Computer Vision · Cross-listed from cs.RO
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Saturday 25 October
Self-balancing exoskeletons offer a promising mobility solution for individuals with lower-limb disabilities. For reliable long-term operation, these exoskeletons require a perception system that is effective in changing environments. In this work, we introduce LT-Exosense, a vision-centric, multi-session mapping system designed to support long-term (semi)-autonomous navigation for exoskeleton users. LT-Exosense extends single-session mapping capabilities by incrementally fusing spatial knowledge across multiple sessions, detecting environmental changes, and updating a persistent global map. This representation enables intelligent path planning, which can adapt to newly observed obstacles and can recover previous routes when obstructions are removed. We validate LT-Exosense through several real-world experiments, demonstrating a scalable multi-session map that achieves an average point-to-point error below 5 cm when compared to ground-truth laser scans. We also illustrate the potential application of adaptive path planning in dynamically changing indoor environments.
Computer Vision
I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
Participating in efforts to endow generative AI with the 3D physical world perception, we propose I2-NeRF, a novel neural radiance field framework that enhances isometric and isotropic metric perception under media degradation. While existing NeRF models predominantly rely on object-centric sampling, I2-NeRF introduces a reverse-stratified upsampling strategy to achieve near-uniform sampling across 3D space, thereby preserving isometry. We further present a general radiative formulation for media degradation that unifies emission, absorption, and scattering into a particle model governed by the Beer-Lambert attenuation law. By composing the direct and media-induced in-scatter radiance, this formulation extends naturally to complex media environments such as underwater, haze, and even low-light scenes. By treating light propagation uniformly in both vertical and horizontal directions, I2-NeRF enables isotropic metric perception and can even estimate medium properties such as water depth. Experiments on real-world datasets demonstrate that our method significantly improves both reconstruction fidelity and physical plausibility compared to existing approaches.
Read the full abstract
Computer Vision · Cross-listed from cs.CL
SentiMaithili: A Benchmark Dataset for Sentiment and Reason Generation for the Low-Resource Maithili Language
Developing benchmark datasets for low-resource languages poses significant challenges, primarily due to the limited availability of native linguistic experts and the substantial time and cost involved in annotation. Given these challenges, Maithili is still underrepresented in natural language processing research. It is an Indo-Aryan language spoken by more than 13 million people in the Purvanchal region of India, valued for its rich linguistic structure and cultural significance. While sentiment analysis has achieved remarkable progress in high-resource languages, resources for low-resource languages, such as Maithili, remain scarce, often restricted to coarse-grained annotations and lacking interpretability mechanisms. To address this limitation, we introduce a novel dataset comprising 3,221 Maithili sentences annotated for sentiment polarity and accompanied by natural language justifications. Moreover, the dataset is carefully curated and validated by linguistic experts to ensure both label reliability and contextual fidelity. Notably, the justifications are written in Maithili, thereby promoting culturally grounded interpretation and enhancing the explainability of sentiment models. Furthermore, extensive experiments using both classical machine learning and state-of-the-art transformer architectures demonstrate the dataset's effectiveness for interpretable sentiment analysis. Ultimately, this work establishes the first benchmark for explainable affective computing in Maithili, thus contributing a valuable resource to the broader advancement of multilingual NLP and explainable AI.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
Frequency-Spatial Interaction Driven Network for Low-Light Image Enhancement
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. With the advent of deep learning, the LLIE technique has achieved significant breakthroughs. However, existing LLIE methods either ignore the important role of frequency domain information or fail to effectively promote the propagation and flow of information, limiting the LLIE performance. In this paper, we develop a novel frequency-spatial interaction-driven network (FSIDNet) for LLIE based on two-stage architecture. To be specific, the first stage is designed to restore the amplitude of low-light images to improve the lightness, and the second stage devotes to restore phase information to refine fine-grained structures. Considering that Frequency domain and spatial domain information are complementary and both favorable for LLIE, we further develop two frequency-spatial interaction blocks which mutually amalgamate the complementary spatial and frequency information to enhance the capability of the model. In addition, we construct the Information Exchange Module (IEM) to associate two stages by adequately incorporating cross-stage and cross-scale features to effectively promote the propagation and flow of information in the two-stage network structure. Finally, we conduct experiments on several widely used benchmark datasets (i.e., LOL-Real, LSRW-Huawei, etc.), which demonstrate that our method achieves the excellent performance in terms of visual results and quantitative metrics while preserving good model efficiency.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Power to the Clients: Federated Learning in a Dictatorship Setting
Federated learning (FL) has emerged as a promising paradigm for decentralized model training, enabling multiple clients to collaboratively learn a shared model without exchanging their local data. However, the decentralized nature of FL also introduces vulnerabilities, as malicious clients can compromise or manipulate the training process. In this work, we introduce dictator clients, a novel, well-defined, and analytically tractable class of malicious participants capable of entirely erasing the contributions of all other clients from the server model, while preserving their own. We propose concrete attack strategies that empower such clients and systematically analyze their effects on the learning process. Furthermore, we explore complex scenarios involving multiple dictator clients, including cases where they collaborate, act independently, or form an alliance in order to ultimately betray one another. For each of these settings, we provide a theoretical analysis of their impact on the global model's convergence. Our theoretical algorithms and findings about the complex scenarios including multiple dictator clients are further supported by empirical evaluations on both computer vision and natural language processing benchmarks.
