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 15 July

Computer Vision

XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentation

Md Mahedi Hasan, Md Mushfiqur Rahaman, Alan Pachkovskiy et al. (+3 more)

Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions. Although recent foundation models such as the Segment Anything Model (SAM) provide strong general-purpose segmentation priors, their natural-image pre-training transfers poorly to the AM XCT domain, where defects appear as subtle non-semantic microstructural anomalies. Moreover, adapting SAM to the AM domain is further limited by the large domain gap and scarcity of labeled real XCT data. We present XCT-SAM, a sequential parameter-efficient adaptation framework for AM XCT defect segmentation. Instead of adapting SAM directly from natural images to XCT data, we first fine-tune Conv-LoRA adapters on an alloy-microstructure dataset and subsequently transfer the adapted model to XCT images, progressively bridging the domain gap. Using Conv-LoRA adapters with rank r=2, the framework injects convolutional spatial inductive bias into SAM's backbone while training approximately 4.15M parameters and keeping over 99% of the model frozen. We evaluate XCT-SAM on out-of-distribution CycleGAN-XCT benchmarks and real-world NIST XCT scans. Across both settings, XCT-SAM consistently outperforms zero-shot SAM and other domain-adapted SAM baselines, achieving the best overall IoU and Dice scores. These results demonstrate the effectiveness of intermediate domain adaptation with parameter-efficient adapters for industrial XCT defect segmentation. The source code is publicly available at https://github.com/Mahedi-61/XCT-SAM.git
Read the full abstract

All authors Md Mahedi Hasan, Md Mushfiqur Rahaman, Alan Pachkovskiy, Imtiaz Ahmed, Jeremy Dawson, Srinjoy Das

Computer Vision

MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report Generation

Yi Lin, Yihao Ding, Elana Benishay et al. (+8 more)

Automated chest CT report generation remains challenging because clinically faithful reporting requires both whole-volume understanding and accurate description of localized anatomical findings. Here we developed and retrospectively evaluated MonteRET, a region-aware retrieval-enhanced framework for generating chest CT findings sections. MonteRET integrates global CT features with region-level anatomical representations, retrieves clinically relevant knowledge using predicted medical conditions and region-level vision-language alignment, and refines initial reports through a knowledge-guided report rewriting agent. We trained our model on a public cohort with 24,128 CT scans from RadGenome-ChestCT. We evaluated MonteRET on the public RadGenome-ChestCT test set of 1,564 CT scans and an external cohort of 82 CT scans from NewYork-Presbyterian/Weill Cornell Medical Center. MonteRET improved report quality, semantic similarity, and clinical efficacy compared with a matched baseline and several state-of-the-art methods. Gains were most pronounced for recall, suggesting fewer omitted findings. Human expert evaluation by radiology residents also favored MonteRET.
Read the full abstract

All authors Yi Lin, Yihao Ding, Elana Benishay, Elefterios Trikantzopoulos, David Nauheim, Hanley Ong, Jiang Bian, Hua Xu, Yuzhe Yang, George Shih, Yifan Peng

Computer Vision

3D Lane Detection with Odometry for High-Speed Vehicle Racing

Omoruyi Atekha, John Subosits and Marcus Greiff

Lane boundary detection is a critical component in autonomous driving systems and has been rigorously studied in regular driving scenarios. However, it is less explored in vehicle racing, where the car moves at higher speeds across more extreme road geometries. To study this problem, we introduce a new dataset for 3D lane detection in racing, featuring >$250$k images from multiple camera feeds and inertial measurements taken with a Lexus LC 500 driving on a closed circuit. With this dataset, we compare various approaches to 3D lane detection and propose modifications that permit frames to be processed at rates of almost 300Hz while retaining high predictive performance in the racing application. This facilitates a multi-camera ensemble approach that is validated on hardware. We show that sensing modalities such as inertial measurements can be leveraged for pre-integration to regress road geometries over both cameras and time, yielding improvements in key metrics. Compared to methods such as BevLaneDet, adding odometry and ensemble predictions improves the F1 score by 3 points and reduces near-vehicle mean absolute errors (MAEs) by $>30 \%$. We show F1 scores $>$0.9 and lateral MAEs of $<$0.18m in vehicle deployments.
Read the full abstract

