RGDA (LR-RGDA), a scalable classifier that combines RGDA's expressivity with the efficiency of linear classifiers. By exploiting the low-rank structure of the covariance via the Woodbury matrix identity, LR-RGDA decomposes the discriminant function into a global affine term refined by a low-rank quadratic perturbation, reducing the inference complexity from $\mathcal{O}(Cd^2)$ to $\mathcal{O}(d^2 + Crd^2)$, where $C$ is the class number, $d$ the feature dimension, and $r \ll d$ the subspace rank. To mitigate representation drift caused by backbone updates, we further introduce Hopfield-based Distribution Compensator (HopDC), a training-free mechanism that uses modern continuous Hopfield Networks to recalibrate historical class statistics through associative memory dynamics on unlabeled anchors, accompanied by a theoretical bound on the estimation error. Extensive experiments on diverse CIL benchmarks demonstrate that our framework achieves state-of-the-art performance, providing a scalable solution for large-scale class-incremental learning with ViTs. Code: https://github.com/raoxuan98-hash/lr_rgda_hopdc.
Read the full abstract

All authors Xuan Rao, Mingming Ha, Bo Zhao, Derong Liu, Cesare Alippi

Computer Vision · Cross-listed from physics.data-an

Comparison of Image Processing Models in Quark Gluon Jet Classification

Daeun Kim, Jaeyoon Cho, Jiwon Lee et al. (+5 more)

Quark-gluon discrimination provides a useful test case for studying how different machine-learning architectures learn the spatial structure of QCD radiation. In this work, we compare convolutional neural network (CNN), Vision Transformers (ViT), and hierarchical Swin Transformers using the same three-channel jet-image representation, consisting of charged-particle momentum, neutral-particle momentum, and charged-particle multiplicity from PYTHIA 8 jets. We study their performance for different training-set sizes and fine-tuning configurations, with particular attention to the role of local and global information in the jet images. CNN and Swin models consistently perform better than ViT in the cases studied. Since both CNN and Swin retain a strong local component in their architectures, this suggests that local jet substructure plays an important role in quark-gluon discrimination. The performance of the hierarchical Swin model also suggests that combining local features over larger spatial scales is useful. Block-wise fine-tuning improves the performance of the Transformer models, although the improvement becomes smaller and the training less stable as more blocks are unfrozen. We also find that self-supervised Momentum Contrast (MoCo) pretraining improves the model initialization, particularly when the amount of labeled training data is limited. Based on these observations, we developed a smaller Swin model adopted to the jet-image representation used in this study. It achieves comparable performance with substantially fewer parameters. The results show that it is important to adapt the model architecture and training procedure to the specific input characteristics of High Energy Physics (HEP) data when applying vision models in HEP.
Read the full abstract

All authors Daeun Kim, Jaeyoon Cho, Jiwon Lee, Wonjun Jeong, Hyeongwoo Noh, Giyeong Kim, Seunghwan Yang, MinJung Kweon

Computer Vision

Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture

Seth Donahue, Irina Djuraskovic, Kunal Shah et al. (+3 more)

Video-based human movement analysis holds potential for movement assessment in clinical practice and research. However, the clinical implementation and trust of multi-view markerless motion capture (MMMC) require that, in addition to being accurate, these systems produce reliable confidence intervals to indicate how accurate they are for any individual. Building on our prior work utilizing variational inference to estimate joint angle posterior distributions, this study evaluates the calibration and reliability of a probabilistic MMMC method. We analyzed data from 68 participants across two institutions, validating the model against an instrumented walkway and standard marker-based motion capture. We measured the calibration of the confidence intervals using the Expected Calibration Error (ECE). The model demonstrated reliable calibration, yielding ECE values generally < 0.1 for both step and stride length and bias-corrected gait kinematics. We observed a median step and stride length error of ~16 mm and ~12 mm respectively, with median bias-corrected kinematic errors ranging from 1.5 to 3.8 degrees across lower extremity joints. Consistent with the calibrated ECE, the magnitude of the model's predicted uncertainty correlated strongly with observed error measures. These findings indicate that, as designed, the probabilistic model reconstruction quantifies epistemic uncertainty, allowing it to identify unreliable outputs without the need for concurrent ground-truth instrumentation.
Read the full abstract