Read the full abstract
Computer Vision
Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation
Source-free domain adaptation (SFDA) involves training a model on source domain and then applying it to a related target domain without access to the source data and labels during adaptation. The complexity of scene information and lack of the source domain make SFDA a difficult task. Recent studies have shown promising results, but many approaches to domain adaptation concentrate on domain shift and neglect the effects of negative transfer, which may impede enhancements of model performance during adaptation. n this paper, addressing this issue, we propose a novel framework of Attention Residual Fusion Network (ARFNet) based on contrast learning for SFDA to alleviate negative transfer and domain shift during the progress of adaptation, in which attention residual fusion, global-local attention contrast, and dynamic centroid evaluation are exploited. Concretely, the attention mechanism is first exploited to capture the discriminative region of the target object. Then, in each block, attention features are decomposed into spatial-wise and channel-wise attentions to achieve the cross-layer attention residual fusion progressively and self-distillation. During adaptation progress, we contrast global and local representations to improve the perceptual capabilities of different categories, which enables the model to discriminate variations between inner-class and intra-class. Finally, a dynamic centroid evaluation strategy is exploited to evaluate the trustworthy centroids and labels for self-supervised self-distillation, which aims to accurately approximate the center of the source domain and pseudo-labels to mitigate domain shift. To validate the efficacy, we execute comprehensive experiments on five benchmarks of varying scales. Experimental outcomes indicate that our method surpasses other techniques, attaining superior performance across SFDA benchmarks.
Read the full abstract
Computer Vision
LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction
Vision-Language Models (VLMs) have shown significant progress in open-set challenges. However, the limited availability of 3D datasets hinders their effective application in 3D scene understanding. We propose LOC, a general language-guided framework adaptable to various occupancy networks, supporting both supervised and self-supervised learning paradigms. For self-supervised tasks, we employ a strategy that fuses multi-frame LiDAR points for dynamic/static scenes, using Poisson reconstruction to fill voids, and assigning semantics to voxels via K-Nearest Neighbor (KNN) to obtain comprehensive voxel representations. To mitigate feature over-homogenization caused by direct high-dimensional feature distillation, we introduce Densely Contrastive Learning (DCL). DCL leverages dense voxel semantic information and predefined textual prompts. This efficiently enhances open-set recognition without dense pixel-level supervision, and our framework can also leverage existing ground truth to further improve performance. Our model predicts dense voxel features embedded in the CLIP feature space, integrating textual and image pixel information, and classifies based on text and semantic similarity. Experiments on the nuScenes dataset demonstrate the method's superior performance, achieving high-precision predictions for known classes and distinguishing unknown classes without additional training data.