Computer Vision

SeeSE3: Emergence of 3D Space in Vision Features

Caroline Chen, Sayna Ebrahimi, Fedor Kitashov et al. (+4 more)

In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space. Unlike previous works that probe 3D awareness of vision features by regressing image-centric quantities such as depth or normals, we investigate the relation between the structure of the space of visual features and the group of Euclidean transformations $SE(3)$. We propose a set of probes to evaluate this relation from both topological and geometric perspectives: a mutual neighborhood metric that measures the alignment between feature neighborhoods and spatial topology, and a Poincaré Adapter to test the linear accessibility of the geometry of camera motion from latent displacements in static scenes. We show that self-supervised vision models, which, in principle, have not been trained with direct 3D supervision or active agency, possess latent subspaces that are remarkably strongly correlated with three-dimensional Euclidean space, when probed correctly. Building on this insight we propose a new class of "Latent-Space Navigation" techniques that perform visual odometry and localization purely in the latent space, bypassing the need for explicit 3D reconstruction.
Read the full abstract

All authors Caroline Chen, Sayna Ebrahimi, Fedor Kitashov, Ming-Hsuan Yang, Leonidas Guibas, Viorica Pătrăucean, Maks Ovsjanikov

Computer Vision · Cross-listed from cs.GR

Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation

NVIDIA: Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz et al. (+12 more)

3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent years, neural simulation has become predominant, with methods such as NuRec playing a central role; however, these methods remain relatively slow and typically require per-scene tuning. In this work, we present Instant NuRec, a feed-forward neural reconstruction model that turns a short multi-view driving log into a fully simulatable 3D Gaussian Splatting (3DGS) world in a single forward pass. The model accepts multi-view input from a calibrated camera rig and emits a layered output consisting of static and dynamic 3DGS layers, a sky cubemap, and per-camera ISP corrections, while providing native support for non-pinhole camera models via 3DGUT. It reconstructs a 10-20-second multi-camera scene in roughly 1.5 seconds and achieves a PSNR on the Waymo Open Dataset that is 2.01 dB above the strongest evaluated baseline. Instant NuRec is deeply integrated into NuRec and is compatible with AlpaSim for closed-loop simulation.
Read the full abstract

All authors NVIDIA: Jiahui Huang, Jiawei Ren, Michal Tyszkiewicz, Bjoern Haefner, Michael Shelley, Xin Kang, Seung Wook Kim, Ning Xu, Qi Wu, Janick Martinez Esturo, Shengyu Huang, Nick Schneider, Laura Leal-Taixe, Zan Gojcic, Sanja Fidler

Computer Vision

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Yuqi Tang, Tengfei Liu, Yizheng Lai et al. (+18 more)

Video generation increasingly relies on keyframe-based workflows, where creators specify a sequence of reference images to guide generation. Although recent models support multi-keyframe conditioning, it remains unclear whether they can faithfully reproduce the prescribed keyframes while maintaining overall video quality. We present KeyFrame-Compass, the first comprehensive benchmark for evaluating keyframe-conditioned video generation. The benchmark contains 386 carefully curated samples spanning three application domains, two video structures, two prompt granularities, two conditioning formats, and four keyframe densities, enabling controlled analysis under diverse generation settings. We further introduce an automated evaluation framework that jointly measures keyframe execution and overall video quality. Specifically, we decompose keyframe execution into six complementary metrics covering presence, fidelity, temporal ordering, localization, persistence, and uniqueness, while assessing overall video quality through evidence-grounded MLLM judgments augmented with specialized perception models. Experiments on nine representative video generation systems reveal several fundamental limitations. Current models exhibit a clear trade-off between faithful keyframe execution and natural video synthesis. Their performance further degrades as keyframe constraints become denser and most open-source models also fail to interpret storyboard-grid inputs as temporally ordered keyframe sequences.
Read the full abstract

All authors Yuqi Tang, Tengfei Liu, Yizheng Lai, Yuran Wang, Yang Shi, Wanshun Su, Zhuoran Zhang, Qixun Wang, Xiaohan Zhang, Xinlei Yu, Xuehai Bai, Xuanyu Zhu, Bohan Zeng, Bozhou Li, Shujie Li, Yifan Dai, Yujie Wei, Shixuan Liu, Haotian Wang, Jialu Chen, Yuanxing Zhang

