Peer Revenue Publish or profit

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision

Wednesday 3 June

Computer Vision

PereStruct: Multimodal Semantic Assembly for Robust Historical Document Parsing

Maksim Shandybo, Ivan Bespalov, Daniil Yefimov et al. (+2 more)

Parsing historical documents with complex, non-standard layouts remains a fundamental bottleneck in large-scale archival digitization. Unlike modern typography, historical newspapers exhibit severe physical degradation and highly irregular page structures that confound even state-of-the-art vision-language models, presenting severe out-of-distribution challenges. We address this gap with an automated pipeline specifically designed for parsing historical newspapers, documents characterized by particularly intricate multi-column layouts. Our approach combines a fine-tuned YOLO architecture for layout analysis and block detection, trained on 1,426 fully human-annotated scanned pages, with a novel semantic assembly module that reconstructs articles by jointly modeling lexical-semantic similarity via TF-IDF, visual embeddings from our fine-tuned YOLO, and geometric layout constraints. This multi-modal integration yields state-of-the-art performance, achieving an F1 score of 0.904 on block-to-article mapping. Notably, end-to-end evaluation against vision-language models (Qwen3.6-35B-A3B and Qwen3.6-Plus) demonstrates that PereStruct achieves substantially higher fidelity (BLEU approximately 0.96 vs 0.34), validating that modular architectures excel where generic VLMs fail on complex historical layouts. To support reproducibility and advance research in this domain, we release both the training corpus of 599 annotated pages and a curated PereStruct benchmark of 93 pages with expert-verified ground-truth block-to-article mappings. This framework establishes a robust foundation for high-fidelity digitization and semantic reconstruction of complex archival materials.
Read the full abstract

All authors Maksim Shandybo, Ivan Bespalov, Daniil Yefimov, Marina Kosheleva, Alexander Loukianov

Computer Vision

Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation

Qiaoyu Chen and Bing Zhang

Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations. Under optimization on limited samples, models overfit to local domain shortcuts. Fine-tuning massive weights on specialized data introduces erroneous inductive biases, inducing a measurable $\mathcal{L}_2$ norm perturbation in the high-dimensional feature space – a phenomenon we formalize as anchor drift. Amplified by nonlinear activations, this drift impairs zero-shot forgery detection across unseen domains.We propose a gradient-free methodology reframing detection from binary classification to an out-of-distribution (OOD) anomaly measurement problem. Treating a frozen foundation model as a stable coordinate system, we establish an absolute natural anchor on the real visual manifold by analytically decoupling statistical and semantic deviations, derived from attention-weighted spatial moments and orthogonal projection of perceptual inconsistencies. Evaluated in an extreme zero-shot setting (trained on face forgeries, tested on universal Text-to-Image generations), our method significantly outperforms gradient-optimized paradigms. Backpropagation-free forward passes and linear solvers enable hardware-agnostic, edge-deployable calibration with minimal latency. Furthermore, the Sherman-Morrison formula unlocks instantaneous online learning against novel attacks and enables privacy-preserving federated collaboration via covariance delta transmission.
Read the full abstract

Computer Vision

Real-Time Industrial Defect Detection on Edge Hardware Using Fine-Tuned YOLOv8: A Systematic Benchmark on the NEU Surface Defect Database and MVTec AD with Automotive & Battery Manufacturing Extensions

Emmanuel Ezeji Somtochukwu and Nitesh Rijal

Automated surface defect detection is critical for ensuring rigorous quality control in high-speed manufacturing environments. While deep learning models offer remarkable accuracy, deploying them on resource-constrained edge hardware without introducing significant latency remains a persistent challenge. This paper presents Industrial-YOLO, an edge-optimized framework built upon a fine-tuned YOLOv8 architecture specifically engineered for real-time industrial defect detection. We conduct a systematic benchmark utilizing the NEU surface defect database for steel sheets and the MVTec AD dataset, supplemented with custom automotive manufacturing extensions representing real-world structural anomalies (scratches, pits, and inclusions). To bridge the gap between algorithmic complexity and edge hardware constraints, target-specific optimizations are introduced via TensorRT and OpenVINO acceleration engines. Experimental results demonstrate that Industrial-YOLO achieves a high-velocity inference speed exceeding 120 FPS on the NVIDIA Jetson Orin platform while maintaining an exceptional mean Average Precision (mAP) of 98.5%. The proposed framework showcases highly robust, zero-latency performance when deployed directly onto an active automotive assembly line, offering a scalable blueprint for next-generation automated optical inspection (AOI) systems.
Read the full abstract

Computer Vision

What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery

Santiago Cepeda, Olga Esteban-Sinovas, Ignacio Arrese et al. (+1 more)