Read the full abstract
Computer Vision
STG-Avatar: Animatable Human Avatars via Spacetime Gaussian
Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DGS-based human avatars has made progress, it still struggles with accurately representing detailed features of non-rigid objects (e.g., clothing deformations) and dynamic regions (e.g., rapidly moving limbs). To address these challenges, we present STG-Avatar, a 3DGS-based framework for high-fidelity animatable human avatar reconstruction. Specifically, our framework introduces a rigid-nonrigid coupled deformation framework that synergistically integrates Spacetime Gaussians (STG) with linear blend skinning (LBS). In this hybrid design, LBS enables real-time skeletal control by driving global pose transformations, while STG complements it through spacetime adaptive optimization of 3D Gaussians. Furthermore, we employ optical flow to identify high-dynamic regions and guide the adaptive densification of 3D Gaussians in these regions. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines in both reconstruction quality and operational efficiency, achieving superior quantitative metrics while retaining real-time rendering capabilities. Our code is available at https://github.com/jiangguangan/STG-Avatar
Read the full abstract
Computer Vision
egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks
Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions. Existing tasks in egocentric perception focus on physical activities, hand-object interactions, and attention modeling - assuming neutral affect and uniform personality. This limits the ability of vision systems to capture key internal drivers of behavior. In this paper, we present egoEMOTION, the first dataset that couples egocentric visual and physiological signals with dense self-reports of emotion and personality across controlled and real-world scenarios. Our dataset includes over 50 hours of recordings from 43 participants, captured using Meta's Project Aria glasses. Each session provides synchronized eye-tracking video, headmounted photoplethysmography, inertial motion data, and physiological baselines for reference. Participants completed emotion-elicitation tasks and naturalistic activities while self-reporting their affective state using the Circumplex Model and Mikels' Wheel as well as their personality via the Big Five model. We define three benchmark tasks: (1) continuous affect classification (valence, arousal, dominance); (2) discrete emotion classification; and (3) trait-level personality inference. We show that a classical learning-based method, as a simple baseline in real-world affect prediction, produces better estimates from signals captured on egocentric vision systems than processing physiological signals. Our dataset establishes emotion and personality as core dimensions in egocentric perception and opens new directions in affect-driven modeling of behavior, intent, and interaction.
Read the full abstract
Computer Vision
Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
Pretrained vision-language models such as CLIP achieve strong zero-shot generalization but remain vulnerable to distribution shifts caused by input corruptions. In this work, we investigate how corruptions affect CLIP's image embeddings and uncover a consistent phenomenon we term as embedding variance collapse, where both intra-class and inter-class variances shrink as corruption severity increases. We find that this collapse is closely tied to performance degradation, with inter-class variance strongly correlated with classification accuracy. To explain this phenomenon, we analyze how corruptions alter the structure of the embedding space. Our theoretical results suggest that the visual encoder tends to encode corruption-related signals, which dilute class-discriminative features and compress the representation geometry. We further show that maximizing inter-class variance, even when estimated from pseudo-labels, can provably enhance embedding quality. Based on this insight, we propose Mint, a simple test-time adaptation method that maximizes pseudo-label-based inter-class variance on the fly using a mean accumulator and a gradient accumulator. Mint operates effectively with small batch sizes and consistently improves performance across multiple corruption benchmarks and CLIP architectures. Our code is available at https://github.com/baowenxuan/Mint .
Read the full abstract
Computer Vision
CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding
Deep stereo matching has advanced significantly on benchmark datasets through fine-tuning but falls short of the zero-shot generalization seen in foundation models in other vision tasks. We introduce CogStereo, a novel framework that addresses challenging regions, such as occlusions or weak textures, without relying on dataset-specific priors. CogStereo embeds implicit spatial cognition into the refinement process by using monocular depth features as priors, capturing holistic scene understanding beyond local correspondences. This approach ensures structurally coherent disparity estimation, even in areas where geometry alone is inadequate. CogStereo employs a dual-conditional refinement mechanism that combines pixel-wise uncertainty with cognition-guided features for consistent global correction of mismatches. Extensive experiments on Scene Flow, KITTI, Middlebury, ETH3D, EuRoc, and real-world demonstrate that CogStereo not only achieves state-of-the-art results but also excels in cross-domain generalization, shifting stereo vision towards a cognition-driven approach.