Computer Vision

Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Models

Wenxuan Chen and Wenjie Feng

Text-to-video (T2V) generators can synthesize realistic and temporally coherent videos, but controllably removing a target concept from a generator remains difficult. Unlike text-to-image concept erasure, T2V unlearning must suppress a target concept that may persist across frames while preserving non-target subjects, actions, scenes, and temporal structure. We propose SIRUS, a training-free inference-time framework for concept-level T2V unlearning. Given textual aliases of a target concept, SIRUS localizes target-related prompt evidence and suppresses target expression during sampling, without updating the text encoder or denoising network. We further introduce a video-oriented evaluation framework for T2V unlearning that separately measures target forgetting, non-target preservation, video quality, jailbreak robustness, and efficiency, using video-level failure criteria, frame-level residue statistics, paired preservation analysis, VBench-based quality diagnostics, and deployment overhead measurement. Across five safety, object, and style concepts on CogVideoX, SIRUS reaches 70.4% average forgetting success and 25.7% average frame hit, compared with 44.4% / 47.2% for VideoEraser, while reducing the average VBench quality drop from -0.043 to -0.016, yielding the strongest forgetting-quality trade-off among fully evaluated baselines. Transfer experiments on Wan2.2 further suggest that SIRUS generalizes across modern T2V backbones.
Read the full abstract

Computer Vision

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Xiaohan Zhang, Yuqing Wen, Junlin Chen et al. (+9 more)

Multi-reference-to-audio-video (MR2AV) generation aims to generate coherent audio-video content conditioned on multiple references and textual instructions. Existing benchmarks mainly focus on text-driven generation, single-reference subject preservation, or isolated audio-video alignment, leaving the emerging MR2AV setting largely unexplored. Compared with these settings, MR2AV requires models to jointly reason over multiple references while generating synchronized visual and audio content. Models must not only preserve each reference faithfully but also correctly bind and compose multiple referenced entities into coherent audio-visual events. To address this gap, we introduce MultiRef-Compass, a unified benchmark for MR2AV generation. It comprises $350$ carefully curated samples constructed through a scalable and controllable asset-composition pipeline, covering multi-view subject preservation, multi-entity binding, and human-object-scene composition. To provide interpretable assessment, MultiRef-Compass defines an evaluation protocol with four dimensions: Basic Quality, Reference Consistency, Audio-Visual Consistency, and Instruction Following, using 14 sub-metrics. MultiRef-Compass integrates automatic metrics with a rejudging-enhanced MLLM-as-a-Judge framework, enabling scalable and auditable evaluation of both perceptual fidelity and reference-conditioned composition. Extensive experiments on eight representative MR2AV systems reveal substantial room for improvement across multiple evaluation dimensions, underscoring the need for a comprehensive benchmark and positioning MultiRef-Compass as a foundation for future MR2AV research.
Read the full abstract

All authors Xiaohan Zhang, Yuqing Wen, Junlin Chen, Yuqi Tang, Yiting He, Lizhuo Shao, Weiming Zhu, Tengfei Liu, Yang Shi, Jialu Chen, Yuanxing Zhang, Huaxiong Li

Computer Vision · Cross-listed from cs.RO

Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning

Zishuo Li, Bowen Yang, Changtao Miao et al. (+29 more)

Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable tools for robot learning. We present Open-AoE, an open, community-oriented egocentric manipulation dataset and toolchain spanning the full pipeline from smartphone capture to model training. Its first release contains approximately 2,000 hours of manipulation video collected in natural environments by 500+ contributors using 400+ smartphones. The dataset provides text annotations, MANO-based hand poses, camera trajectories, and temporally localized atomic actions. Open-AoE further includes a data processing pipeline that transforms raw recordings into structured samples through temporal action segmentation, semantic annotation, hand reconstruction, and camera trajectory reconstruction. Meanwhile, we provide a separate downstream toolchain supports visualization, cross-embodiment retargeting, model-specific data conversion, and training recipes for VLA policies, WAMs, and World Models. By integrating scalable capture, structured processing, and downstream adaptation, Open-AoE reduces the barriers to both data contribution and reuse, providing practical open infrastructure for embodied model training, human-to-robot transfer, and world modeling.
Read the full abstract