Maximal safe resection is the primary objective in glioma surgery. Neuronavigation guidance is progressively degraded by brain shift after dural opening. Intraoperative MRI can compensate but needs dedicated infrastructure and is rarely available, whereas intraoperative ultrasound (ioUS) is inexpensive, repeatable, and compatible with routine workflows. Navigation systems combining ioUS with preoperative MRI usually rely on rigid registration; even deformable multimodal registration is limited by ultrasound speckle contrast, a narrow field of view, and the inability to represent structures absent from the preoperative scan, most critically the resection cavity and residual tumor. We propose an end-to-end pipeline that generates a new whole-brain MRI volume in the preoperative imaging space by merging the preoperative MRI, a synthetic MRI generated from the ioUS, and a deformable registration anchored on that synthetic image. It integrates a 2.5D residual-transformer synthesis backbone (ResViT-2.5D) and a two-stage registration coupling NiftyReg with a synthesis-anchored SynthMorph stage, operating directly on raw scanner inputs. On a post-resection ReMIND cohort, ResViT-2.5D produced synthetic images closely matching the intraoperative T2 across structural, intensity, and perceptual metrics. In 14 subjects with 215 expert landmarks, the synthesis-anchored registration reduced the mean target registration error from 6.27 to 5.86 mm, matching a strong classical NiftyReg baseline (5.85 mm) while yielding a diffeomorphic deformation field in every subject. The contribution is not a gain in registration accuracy but the integrated volume itself, which inside the ultrasound field of view it reflects the intraoperative post-resection state. This provides the surgeon with an MRI-like update of the operative field with potential for integration into surgical-navigation workflows.
Read the full abstract

All authors Santiago Cepeda, Olga Esteban-Sinovas, Ignacio Arrese, Rosario Sarabia

Computer Vision · Cross-listed from eess.SP

FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis

Shuo Liu, Xianghong Lin, Yukun Wei et al. (+1 more)

The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. However, detection is severely hampered by two fundamental issues during model training. Firstly, extreme class imbalance (less than 1% steganographic samples) induces a strong decision bias. Secondly, the invisibility of generative steganography means its features are nearly indistinguishable from benign text; this similarity, compounded by their extreme rarity, leads to severe feature marginalization, where faint steganographic signals are completely overwhelmed. To directly address these optimization-level challenges, we propose FADRW (Feature-Aware Modulated and Dynamically Reweighted Loss), a novel loss function framework engineered for few-shot steganalysis. FADRW employs Dynamic Reweighting to progressively counteract decision bias, and a Feature-Aware Modulation module to structurally reshape the feature space, preventing feature marginalization by enhancing the separability of these subtle features. Extensive experiments on datasets from three real-world social platforms demonstrate that FADRW significantly outperforms state-of-the-art methods, particularly in the challenging few-shot steganographic sample scenario.
Read the full abstract

All authors Shuo Liu, Xianghong Lin, Yukun Wei, Zhongliang Yang

Computer Vision

MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework

Haowen Xiang, Yibo Yan, Jiahao Huo et al. (+4 more)

Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language Models (VLMs), but this design makes deployment expensive in both storage and computational overhead. Existing efficiency techniques usually optimize only part of this budget, leaving multimodal retrievers without a unified way to trade accuracy for both vector width and encoder depth. Therefore, we propose MM-Matryoshka, a 2D Matryoshka training framework for budget-elastic Visual Document Retrieval (VDR), enabling ColPali-style multi-vector retrieval elastic along both dimension and layer. At inference time, a single retriever can select a 2D selectable budget without training separate models for different budgets. Through comprehensive experiments across multiple representative backbones, we demonstrate that by retaining significantly higher quality than direct truncation baselines while substantially reducing storage and computational overhead, MM-Matryoshka can offer robust budget elasticity for efficient VDR.
Read the full abstract

All authors Haowen Xiang, Yibo Yan, Jiahao Huo, Yu Huang, Yi Cao, Mingdong Ou, Xuming Hu

Computer Vision · Cross-listed from q-bio.QM

DSU-Net: An Attention-Enhanced Dense Skip U-Net for Breast Lesion Segmentation in Mammographic Images

Reza Bozorgpour and Mohammadreza Soltany Sadrabadi

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early detection essential for effective treatment. Mammography is the primary screening modality; however, accurate delineation of suspicious lesions remains challenging and subject to inter-observer variability. Automated segmentation methods can assist radiologists by providing consistent and efficient lesion localization. This study presents DSU-Net, an attention-enhanced Dense Skip U-Net architecture for automated breast lesion segmentation in mammographic images. The proposed framework integrates dense skip connections and attention mechanisms to improve feature propagation, preserve spatial information, and enhance lesion boundary delineation. Experiments were conducted using the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). To address severe foreground-background imbalance, a composite loss function combining Dice loss, focal loss, and binary cross-entropy loss was employed during training. The proposed model achieved a Dice Similarity Coefficient of 0.9421, an Intersection over Union of 0.8905, an accuracy of 0.9711, and an AUC-ROC of 0.9878 on the validation dataset. Qualitative evaluation demonstrated accurate delineation of lesions with varying sizes and morphologies, while quantitative results confirmed robust discrimination between lesion and background regions. These findings demonstrate that DSU-Net provides accurate and reliable breast lesion segmentation in mammographic images and highlights the potential of attention-guided deep learning for computer-aided breast cancer screening and diagnosis.
Read the full abstract

Computer Vision

Attention-Guided Autoencoder Fusion for Insulator Defect Detection Using UAV Transmission-Line Imaging