Read the full abstract
Computer Vision
GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation
Vision Language Models (VLMs) achieve strong performance on many vision-language tasks but often struggle with spatial reasoning$\unicode{x2014}$a prerequisite for many applications. Empirically, we find that a dataset produced by a current training data generation pipeline has a 57.6% human validation rate. These rates stem from current limitations: single-image 3D reconstruction introduces cascading modeling errors and requires wide answer tolerances, while caption-based methods require hyper-detailed annotations and suffer from generative hallucinations. We present GRAID, built on the key insight that qualitative spatial relationships can be reliably determined from 2D geometric primitives alone. By operating exclusively on 2D bounding boxes from standard object detectors, GRAID avoids both 3D reconstruction errors and generative hallucinations, resulting in datasets that are of higher quality than existing tools that produce similar datasets as validated by human evaluations. We apply our framework to the BDD100k, NuImages, and Waymo datasets, generating over 8.5 million high-quality VQA pairs creating questions spanning spatial relations, counting, ranking, and size comparisons. We evaluate one of the datasets and find it achieves 91.16% human-validated accuracy$\unicode{x2014}$compared to 57.6% on a dataset generated by recent work. Critically, we demonstrate that when trained on GRAID data, models learn spatial reasoning concepts that generalize: models fine-tuned on 6 question types improve on over 10 held-out types, with accuracy gains of 47.5% on BDD and 37.9% on NuImages for Llama 3.2B 11B, and when trained on all questions types, achieve improvements on several existing benchmarks such as BLINK. The GRAID framework, datasets, and additional information can be found $\href{this https URL}{here}$.
Read the full abstract
Computer Vision
Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
Capturing diversity is crucial in conditional and prompt-based image generation, particularly when conditions contain uncertainty that can lead to multiple plausible outputs. To generate diverse images reflecting this diversity, traditional methods often modify random seeds, making it difficult to discern meaningful differences between samples, or diversify the input prompt, which is limited in verbally interpretable diversity. We propose Rainbow, a novel conditional image generation framework, applicable to any pretrained conditional generative model, that addresses inherent condition/prompt uncertainty and generates diverse plausible images. Rainbow is based on a simple yet effective idea: decomposing the input condition into diverse latent representations, each capturing an aspect of the uncertainty and generating a distinct image. First, we integrate a latent graph, parameterized by Generative Flow Networks (GFlowNets), into the prompt representation computation. Second, leveraging GFlowNets' advanced graph sampling capabilities to capture uncertainty and output diverse trajectories over the graph, we produce multiple trajectories that collectively represent the input condition, leading to diverse condition representations and corresponding output images. Evaluations on natural image and medical image datasets demonstrate Rainbow's improvement in both diversity and fidelity across image synthesis, image generation, and counterfactual generation tasks.
Read the full abstract
Computer Vision
Mitigating Coordinate Prediction Bias from Positional Encoding Failures
While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, precise coordinate prediction remains a significant challenge, particularly as high-resolution inputs cause visual positional encodings (VPEs) to degrade. We demonstrate that these encoding failures do not result in random noise but instead trigger predictable, directional biases, suggesting that models default to internal spatial priors when grounding signals are weak. To counteract this, we introduce Vision-PE Shuffle Guidance (VPSG), a training-free, inference-time correction method. VPSG isolates position-unconditioned tendencies by shuffling VPEs and utilizes this negative evidence to steer digit decoding through a lightweight finite-state machine. Evaluation on the ScreenSpot-Pro benchmark confirms that VPSG effectively rectifies coordinate drift, yielding consistent improvements in localization accuracy across various model scales without any retraining. Our code is available at https://github.com/taoxj2001/VPSG.
Read the full abstract
Friday 24 October
Computer Vision
Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
Vision Transformers (ViTs), such as DINOv2, achieve strong performance across domains but often repurpose low-informative patch tokens in ways that reduce the interpretability of attention and feature maps. This challenge is especially evident in medical imaging, where domain shifts can degrade both performance and transparency. In this paper, we introduce Randomized-MLP (RMLP) regularization, a contrastive learning-based method that encourages more semantically aligned representations. We use RMLPs when fine-tuning DINOv2 to both medical and natural image modalities, showing that it improves or maintains downstream performance while producing more interpretable attention maps. We also provide a mathematical analysis of RMLPs, offering insights into its role in enhancing ViT-based models and advancing our understanding of contrastive learning.