All authors Zishuo Li, Bowen Yang, Changtao Miao, Kai Zhu, Hao Chen, Qingze Guan, Zhengxing Wu, Wanke Zhan, Yang Sun, Zhiyi Huang, Zitong Shan, Zhenchao Jin, Jiadong Hong, Taowen Wang, Yushi Feng, You Liu, Yibo Wang, Yifan Yang, Zhaowen Zhou, Man Luo, Hao Cheng, Bo Zhang, Jianshu Li, Jiansheng Cai, Guocai Yao, Jize Zhang, Chenhao Lin, Renjing Xu, Lequan Yu, Chao Shen, Chunhua Shen, Zhe Li

Computer Vision · Cross-listed from eess.IV

OvAi Focus: AI-based Multi-class Segmentation of Functional Ovaries and Adnexal Masses in Gynecological Ultrasound

Niccolò Tallone, Francesca Salis, Pio Raffaele Fina et al. (+13 more)

Ovarian cancer is the deadliest gynecological malignancy; accurate and objective segmentation of adnexal masses and functional ovaries in ultrasound (US) remains challenging due to operator variability and morphological complexity. We present OvAi Focus (SynDiag s.r.l., Italy), a stand-alone AI software medical device that performs multi-class semantic segmentation of functional ovaries and adnexal masses, distinguishing cystic from solid components. The system was trained and independently validated on a multicenter dataset of 1,081 adult women from 6 centers across Italy and Israel. Segmentation achieved DICE scores of 0.87 (complete lesion), 0.85 (cystic), 0.68 (solid), and 0.62 (functional ovary), in line with or superior to state-of-the-art approaches across heterogeneous acquisition settings.
Read the full abstract

All authors Niccolò Tallone, Francesca Salis, Pio Raffaele Fina, Roberta Massobrio, Rosilari Bellacosa Marotti, Daniele Conti, Luca Fuso, Luca Mariani, Annamaria Ferrero, Alessandro Arena, Stefano Cosma, Dan Grisaru, Angelo Lacalandra, Renato Seracchioli, Marianna Roccio, Federica Gerace

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

A vision foundation model for single-cell biology via spatial gene cartography

Ridvan Yesiloglu, Sakib Mostafa, James Zou et al. (+5 more)

Most single-cell foundation models are adapted from language models, representing each cell as a sequence of gene tokens. This discards the relationships among genes and often the magnitude of their expression. We present scVision, a vision foundation model that instead renders each cell as a continuous image. Using optimal transport, it places genes at fixed positions on a single shared, pan-tissue layout so that co-expressed genes become spatial neighbours, turning a transcriptome into an image in which gene programs appear as local texture. We pretrain a vision transformer by masked image modelling on 72 million human cells and use the frozen encoder with no fine-tuning. In zero-shot evaluations on six independent, held-out studies, scVision is the most accurate cell-type annotator and recovers gene programs without supervision, ahead of existing foundation models and classical baselines; on multi-study integration it matches the strongest token-based model while conserving the most biological structure, without ever seeing a batch label. Permuting the gene layout with the network fixed sharply lowers accuracy, more than removing the vision transformer itself, showing that biologically meaningful position, not the network, carries the signal. By preserving expression magnitude and gene relationships, scVision reframes single-cell representation learning as a vision problem, connecting it to the mature methods of computer vision.
Read the full abstract

All authors Ridvan Yesiloglu, Sakib Mostafa, James Zou, Ash Alizadeh, Jiajun Wu, Lei Xing, Ehsan Adeli, Md Tauhidul Islam

Computer Vision

VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

Zhihao Xie, Junfeng Wu, Xinting Hu et al. (+2 more)