Malak Allam, Khaled Shaban and Ali Hamdi

Automated defect detection in high-voltage transmission-line insulators remains challenging due to severe class imbalance, large scale variation, and the small spatial extent of defect instances in Unmanned Aerial Vehicle (UAV) imagery. To address these challenges, this paper proposes AE-YOLO, an Attention-Guided AutoEncoder-Enhanced YOLO framework for robust insulator defect detection. The architecture integrates lightweight bottleneck autoencoders within a Feature Pyramid Network-Path Aggregation Network (FPN-PAN) neck. This preserves anomaly-sensitive information during multi-scale feature fusion. Convolutional Block Attention Modules (CBAM) are used throughout the backbone, enhancing feature discrimination and suppressing background interference. The framework also introduces a variance-maximizing autoencoder regularization strategy, which encourages diverse, defect-discriminative latent representations. The network trains using a unified objective that combines focal loss, Complete IoU (CIoU) loss, and autoencoder regularization to address foreground-background imbalance and improve localization accuracy. During inference, Weighted Boxes Fusion (WBF) combines predictions from YOLOv8, YOLOv10, and YOLO11. An autoencoder-guided confidence boosting mechanism improves sensitivity to rare defect categories. Experiments on the Insulator-Defect Detection dataset show that AE-YOLO with an EfficientNetV2 backbone achieves 95.10 percent mAP at 0.5, 96.40 percent precision, and 93.80 percent recall. This performance surpasses the strongest YOLO-family baseline by 5.0 points in mAP at 0.5 and 6.7 points in recall. These results confirm the effectiveness and adaptability of the framework. The model is a practical and scalable solution for UAV-based transmission-line inspection and defect monitoring.
Read the full abstract

Computer Vision

GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory

Haozhe Chi, Yang Jin and Yadong Mu

Agentic long-video question answering often relies on sparse RGB sampling and caption retrieval. This reliance can lead to missed brief motion events and repeated processing of irrelevant intervals. We introduce GOPAgen, a framework that integrates codec-native Groups of Pictures (GOPs) and motion vectors into an agentic retrieval pipeline. GOPAgen constructs global textual memory and uses two-stage query-conditioned temporal selection. A global-sufficiency check precedes local evidence extraction. Caption and motion agents represent selected intervals as typed memory pages containing complementary appearance and motion evidence, temporal metadata, and provenance. A GOP-Tree organizes these pages for conditional retrieval when the global evidence is insufficient. GOPAgen achieves 65.3% accuracy on MotionBench Test and 78.7% on EgoSchema, exceeding the reported agentic baselines listed for these benchmarks. It also achieves 73.2% on LongVideoBench validation and 77.3% on MLVU, while remaining below the strongest listed baseline on LVBench and Video-MME Long. These results support codec-aware structured memory as an effective interface for selective long-video reasoning.
Read the full abstract

Computer Vision

BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding

Muhammad Usama, Didier Stricker, Mohammad Sadil Khan et al. (+1 more)

Learning representations of CAD models is a largely open problem. While 3D representation learning has flourished around point clouds and meshes, the native format of CAD - boundary representations BReps, which encodes exact parametric surfaces, curves, and their topology, has received little attention as a representation learning substrate. We introduce BRepCLIP, the first framework to align BRep geometry with language and image embeddings through contrastive pretraining. We model each CAD object as a sequence of face and edge tokens with separate discrete vocabularies for surface and curve geometry, augmented with spatial and semantic descriptors that capture surface types (e.g., cylindrical, torus, NURBS) and curve primitives (e.g., line, arc, B-spline). A transformer encoder aggregates these tokens into a global BRep embedding, aligned with CLIP's text and image encoders via a joint contrastive objective. BRepCLIP generates more discriminative and semantically grounded embeddings than existing point-based alternatives, improving Top-1 retrieval over OpenShape by 40.4%, 22.0%, and 23.9% on ABC, CADParser, and Automate, respectively, and improving zero-shot classification on FabWave by 15% in Top-1 score. We further demonstrate its utility as a CAD-aware similarity metric for evaluating text and image-conditioned CAD generation, establishing the importance of structure-aware pretraining for multimodal CAD understanding. Project page is available at https://muhammadusama100.github.io/BrepClip2026/
Read the full abstract

All authors Muhammad Usama, Didier Stricker, Mohammad Sadil Khan, Muhammad Zeshan Afzal

Computer Vision

Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learning

Amirhossein Zhalehmehrabi, Tiziano Tezze, Alberto Castellini et al. (+1 more)

We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileged LiDAR sensing guides the contrastive objective through a geometry-aware similarity metric and adaptive temperature scaling, encouraging visual embeddings to capture navigation-relevant structure rather than scene-specific appearance. The resulting encoder is pretrained independently, frozen, and used as the perceptual backbone for reinforcement learning, decoupling representation learning from policy optimization. We further introduce a cross-stage domain mismatch between representation pretraining and policy learning to suppress environment-specific shortcuts and promote reliance on task-relevant features. Extensive experiments in high-fidelity simulation demonstrate that our approach significantly improves policy-level scene transfer across diverse indoor and outdoor environments. At deployment, the agent relies only on monocular RGB observations together with standard task-related inputs such as goal position and proprioceptive signals, without access to LiDAR or other privileged sensors. Our method outperforms large pretrained vision models and standard contrastive baselines under severe appearance and semantic shifts. We also release a multimodal dataset to support future research on privileged-guided visual representation learning for navigation. The code is available at:
Read the full abstract

All authors Amirhossein Zhalehmehrabi, Tiziano Tezze, Alberto Castellini, Alessandro Farinelli

Computer Vision

Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers

Jean Cordonnier, Chenghao Xu, Olga Fink et al. (+1 more)