Read the full abstract
Computer Vision
Automating Coral Reef Fish Family Identification on Video Transects Using a YOLOv8-Based Deep Learning Pipeline
Coral reef monitoring in the Western Indian Ocean is limited by the labor demands of underwater visual censuses. This work evaluates a YOLOv8-based deep learning pipeline for automating family-level fish identification from video transects collected in Kenya and Tanzania. A curated dataset of 24 families was tested under different configurations, providing the first region-specific benchmark for automated reef fish monitoring in the Western Indian Ocean. The best model achieved mAP@0.5 of 0.52, with high accuracy for abundant families but weaker detection of rare or complex taxa. Results demonstrate the potential of deep learning as a scalable complement to traditional monitoring methods.
Read the full abstract
Computer Vision
Deep Learning Models for Coral Bleaching Classification in Multi-Condition Underwater Image Datasets
Coral reefs support numerous marine organisms and are an important source of coastal protection from storms and floods, representing a major part of marine ecosystems. However coral reefs face increasing threats from pollution, ocean acidification, and sea temperature anomalies, making efficient protection and monitoring heavily urgent. Therefore, this study presents a novel machine-learning-based coral bleaching classification system based on a diverse global dataset with samples of healthy and bleached corals under varying environmental conditions, including deep seas, marshes, and coastal zones. We benchmarked and compared three state-of-the-art models: Residual Neural Network (ResNet), Vision Transformer (ViT), and Convolutional Neural Network (CNN). After comprehensive hyperparameter tuning, the CNN model achieved the highest accuracy of 88%, outperforming existing benchmarks. Our findings offer important insights into autonomous coral monitoring and present a comprehensive analysis of the most widely used computer vision models.
Read the full abstract
Computer Vision · Cross-listed from cs.AI
Multimodal Detection of Fake Reviews using BERT and ResNet-50
In the current digital commerce landscape, user-generated reviews play a critical role in shaping consumer behavior, product reputation, and platform credibility. However, the proliferation of fake or misleading reviews often generated by bots, paid agents, or AI models poses a significant threat to trust and transparency within review ecosystems. Existing detection models primarily rely on unimodal, typically textual, data and therefore fail to capture semantic inconsistencies across different modalities. To address this gap, a robust multimodal fake review detection framework is proposed, integrating textual features encoded with BERT and visual features extracted using ResNet-50. These representations are fused through a classification head to jointly predict review authenticity. To support this approach, a curated dataset comprising 21,142 user-uploaded images across food delivery, hospitality, and e-commerce domains was utilized. Experimental results indicate that the multimodal model outperforms unimodal baselines, achieving an F1-score of 0.934 on the test set. Additionally, the confusion matrix and qualitative analysis highlight the model's ability to detect subtle inconsistencies, such as exaggerated textual praise paired with unrelated or low-quality images, commonly found in deceptive content. This study demonstrates the critical role of multimodal learning in safeguarding digital trust and offers a scalable solution for content moderation across various online platforms.