All authors Seth Donahue, Irina Djuraskovic, Kunal Shah, Fabian Sinz, Ross Chafetz, R. James Cotton

Computer Vision

Jailbreaks on Vision Language Model via Multimodal Reasoning

Aarush Noheria and Yuguang Yao

Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation. However, their outputs are highly sensitive to prompt variations, which can reveal vulnerabilities in safety alignment. In this work, we present a jailbreak framework that exploits post-training Chain-of-Thought (CoT) prompting to construct stealthy prompts capable of bypassing safety filters. To further increase attack success rates (ASR), we propose a ReAct-driven adaptive noising mechanism that iteratively perturbs input images based on model feedback. This approach leverages the ReAct paradigm to refine adversarial noise in regions most likely to activate safety defenses, thereby enhancing stealth and evasion. Experimental results demonstrate that the proposed dual-strategy significantly improves ASR while maintaining naturalness in both text and visual domains.
Read the full abstract

Computer Vision

FlexMap: Robust HD Map Construction under Flexible Camera Configurations

Run Wang, Chaoyi Zhou, Amir Salarpour et al. (+5 more)

High-definition (HD) maps provide essential semantic information about road structures for autonomous driving, but existing HD map construction methods typically require calibrated multi-camera rigs and explicit 2D-to-BEV transformations. Such pipelines degrade when camera views are missing or pose estimates are inaccurate, limiting their use across heterogeneous fleet configurations. We introduce FlexMap, a vectorized HD mapping framework that adapts to varying camera configurations without architectural changes or per-configuration retraining and does not require camera parameters as model input. FlexMap replaces explicit geometric projection with a geometry foundation model that encodes cross-view 3D structure. A spatial-temporal enhancement module then separates cross-view spatial reasoning from temporal aggregation, while a camera-aware decoder uses the token produced for each input view to adapt its attention without camera poses. Experiments on nuScenes and Argoverse 2 show that FlexMap outperforms pose-dependent baselines using estimated poses and maintains comparable accuracy across all evaluated camera configurations, including those with missing views.
Read the full abstract

All authors Run Wang, Chaoyi Zhou, Amir Salarpour, Xi Liu, Zhi-Qi Cheng, Feng Luo, Mert D. Pesé, Siyu Huang

Computer Vision

Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes

Gonzalo Gomez-Nogales, Yicong Hong, Chongjian Ge et al. (+4 more)

Traditional rendering pipelines rely on complex assets, accurate materials and lighting, and substantial computational resources to produce realistic imagery, yet they still face challenges in scalability and realism for populated dynamic scenes. We present C2R (Coarse-to-Real), a generative rendering framework that synthesizes real-style urban crowd videos from coarse 3D simulations. Our approach uses coarse 3D renderings to explicitly control scene layout, camera motion, and human trajectories, while a learned neural renderer generates realistic appearance, lighting, and fine-scale dynamics guided by text prompts. To overcome the lack of paired training data between coarse simulations and real videos, we adopt a two-stage synthetic-real domain-hedging strategy that first learns a strong generative prior from large-scale real footage, and then introduces controllability by using a small amount of paired synthetic coarse-to-fine data to anchor shared implicit spatio-temporal features across domains. The resulting system supports coarse-to-fine control, generalizes across diverse CG and game inputs, and produces temporally consistent, controllable, and realistic urban scene videos from minimal 3D input. We will release the model and project webpage at https://gonzalognogales.github.io/coarse2real/.
Read the full abstract

All authors Gonzalo Gomez-Nogales, Yicong Hong, Chongjian Ge, Peiye Zhuang, Marc Comino-Trinidad, Dan Casas, Yi Zhou

Computer Vision · Cross-listed from cs.LG

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models

Mingyu Lu, Soham Gadgil, Chris Lin et al. (+2 more)