Multi-modal novel view synthesis (NVS) combining RGB and thermal imagery enables precise 3D scene reconstruction with visual and thermal information. However, existing methods typically rely on precisely calibrated RGB-thermal image pairs or stereo setups, limiting scalability and practical deployment. To address this, we introduce a framework for unpaired RGB-thermal NVS that leverages VGGT, a 3D feed-forward transformer architecture, to independently estimate camera poses for each modality. The pose sets are then aligned using the Procrustes algorithm with a cross-modal feature matcher, enabling joint registration without paired calibration. Building on this alignment, we further propose a multi-modal 3D Gaussian Splatting approach that learns directly from unpaired RGB and thermal images. Experiments on diverse scenes demonstrate that our method achieves competitive performance in thermal view synthesis while maintaining RGB fidelity. Moreover, we show that existing reconstruction approaches can produce modality-specific reconstructions that lack cross-modal consistency. We thus introduce a benchmarking framework to rigorously evaluate both per-modality image synthesis and the multi-modal coherence of reconstructed scenes.
Read the full abstract

All authors Jean Cordonnier, Chenghao Xu, Olga Fink, Malcolm Mielle

Computer Vision

LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval

Shahrzad Esmat, Chaunte W. Lacewell, Sameh Gobriel et al. (+2 more)

Retrieval systems underpin modern AI applications – spanning visual search, recommendation engines, and multi-modal question answering. Modern multi-stage retrieval systems require the joint optimization of highly coupled parameters, yet traditional hyperparameter optimization (HPO) methods – including Tree-structured Parzen Estimators (TPE) and Gaussian Process Bayesian Optimization – rely on an independence assumption that fundamentally prevents them from navigating these coupled configuration spaces. We address this limitation with a phase-aware large language model (LLM) agent that conditions each proposal on its full optimization history, navigating the coupled parameter space across phase-partitioned exploration, exploitation, and fine-tuning stages. Evaluated on the HICO-DET human-object interaction retrieval benchmark using Intel VDMS (Visual Data Management System), our agent outperforms Optuna TPE by +33.3% and VDTuner by +34.2% under SIEVE (Safeguarded Index Evaluation of Vector-search Efficiency, a quality-constrained throughput metric), delivering a 15.3x throughput gain over UniIR. Validation across three benchmarks confirms that the agent's advantage grows with the degree of parameter coupling: +33.3% on HICO-DET (high coupling), methods converge within 1% on GLDv2 (moderate coupling) and within 3.6% on SIFT1M (near-independent control). Cross-system validation on Milvus confirms the optimizer ranks first on all three datasets without modification, demonstrating transferability across vector database management system (VDBMS) platforms.
Read the full abstract

All authors Shahrzad Esmat, Chaunte W. Lacewell, Sameh Gobriel, Nilesh Jain, Ali Jannesari

Computer Vision

Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?

Joong Ho Kim and Keith G. Mills

Diffusion Models (DM) have revolutionized text-driven generation by enabling the synthesis of high-quality, photorealistic visual content from user prompts. Whereas prior advances in visual generation such as VAEs and GANs were primarily evaluated on perceptual or visual similarity metrics such as FID PSNR, DM advances have fostered the development of more advanced Human Preference Metrics (HPM) that model and quantify human judgment as scalar values. However, DMs synthesize content using an inherently stochastic process where random noise seeds generation. The initial random noise directly affects the quality of generated outputs, both qualitatively and quantitatively. This influence is pronounced in smaller models for local deployment scenarios. Given this phenomenon, we first investigate to what extent we can predict scalar HPM scores prior to committing compute resources for generation. Further, we then investigate to what extent we can leverage such prediction to improve the quality of generated images, and also study which HPMs are best suited for this task. Our investigation reveals that not only is this possible, but that it is feasible to achieve negligible hardware overhead.
Read the full abstract

Computer Vision

Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning

Deepika SN Vemuri, Sayanta Adhikari, Ankit Saha et al. (+2 more)

Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this by representing classes through meaningful semantic abstractions, but typically treat all concepts as a flat, unstructured set learned at a single neural network layer. This overlooks a fundamental property of human semantic understanding: concepts being organized hierarchically, from general to specific. While deep networks do learn a hierarchy of visual features, this structure is rarely aligned with explicit semantic hierarchies. Drawing on Formal Concept Analysis, we demonstrate that formal concept lattices provide principled semantic scaffolds to guide neural network learning. These lattices naturally identify where in the network concepts should be learned based on their level of generality. This allows the model to develop staged, semantically grounded representations throughout its depth. Empirical results on real-world datasets show that our models produce more interpretable embeddings, support more effective interventions, and learn concept representations that are both meaningful and hierarchically structured.
Read the full abstract

All authors Deepika SN Vemuri, Sayanta Adhikari, Ankit Saha, Krishn Vishwas Kher, Vineeth N Balasubramanian

Computer Vision

ORACLE-CT: Anatomy-Aware Support Pooling for CT Classification

Lavsen Dahal, Yubraj Bhandari, Geoffrey Rubin et al. (+1 more)