Read the full abstract
Computer Vision
Point-level Uncertainty Evaluation of Mobile Laser Scanning Point Clouds
Reliable quantification of uncertainty in Mobile Laser Scanning (MLS) point clouds is essential for ensuring the accuracy and credibility of downstream applications such as 3D mapping, modeling, and change analysis. Traditional backward uncertainty modeling heavily rely on high-precision reference data, which are often costly or infeasible to obtain at large scales. To address this issue, this study proposes a machine learning-based framework for point-level uncertainty evaluation that learns the relationship between local geometric features and point-level errors. The framework is implemented using two ensemble learning models, Random Forest (RF) and XGBoost, which are trained and validated on a spatially partitioned real-world dataset to avoid data leakage. Experimental results demonstrate that both models can effectively capture the nonlinear relationships between geometric characteristics and uncertainty, achieving mean ROC-AUC values above 0.87. The analysis further reveals that geometric features describing elevation variation, point density, and local structural complexity play a dominant role in predicting uncertainty. The proposed framework offers a data-driven perspective of uncertainty evaluation, providing a scalable and adaptable foundation for future quality control and error analysis of large-scale point clouds.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
DMVFC: Deep Learning Based Functionally Consistent Tractography Fiber Clustering Using Multimodal Diffusion MRI and Functional MRI
Tractography fiber clustering using diffusion MRI (dMRI) is a crucial method for white matter (WM) parcellation to enable analysis of brains structural connectivity in health and disease. Current fiber clustering strategies primarily use the fiber geometric characteristics (i.e., the spatial trajectories) to group similar fibers into clusters, while neglecting the functional and microstructural information of the fiber tracts. There is increasing evidence that neural activity in the WM can be measured using functional MRI (fMRI), providing potentially valuable multimodal information for fiber clustering to enhance its functional coherence. Furthermore, microstructural features such as fractional anisotropy (FA) can be computed from dMRI as additional information to ensure the anatomical coherence of the clusters. In this paper, we develop a novel deep learning fiber clustering framework, namely Deep Multi-view Fiber Clustering (DMVFC), which uses joint multi-modal dMRI and fMRI data to enable functionally consistent WM parcellation. DMVFC can effectively integrate the geometric and microstructural characteristics of the WM fibers with the fMRI BOLD signals along the fiber tracts. DMVFC includes two major components: (1) a multi-view pretraining module to compute embedding features from each source of information separately, including fiber geometry, microstructure measures, and functional signals, and (2) a collaborative fine-tuning module to simultaneously refine the differences of embeddings. In the experiments, we compare DMVFC with two state-of-the-art fiber clustering methods and demonstrate superior performance in achieving functionally meaningful and consistent WM parcellation results.
Read the full abstract
Computer Vision
Combining SAR Simulators to Train ATR Models with Synthetic Data
This work aims to train Deep Learning models to perform Automatic Target Recognition (ATR) on Synthetic Aperture Radar (SAR) images. To circumvent the lack of real labelled measurements, we resort to synthetic data produced by SAR simulators. Simulation offers full control over the virtual environment, which enables us to generate large and diversified datasets at will. However, simulations are intrinsically grounded on simplifying assumptions of the real world (i.e. physical models). Thus, synthetic datasets are not as representative as real measurements. Consequently, ATR models trained on synthetic images cannot generalize well on real measurements. Our contributions to this problem are twofold: on one hand, we demonstrate and quantify the impact of the simulation paradigm on the ATR. On the other hand, we propose a new approach to tackle the ATR problem: combine two SAR simulators that are grounded on different (but complementary) paradigms to produce synthetic datasets. To this end, we use two simulators: MOCEM, which is based on a scattering centers model approach, and Salsa, which resorts on a ray tracing strategy. We train ATR models using synthetic dataset generated both by MOCEM and Salsa and our Deep Learning approach called ADASCA. We reach an accuracy of almost 88 % on the MSTAR measurements.
Read the full abstract
Computer Vision
Towards Fine-Grained Human Motion Video Captioning
Generating accurate descriptions of human actions in videos remains a challenging task for video captioning models. Existing approaches often struggle to capture fine-grained motion details, resulting in vague or semantically inconsistent captions. In this work, we introduce the Motion-Augmented Caption Model (M-ACM), a novel generative framework that enhances caption quality by incorporating motion-aware decoding. At its core, M-ACM leverages motion representations derived from human mesh recovery to explicitly highlight human body dynamics, thereby reducing hallucinations and improving both semantic fidelity and spatial alignment in the generated captions. To support research in this area, we present the Human Motion Insight (HMI) Dataset, comprising 115K video-description pairs focused on human movement, along with HMI-Bench, a dedicated benchmark for evaluating motion-focused video captioning. Experimental results demonstrate that M-ACM significantly outperforms previous methods in accurately describing complex human motions and subtle temporal variations, setting a new standard for motion-centric video captioning.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models
Pretrained diffusion models have demonstrated strong capabilities in zero-shot inverse problem solving by incorporating observation information into the generation process of the diffusion models. However, this presents an inherent dilemma: excessive integration can disrupt the generative process, while insufficient integration fails to emphasize the constraints imposed by the inverse problem. To address this, we propose Noise Combination Sampling, a novel method that synthesizes an optimal noise vector from a noise subspace to approximate the measurement score, replacing the noise term in the standard Denoising Diffusion Probabilistic Models process. This enables conditional information to be naturally embedded into the generation process without reliance on step-wise hyperparameter tuning. Our method can be applied to a wide range of inverse problem solvers, including image compression, and, particularly when the number of generation steps $T$ is small, achieves superior performance with negligible computational overhead, significantly improving robustness and stability.