As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces. While the Shapley value offers a theoretically grounded approach to attribution, it faces a dual computational bottleneck: (i) the prohibitive cost of exhaustive model retraining for each sampled subset of players (i.e., data contributors) and (ii) the combinatorial number of subsets needed to estimate marginal contributions due to contributor interactions. To this end, we propose SurrogateSHAP, a retraining-free framework that approximates the expensive retraining game through inference from a pretrained model. To further improve efficiency, we employ a gradient-boosted tree to approximate the utility function and derive Shapley values analytically from the tree-based model. We evaluate SurrogateSHAP across three diverse attribution tasks: (i) image quality for DDPM-CFG on CIFAR-20, (ii) aesthetics for Stable Diffusion on Post-Impressionist artworks, and (iii) product diversity for FLUX.1 on Fashion-Product data. Across settings, SurrogateSHAP outperforms prior methods while substantially reducing computational overhead, consistently identifying influential contributors across multiple utility metrics. Finally, we demonstrate that SurrogateSHAP effectively localizes data sources responsible for spurious correlations in clinical images, providing a scalable path toward auditing safety-critical generative models.
Read the full abstract

All authors Mingyu Lu, Soham Gadgil, Chris Lin, Chanwoo Kim, Su-In Lee

Computer Vision

VMonarch: Efficient Video Diffusion Transformers with Structured Attention

Cheng Liang, Haoxian Chen, Liang Hou et al. (+4 more)

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally represented by the Monarch matrix. It is a class of structured matrices with flexible sparsity, enabling sub-quadratic attention via an alternating minimization algorithm. Accordingly, we propose VMonarch, a novel attention mechanism for Video DiTs that enables efficient computation over the dynamic sparse patterns with structured Monarch matrices. First, we adapt spatio-temporal Monarch factorization to explicitly capture the intra-frame and inter-frame correlations of the video data. Second, we introduce a recomputation strategy to mitigate artifacts arising from instabilities during alternating minimization of Monarch matrices. Third, we propose a novel online entropy algorithm fused into FlashAttention, enabling fast Monarch matrix updates for long sequences. Extensive experiments demonstrate that VMonarch achieves comparable or superior generation quality to full attention on VBench after minimal tuning. It overcomes the attention bottleneck in Video DiTs, reduces attention FLOPs by a factor of 17.5, and achieves a speedup of over 5x in attention computation for long videos, surpassing state-of-the-art sparse attention methods at 90% sparsity. Code is available at https://github.com/EricLina/VMonarch.
Read the full abstract

All authors Cheng Liang, Haoxian Chen, Liang Hou, Qi Fan, Gangshan Wu, Xin Tao, Limin Wang

Computer Vision

Is Hierarchical Quantization Essential for Optimal Reconstruction?

Shirin Reyhanian and Laurenz Wiskott

Vector-quantized variational autoencoders (VQ-VAEs) are central to models that rely on high reconstruction fidelity, from neural compression to generative pipelines. Hierarchical extensions, such as VQ-VAE2, are often credited with superior reconstruction performance because they split global and local features across multiple levels. However, since higher levels derive all their information from lower levels, they should not carry additional reconstructive content beyond what the lower-level already encodes. Combined with recent advances in training objectives and quantization mechanisms, this leads us to ask whether a single-level VQ-VAE, with matched representational budget and no codebook collapse, can equal the reconstruction fidelity of its hierarchical counterpart. Although the multi-scale structure of hierarchical models may improve perceptual quality in downstream tasks, the effect of hierarchy on reconstruction accuracy, isolated from codebook utilization and overall representational capacity, remains empirically underexamined. We revisit this question by comparing a two-level VQ-VAE and a capacity-matched single-level model on high-resolution ImageNet images. Consistent with prior observations, we confirm that inadequate codebook utilization limits single-level VQ-VAEs and that overly high-dimensional embeddings destabilize quantization and increase codebook collapse. We show that lightweight interventions such as initialization from data, periodic reset of inactive codebook vectors, and systematic tuning of codebook hyperparameters significantly reduce collapse. Our results demonstrate that when representational budgets are matched, and codebook collapse is mitigated, single-level VQ-VAEs can match the reconstruction fidelity of hierarchical variants, challenging the assumption that hierarchical quantization is inherently superior for high-quality reconstructions.
Read the full abstract

Computer Vision

Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning

Jian Shi, Michael Birsak, Wenqing Cui et al. (+2 more)

This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and spatial reasoning. Our findings clarify the role of PEs as a causal mechanism that governs spatial structure in ViT representations. Our code is provided in https://github.com/shijianjian/vit-geometry-probes
Read the full abstract

All authors Jian Shi, Michael Birsak, Wenqing Cui, Zhenyu Li, Peter Wonka