Abdominal CT disease classification is challenging because each scan is a large 3D volume with many possible findings, while diagnostic evidence is often confined to specific organs or anatomical compartments. Most study-level classifiers aggregate encoder features using anatomy-agnostic pooling or attention, creating a mismatch between localized disease evidence and global evidence aggregation. We propose ORACLE–CT, an encoder-agnostic anatomy-aware aggregation framework that uses multi-organ segmentation to define label-specific anatomical supports and restrict attention pooling to relevant regions. The framework supports single-organ, multi-organ union, comparative, localized, and global support strategies. We evaluate ORACLE–CT with three encoder families: DINOv3, I3D–ResNet-121, and the radiology-native Pillar–0 encoder. Models are trained end-to-end on MERLIN and evaluated internally and under frozen external transfer to Duke–Abdomen and AMOS. Compared with global average pooling, support-masked pooling improved MERLIN macro-AUROC/AUPRC from 0.838/0.638 to 0.858/0.676 for DINOv3 and from 0.829/0.617 to 0.848/0.659 for I3D–ResNet-121. On harmonized 10-label external evaluation, DINOv3 improved on Duke–Abdomen from 0.802/0.628 to 0.835/0.683 and on AMOS from 0.742/0.313 to 0.762/0.350, with similar gains for I3D–ResNet-121. For Pillar–0, most gains came from learned attention, with smaller additional benefit from anatomical masking. ORACLE–CT improves discrimination and external robustness while preserving an auditable link between predictions and anatomical evidence.
Read the full abstract

All authors Lavsen Dahal, Yubraj Bhandari, Geoffrey Rubin, Joseph Y. Lo

Computer Vision

Horse Eye Blink Detection and Classification for Equine Affective State Assessment

João Alves, Signe Møller-Skuldbøl, Pia Haubro Andersen et al. (+1 more)

Automated detection of equine facial action units (AUs) is a promising yet under-explored avenue for pain and affective state assessment in horses. Half and full-blink movements are recognised indicators of pain and stress, but as micro-expressions, their subtle, fine-grained nature makes them easily missed by the naked eye and only discernible through frame-by-frame video inspection, making reliable automated detection from video a particularly demanding task. We develop and evaluate three methods for automated blink classification from horse videos: a frame-based YOLOv12 detector, an optical flow magnitude thresholding approach, and a fine-tuned VideoMAE model, tested on a publicly available dataset. We achieve a macro-F1 score of 0.898 when doing blink classification and 0.926 on binary blink detection. Our results highlight both the potential and the inherent challenges of fine-grained AU detection for equine welfare monitoring.
Read the full abstract

All authors João Alves, Signe Møller-Skuldbøl, Pia Haubro Andersen, Rikke Gade

Computer Vision

Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classification

Feixiang Zhou, Jianyang Xie, Zhuangzhi Gao et al. (+10 more)

The missing-modality problem poses a significant challenge in image-tabular multimodal learning across a wide range of multimedia applications, including product understanding, recommendation systems, and medical diagnosis. This challenge is particularly pronounced when the two modalities are highly heterogeneous, as images and tabular attributes differ substantially in their semantic granularity and data distributions. Existing methods learn modality-invariant representations through disentanglement and alignment over global token-averaged features, capturing only coarse cross-modal consistency and overlooking fine-grained semantic and distributional misalignment, which hampers the exploitation of complementary cues under missing modalities. To address this, we propose DFPL, a novel framework for fine-grained prototype learning. Specifically, Shared-Specific Prototype Modeling (SSPM) extracts compact and diverse shared and modality-specific prototypes, and further performs prototype-level disentanglement to suppress redundant intra-modality correlations. Additionally, we propose a Prototype-guided Fine-grained Alignment (PFA) module that jointly enforces prototype-level distribution matching and prototype-to-class semantic alignment within a unified prototype space, thereby preserving both fine-grained distributional and semantic consistency across modalities. We further introduce a Class-aware Multi-scale Aggregation (CMA) module to adaptively aggregate shared semantics and modality-specific characteristics from global and prototype levels for robust predictions. Extensive experiments on three diverse image-tabular benchmarks demonstrate the superiority of our method compared to the previous approaches under various missing-modality settings. Code will be made publicly available.
Read the full abstract

All authors Feixiang Zhou, Jianyang Xie, Zhuangzhi Gao, Qinkai Yu, Fu Wang, Yuheng Fan, Jing Li, Zheheng Jiang, Yitian Zhao, Yanda Meng, He Zhao, Gregory Y.H. Lip, Yalin Zheng

Computer Vision · Cross-listed from cs.RO

Uncertainty-Aware Adaptive Sensor Fusion for Autonomous Navigation

Simegnew Yihunie Alaba and Yuichi Motai

This work introduces a hybrid deep learning approach integrated with an Unscented Kalman Filter (UKF) to enhance pose estimation accuracy in Visual-Inertial Odometry (VIO) for autonomous navigation. The proposed model employs a Vision Transformer (ViT) network to effectively capture temporal dependencies from inertial measurement unit (IMU) data and utilizes a Multiscale Convolutional Neural Network (MCNN) to learn optical flow-based motion cues from visual data. An adaptive sensor fusion module dynamically weights IMU and visual features by leveraging estimated uncertainty, thus improving robustness in diverse and challenging environmental conditions. Additionally, a novel uncertainty-aware loss function is proposed to explicitly incorporate prediction uncertainty into the learning process, enabling robust and accurate navigation under noisy, incomplete, or unreliable sensor inputs. Comprehensive evaluations of the KITTI dataset demonstrate that the proposed method significantly outperforms baseline approaches, achieving superior performance in terms of Absolute Trajectory Error (ATE) and Relative Pose Error (RPE). The lightweight and computationally efficient model processes data at 155 FPS on an NVIDIA A100 GPU, making it highly suitable for deployment in resource-constrained autonomous systems.
Read the full abstract