Read the full abstract
Computer Vision
Scanner-Agnostic MRI Harmonization via SSIM-Guided Disentanglement
The variability introduced by differences in MRI scanner models, acquisition protocols, and imaging sites hinders consistent analysis and generalizability across multicenter studies. We present a novel image-based harmonization framework for 3D T1-weighted brain MRI, which disentangles anatomical content from scanner- and site-specific variations. The model incorporates a differentiable loss based on the Structural Similarity Index (SSIM) to preserve biologically meaningful features while reducing inter-site variability. This loss enables separate evaluation of image luminance, contrast, and structural components. Training and validation were performed on multiple publicly available datasets spanning diverse scanners and sites, with testing on both healthy and clinical populations. Harmonization using multiple style targets, including style-agnostic references, produced consistent and high-quality outputs. Visual comparisons, voxel intensity distributions, and SSIM-based metrics demonstrated that harmonized images achieved strong alignment across acquisition settings while maintaining anatomical fidelity. Following harmonization, structural SSIM reached 0.97, luminance SSIM ranged from 0.98 to 0.99, and Wasserstein distances between mean voxel intensity distributions decreased substantially. Downstream tasks showed substantial improvements: mean absolute error for brain age prediction decreased from 5.36 to 3.30 years, and Alzheimer's disease classification AUC increased from 0.78 to 0.85. Overall, our framework enhances cross-site image consistency, preserves anatomical fidelity, and improves downstream model performance, providing a robust and generalizable solution for large-scale multicenter neuroimaging studies.
Read the full abstract
Computer Vision · Cross-listed from cs.LG
MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification
Generative modeling has emerged as a powerful paradigm for representation learning, but its direct applicability to challenging fields like medical imaging remains limited: mere generation, without task alignment, fails to provide a robust foundation for clinical use. We propose MAGIC-Flow, a conditional multiscale normalizing flow architecture that performs generation and classification within a single modular framework. The model is built as a hierarchy of invertible and differentiable bijections, where the Jacobian determinant factorizes across sub-transformations. We show how this ensures exact likelihood computation and stable optimization, while invertibility enables explicit visualization of sample likelihoods, providing an interpretable lens into the model's reasoning. By conditioning on class labels, MAGIC-Flow supports controllable sample synthesis and principled class-probability estimation, effectively aiding both generative and discriminative objectives. We evaluate MAGIC-Flow against top baselines using metrics for similarity, fidelity, and diversity. Across multiple datasets, it addresses generation and classification under scanner noise, and modality-specific synthesis and identification. Results show MAGIC-Flow creates realistic, diverse samples and improves classification. MAGIC-Flow is an effective strategy for generation and classification in data-limited domains, with direct benefits for privacy-preserving augmentation, robust generalization, and trustworthy medical AI.
Read the full abstract
Computer Vision
Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than visual inputs. Some methods attempt to mitigate hallucination by amplifying visual token attention proportionally to their attention scores. However, these methods overlook the visual attention sink problem, where attention is frequently misallocated to task-irrelevant visual regions, and neglect cross-modal fusion balance by enhancing only visual attention without adjusting attention to the user query. This can result in amplifying incorrect areas while failing to properly interpret the user query. To address these challenges, we propose a simple yet effective method called Gaze Shift-Guided Cross-modal Fusion Enhancement (GIFT). GIFT pre-computes a holistic visual saliency map by tracking positive changes in visual attention, or "gaze shifts", during user query comprehension, and leverages this map to amplify attention to both salient visual information and the user query at each decoding step. This reduces the impact of visual attention sink, as irrelevant tokens exhibit minimal shifts, while ensuring balanced cross-modal fusion for well-integrated representation. Extensive experiments show that GIFT effectively mitigates hallucination in VLMs across both generative and classification tasks, achieving up to 20.7% improvement over greedy decoding, while maintaining general vision-language performance with low computational overhead.