Computer Vision

Would you still call this Dax? Novel Visual References in VLMs and Humans

Ada Defne Tür, Gaurav Kamath, Joyce Chai et al. (+2 more)

Vision-language models (VLMs), like human learners, are frequently exposed to new visual concepts, but how they map novel visual references to language after exposure remains largely underexplored, particularly when those references contradict prior knowledge from pre-training. To study this, we present the Novel Visual References Dataset (NVRD): 19,176 images spanning 90 visual concepts across different levels of visual novelty, each with up to 20 increasingly perturbed versions of the original object to probe generalization. Unlike prior work on visual augmentations of familiar concepts, NVRD comprises entirely novel, open-ended stimuli constructed from scratch, mirroring how humans encounter genuinely new concepts. We evaluate 3 open- and 2 closed-source models alongside 2,400 human judgments for direct human-model comparison, and find that (i) models struggle to acquire novel concepts in-context when they contradict prior knowledge, and (ii) while models and humans show correlated sensitivity to visual perturbations, models significantly overgeneralize, extending learned labels to stimuli that humans reject. We contribute NVRD as a corpus and benchmark for research on visual concept learning in both humans and machines.
Read the full abstract

All authors Ada Defne Tür, Gaurav Kamath, Joyce Chai, Siva Reddy, Benno Krojer

Computer Vision

UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching

Qilin Huang, Quynh Anh Huynh, Long Le et al. (+5 more)

Existing feed-forward networks excel at predicting a single set of physical properties from visual appearance, but this point-estimate paradigm fundamentally fails to capture the real world's inherent physical ambiguity. We address this by reframing physics prediction as a task of learning a controllable, continuous distribution of material properties. We introduce UNIPIXIE, a framework trained to predict a continuous and parameterized path of physically plausible material properties from a single visual input. By learning a direct mapping along an object's softest-to-stiffest spectrum on our PIXIEMULTIVERSE dataset, UNIPIXIE allows for controllable generation of diverse, physically valid material fields via a single intuitive parameter. Crucially, UNIPIXIE introduces a novel unified architecture to produce simulation-ready parameters for diverse physics solvers, including continuum-based Material Point Method (MPM), reduced-order deformation based on Linear Blend Skinning (LBS), and anchor-based Spring-Mass systems, addressing a key portability issue in prior work. Experiments show our approach not only generates a rich variety of plausible dynamics but also reduces Young's Modulus prediction error by over 50% against the strongest deterministic baseline, bridging the gap between static point estimates and the continuous nature of physical reality. Project page: https://unipixie.github.io/
Read the full abstract

All authors Qilin Huang, Quynh Anh Huynh, Long Le, Chen Wang, Chuhao Chen, Ryan Lucas, Eric Eaton, Lingjie Liu

Computer Vision

Deep Learning-assisted AMD Staging based on OCT and OCT Angiography

Yukun Guo, Tristan T. Hormel, An-Lun Wu et al. (+4 more)

To develop and evaluate deep learning models for automated grading of age-related macular degeneration (AMD) severity using optical coherence tomography (OCT) and OCT angiography (OCTA) data. Two hundred seventy-one participants aged >= 50 years with varying AMD severities. Central macular 6 x 6 mm OCT/OCTA volumes were acquired using a swept-source OCTA system (SOLIX; Visionix/Optovue Inc., CA). AMD severity was graded into four stages (No AMD, Early AMD, Intermediate AMD, and Advanced AMD) according to the AREDS simplified severity scale. Three deep learning models were developed using different input modalities: (1) biomarker maps derived from segmented pathological features, including retinal fluid, drusen, geographic atrophy (GA), and macular neovascularization (MNV); (2) two-dimensional (2D) en face OCT and OCTA projections; and (3) three-dimensional (3D) OCT/OCTA volumes. EfficientNet-based architectures were trained using normalized inputs, data augmentation, and five-fold cross-validation. A total of 2,030 OCT/OCTA volumes from 351 eyes of 271 participants were analyzed. All models demonstrated strong AMD staging performance with substantial agreement with the reference standard (QWK >= 0.83). The biomarker-based model achieved the highest overall performance (QWK = 0.85 +/- 0.03, mean +/- standard deviation) and the best detection of early AMD (F1-score = 0.59 +/- 0.14). The 3D model achieved performance comparable to the 2D OCT/OCTA model (QWK = 0.83 +/- 0.04 vs. 0.83 +/- 0.09), while the 2D OCT/OCTA model showed the highest precision (0.79 +/- 0.06) and most accurately identified eyes without AMD. Deep learning models using OCT/OCTA data can accurately and automatically grade AMD severity. Among the evaluated approaches, the biomarker-based model provided the most balanced performance and showed particular value for early AMD detection.
Read the full abstract

All authors Yukun Guo, Tristan T. Hormel, An-Lun Wu, Liqin Gao, Min Gao, Steven T. Bailey, Yali Jia

Computer Vision

Three-Dimensional Retinal Microvasculature Restoration in OCT Angiography

Yukun Guo, Min Gao, Tristan T. Hormel et al. (+3 more)

Optical coherence tomographic angiography (OCTA) is a powerful technique for imaging retinal microvasculature. However, acquiring reliable quantification of retinal blood flow and areas of retinal nonperfusion is challenging because of imaging artifacts. Existing methods primarily focus on noise suppression, projection artifact removal, or signal enhancement to improve the image quality of OCTA in cross-sectional or two-dimensional (2D) en face projections, while neglecting the intrinsic three-dimensional vascular architecture. In this study, we propose a deep learning-based algorithm for restoring capillary anatomical vasculature from a single OCTA volume. The network consists of an EfficientNet-B5 encoder and a decoder incorporating concurrent spatial and channel squeeze-and-excitation modules, connected via skip connections to preserve spatial resolution. Three adjacent B-frames are used as input to predict the restored middle B-frame. We evaluated the performance of the model using the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) against ground truth generated from averaging multiple scans. The results show that the proposed model significantly (both p < 0.001) improved image quality compared with the original single OCTA volume, with a PSNR of 26.16 +/- 1.26 vs. 22.23 +/- 0.78 and an SSIM of 0.91 +/- 0.02 vs. 0.72 +/- 0.03. The proposed model also significantly (p < 0.001) improved microvascular fidelity, measured by the Dice coefficient overlap between the model output and ground truth, in both 2D and 3D by at least 3.8% and 51.2%, respectively, across several different vascular slabs.
Read the full abstract

All authors Yukun Guo, Min Gao, Tristan T. Hormel, Steven T. Bailey, Thomas S. Hwang, Yali Jia

Computer Vision

Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin

Sayan Mandal, Rocco Sedona, Simon Besnard et al. (+4 more)

Accurate, spatially explicit characterization of tropical forest structure is essential for carbon accounting and ecosystem monitoring, yet most ML pipelines predict canopy-top height proxies (e.g., RH95/RH98) or AGBD as separate scalar targets, rather than learning the forest vertical structure as an ordered profile. The community lacks a ML-ready multimodal benchmark for predicting the entire GEDI RH profile jointly with AGBD, or for evaluating methods that enforce physically consistent ordering across RH percentiles. We address this with Biomazon, a 20 m multimodal benchmark dataset over the Amazon Basin that pairs GEDI RH and AGBD targets with multi-sensor predictors (Sentinel-1/2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World LULC, and AlphaEarth embeddings) under standardized spatial splits and evaluation protocols. Using a shared encoder-decoder with task-specific heads as a baseline framework, we conduct a comprehensive ablation study of (i) backbone/model scale, (ii) modality contributions, and (iii) the use of auxiliary embeddings under standalone and fusion settings, and we report both single-target and joint-target results to quantify tradeoffs under a unified training protocol. Finally, we contextualize baseline performance through regionally aligned comparisons against existing gridded products, including GEDI L4D RH10-RH98 and AGBD, at matching temporal scale. Biomazon, together with the accompanying protocols and baseline results, establishes a reference benchmark for future work on structurally consistent RH-profile prediction and structure-biomass modeling in tropical forests.
Read the full abstract

All authors Sayan Mandal, Rocco Sedona, Simon Besnard, Mikhail Urbazaev, Morris Riedel, Ehsan Zandi, Gabriele Cavallaro

Computer Vision

Recovering Physically Plausible Human-Object Interactions from Monocular Videos

Dingbang Huang, Etienne Vouga, Qixing Huang et al. (+1 more)

In this paper, we propose RePHO, a method to reconstruct physically plausible human-object interactions (HOI) from monocular videos. While existing kinematic-based approaches produce visually plausible motion, they often result in physically implausible artifacts such as interpenetration and object floating. To overcome these issues, we introduce a physics-guided reconstruction framework. We begin with a kinematic estimate and then refine it by training a policy with reinforcement learning (RL). This policy is optimized to reproduce the interaction in a physics simulator. Because kinematic estimates are typically noisy, naive RL training can fail. Therefore, we propose an adaptive sampling strategy with a dual self-updating mechanism that can identify the frames with the most informative and reliable kinematic reconstruction. Our process progressively improves reconstruction quality and yields physically consistent HOI sequences. We demonstrate our approach on two standard HOI benchmarks and achieve clear improvements in physical plausibility metrics over state-of-the-art methods. Project Page: https://dingbang777.github.io/RePHO/
Read the full abstract

All authors Dingbang Huang, Etienne Vouga, Qixing Huang, Georgios Pavlakos

Computer Vision

LightVesselNet: An Ultra-Lightweight Sub-100K Parameter Network for Retinal Blood Vessel Segmentation

Shadman Sobhan and Farhana Jalil

Retinal blood vessel segmentation plays a vital role in the early detection of diabetic retinopathy and glaucoma. While recent deep learning models have achieved great segmentation accuracy, they typically require heavy computational resources, making real-world deployment on edge devices difficult. In this paper, we propose LightVesselNet, an efficient neural network designed for retinal vessel segmentation in a resource-constrained environment. Despite containing only 75K parameters, LightVesselNet performs competitively with much larger models. The network employs a compact encoder decoder architecture enhanced with channel and spatial attention mechanisms, a multi-scale feature aggregation module at the bottleneck, and a subpixel upsampling strategy in the decoder. A dedicated edge residual connection preserves fine vessel detail throughout decoding. Extensive experiments on five publicly available datasets: DRIVE, STARE, CHASEDB1, FIVES, and HRF, yield sensitivity scores of 0.8189, 0.8499, 0.8640, 0.8634, 0.8096, and Dice coefficients of 0.8070, 0.8072, 0.8181, 0.8649, and 0.7686, respectively. LightVesselNet shows improved efficiency (Performance vs Parameter or GFlops) compared to State-of-the-Art models. Cross-dataset evaluation confirms the model's generalisation capability. Overall, LightVesselNet is a strong candidate for deployment in low-resource clinical settings and mobile screening tools.
Read the full abstract