Read the full abstract
Computer Vision
Human-Centric Anomaly Detection in Surveillance Videos Using YOLO-World and Spatio-Temporal Deep Learning
Anomaly detection in surveillance videos remains a challenging task due to the diversity of abnormal events, class imbalance, and scene-dependent visual clutter. To address these issues, we propose a robust deep learning framework that integrates human-centric preprocessing with spatio-temporal modeling for multi-class anomaly classification. Our pipeline begins by applying YOLO-World - an open-vocabulary vision-language detector - to identify human instances in raw video clips, followed by ByteTrack for consistent identity-aware tracking. Background regions outside detected bounding boxes are suppressed via Gaussian blurring, effectively reducing scene-specific distractions and focusing the model on behaviorally relevant foreground content. The refined frames are then processed by an ImageNet-pretrained InceptionV3 network for spatial feature extraction, and temporal dynamics are captured using a bidirectional LSTM (BiLSTM) for sequence-level classification. Evaluated on a five-class subset of the UCF-Crime dataset (Normal, Burglary, Fighting, Arson, Explosion), our method achieves a mean test accuracy of 92.41% across three independent trials, with per-class F1-scores consistently exceeding 0.85. Comprehensive evaluation metrics - including confusion matrices, ROC curves, and macro/weighted averages - demonstrate strong generalization and resilience to class imbalance. The results confirm that foreground-focused preprocessing significantly enhances anomaly discrimination in real-world surveillance scenarios.
Read the full abstract
Computer Vision
VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT
Vision-language models (VLMs) are increasingly used to evaluate multimodal content, including presentation slides, yet their slide-specific understanding remains underexplored {despite their growing role as critics in agentic, model-forward pipelines}. We introduce VLM-SlideEval, an evaluation framework that probes VLMs along three axes: (1) element-level extraction from slide images aligned to ground truth; (2) robustness to controlled perturbations in geometry, style, and text; and (3) higher-level comprehension, such as recovering a deck's narrative order from shuffled slides. Using publicly available decks from Zenodo (https://huggingface.co/datasets/Forceless/Zenodo10K/viewer/default/pptx), we standardize ground-truth element metadata from PowerPoint XML and live renderings into a unified, verifiable schema. Empirically, VLMs underperform on pixel-accurate extraction and show non-trivial agreement, fidelity, and consistency under controlled perturbations, while performing better on single-slide content understanding; however, they do not reliably capture narrative structure across slides. These results highlight the limits of current VLMs for slide evaluation and motivate calibrated, critic-in-the-loop evaluators that drive iterative refinement and selection in agentic pipelines.
Read the full abstract
Computer Vision
Caption-Driven Explainability: Probing CNNs for Bias via CLIP
Robustness has become one of the most critical problems in machine learning (ML). The science of interpreting ML models to understand their behavior and improve their robustness is referred to as explainable artificial intelligence (XAI). One of the state-of-the-art XAI methods for computer vision problems is to generate saliency maps. A saliency map highlights the pixel space of an image that excites the ML model the most. However, this property could be misleading if spurious and salient features are present in overlapping pixel spaces. In this paper, we propose a caption-based XAI method, which integrates a standalone model to be explained into the contrastive language-image pre-training (CLIP) model using a novel network surgery approach. The resulting caption-based XAI model identifies the dominant concept that contributes the most to the models prediction. This explanation minimizes the risk of the standalone model falling for a covariate shift and contributes significantly towards developing robust ML models. Our code is available at https://github.com/patch0816/caption-driven-xai
Read the full abstract
Computer Vision
Reconnaissance Automatique des Langues des Signes : Une Approche Hybridée CNN-LSTM Basée sur Mediapipe
Sign languages play a crucial role in the communication of deaf communities, but they are often marginalized, limiting access to essential services such as healthcare and education. This study proposes an automatic sign language recognition system based on a hybrid CNN-LSTM architecture, using Mediapipe for gesture keypoint extraction. Developed with Python, TensorFlow and Streamlit, the system provides real-time gesture translation. The results show an average accuracy of 92%, with very good performance for distinct gestures such as “Hello” and “Thank you”. However, some confusions remain for visually similar gestures, such as “Call” and “Yes”. This work opens up interesting perspectives for applications in various fields such as healthcare, education and public services.