Computer Vision

TopoPult-SSL: Gland-Mask-Free Cross-Device Meibomian Gland Segmentation via Self-Distilled Weak Clinical Priors

Nicolò Savioli and Luca Del Tongo

Every new clinical imaging device creates a domain shift where dense gland masks are expensive yet cheap clinical signals – eyelid outlines, Pult grades, morphometric ratios – are routinely recorded. We present TopoPult-SSL, a two-stage framework for cross-device meibomian gland segmentation. Stage 1 adapts a source-trained model without target gland masks in the training loss, using four weak-prior anchors driven by target eyelid masks and clinical metadata only. Stage 2, when target gland masks are available, distils complementary Stage-1 teachers into a single compact student via supervised self-distillation. We develop and validate the technique on the public MGD-1k to CAMG research benchmark (1,000 to 100 images, different device), where the distilled model achieves Dice 0.716+/-0.006 (best 0.726), surpassing UA-MT (0.710) and the ensemble teacher (0.720) – with a single pass. The gland-mask-free Stage-1 variant reaches Precision 0.694 vs. 0.30-0.34 for SAM/MedSAM (p<0.001), enabling deployment without dense gland contouring. Code and reproducibility scripts are released.
Read the full abstract

Computer Vision · Cross-listed from cs.GR

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

Parsa Esmati, Somjit Nath, Katja Hofmann et al. (+3 more)

Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this question by probing video diffusion models along latent trajectories corresponding to real videos with known physical plausibility. To obtain such trajectories, we approximately invert the deterministic sampling process by integrating the learned velocity field backward from a clean video latent to noise, giving access to the model's intermediate states and attention maps. Using these recovered trajectories, we show that physical plausibility is linearly decodable from diffusion transformer states across IntPhys and InfLevel, reaching around 81.27% average accuracy and outperforming dedicated representation-learning baselines such as V-JEPA and VideoMAE. Surprisingly, this signal is absent from the VAE latent input and emerges inside the denoising transformer itself, despite the model not being trained with a self-supervised predictive objective. These findings suggest that physically meaningful representations can arise as a byproduct of generative denoising.
Read the full abstract

All authors Parsa Esmati, Somjit Nath, Katja Hofmann, Derek Nowrouzezahrai, Samira Ebrahimi Kahou, Majid Mirmehdi

Computer Vision

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

Tobia Poppi, Silvia Cappelletti, Sara Sarto et al. (+5 more)

Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture. In this work, we ask whether safety can be represented as a portable latent direction, learned once and reused across heterogeneous generators. We introduce the first framework for cross-model safety steering, in which a safety direction is estimated in a source LLM from paired safe-unsafe prompts, transported to a target generator through a lightweight alignment fitted on benign data alone, and applied at inference time. Crucially, our pipeline never accesses unsafe data on the target side, isolating whether safety can be transferred through shared representation geometry. Beyond a single global direction, we also identify a multi-vector extension that captures category-specific safety behaviors, enabling more selective control. We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs. Across models, transferred safety directions achieve ASR reduction and CLIP-Score/FID trade-offs comparable to directions learned natively on the target model using unsafe data, while requiring no target-side unsafe data. This indicates that safety improvements do not come at the expense of generation quality. Our results point to a modular view of safety: safety-relevant behavior is not purely model-local, but can be controlled through latent directions that persist across models. This suggests a new path toward lightweight, reusable safety mechanisms that do not require target-side unsafe data.
Read the full abstract

All authors Tobia Poppi, Silvia Cappelletti, Sara Sarto, Florian Schiffers, Garin Kessler, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Computer Vision

Personal AI Agent for Camera Roll VQA

Thao Nguyen, Krishna Kumar Singh, Donghyun Kim et al. (+2 more)

We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera roll and retrieve relevant photos to answer queries, ranging from simple factual questions (e.g., “Name of the food I tried yesterday?”) to more open-ended ones (e.g., “Recommend some dishes I have never eaten before”). Given the vast nature of the personal camera roll (i.e., multiple years, hundreds to thousands of photos), a successful AI assistant needs to understand a long-horizon, highly personalized visual content stream in order to navigate and locate the correct and/or relevant information. To support this, we collect and manually annotate questions that mimic real-world usage. The final dataset, camroll, contains 50 users, 31,476 images, and 2,500 QA pairs. We further design camroll-agent, a conversational AI agent equipped with hierarchical memory and a minimal set of tools for efficient navigation over large, personalized visual memory. Experimental results show that camroll-agent outperforms numerous baselines and methods for long-context understanding AI agents system. Together, the camroll dataset and camroll-agent highlight the gap in AI agents' long-context reasoning: personalized visual memory requires different approaches from standard long-context textual memory, especially when consistency, visual details, and user-specific context are present.
Read the full abstract

All authors Thao Nguyen, Krishna Kumar Singh, Donghyun Kim, Yong Jae Lee, Yuheng Li