Video generation models typically rely on 3D-VAEs trained for pixel-level reconstruction, whose latent spaces may underrepresent semantic structure. We introduce VideoRAE, a representation autoencoder that converts features from a frozen video foundation model into compact, reconstruction-capable latents for video generation. A lightweight 1D self-attention projector compresses multi-scale hierarchical features, producing continuous latents for Diffusion Transformers and discrete tokens for autoregressive models through multi-codebook high-dimensional quantization. During decoding, a local-global representation alignment objective transfers semantic structure from the frozen encoder and removes the need for KL regularization. Comprehensive experiments show that VideoRAE achieves strong reconstruction in both continuous and discrete regimes. On UCF-101, autoregressive and diffusion generators built on VideoRAE achieve class-conditional gFVD scores of 40 and 93, respectively, while converging approximately five times faster than autoencoder baselines. In controlled 2B-parameter text-to-video experiments, replacing LTX-VAE with VideoRAE accelerates convergence and consistently improves VBench performance. These results establish frozen video foundation representations as compact, versatile, and generation-friendly video latents. Code and models are available at https://zhxie0117.github.io/VideoRAE/.
Read the full abstract

All authors Zhihao Xie, Junfeng Wu, Xinting Hu, Junchao Huang, Li Jiang

Computer Vision

From Pixels to States: Rethinking Interactive World Models as Game Engines

Zhen Li, Zian Meng, Shuwei Shi et al. (+4 more)

Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a data-driven route toward this goal by predicting future observations conditioned on user actions, and are increasingly regarded as potential next-generation game engines. Realizing a genuinely interactive game world, however, requires interaction outcomes that follow rules over evolving game conditions, consequences that persist over long horizons, and a generation loop that operates in real time. Conventional game engines realize these properties through a recurrent action-state-observation loop, in which player actions update an explicit game state according to predefined rules and observations are rendered from the resulting state. Taking this loop as an organizing lens, this paper examines interactive game world modeling along four dimensions: player action control, game state dynamics, state-observation persistence, and real-time interactive generation. For each dimension, we start from the capabilities required by an interactive game world, group existing approaches into representative families, and discuss the strengths and trade-offs of each family. Complementing this analysis, we present a scalable data engine for Black Myth: Wukong that collects over 90 hours of gameplay with frame-aligned player actions, ground-truth game states, and visual observations, together with structured and semantic annotations, as a resource for state-aware game world modeling. We hope this paper offers a clear picture of where the field stands and fosters progress toward interactive game worlds.
Read the full abstract

All authors Zhen Li, Zian Meng, Shuwei Shi, Mingliang Zhai, Jiaming Tan, Chuanhao Li, Kaipeng Zhang

Computer Vision

Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study

Zhan Chen, Jiqiao Ma and Chih-wen Kuo

Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning process as domain specialists and uses a lightweight page-level image classifier to dispatch pages by visual style. When the checkpoint pool lacks a suitable specialist, we train an additional expert for that domain. On three frozen test sets, the routed system matches the selected specialist for each style at two-decimal precision: 0.30 percent CER on regular script, 1.57 percent on memorials, and 4.83 percent on running script. The router achieves 99.3 percent page-level domain accuracy and matches the domain-label oracle at the same precision. Two of the three selected specialists were not trained specifically for their final domain; only the running-script expert was trained with that domain as its target. We report the evaluation protocol, router design, and per-page predictions to make the comparison reproducible.
Read the full abstract

Computer Vision

M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming

Ke Cheng, Hanqiao Ye, Lei Shi et al. (+8 more)

Driving-world generation has emerged as a core capability for scalable autonomous-driving simulation, yet existing methods remain limited in object-level controllability and long-horizon stability. We present M$^\text{4}$World, a Multi-view and Multimodal generative driving world model that synthesizes future surround-view video streams and synchronized LiDAR scans while supporting interactive object Manipulation and stable Minute-long streaming. Fine-grained object manipulation is realized through a flexible conditioning interface that supports explicit control over both the spatial layout and visual appearance of individual objects. Stable minute-long streaming, on the other hand, is achieved through a multi-stage training framework that enables online causal generation in only four denoising steps while maintaining coherent world dynamics throughout extended rollouts. Building on these components, we introduce an efficient few-clip post-training as well as a suite of visual reference-conditioned generation models, preserving general generation ability while allowing rare-case customization for long-tail controllability. To assess controllability beyond realism, we further introduce an automated VLM-based judging pipeline that evaluates scene-level condition adherence, view-wise object controllability, and cross-view object consistency. Comprehensive experiments show that M$^\text{4}$World consistently delivers high generation quality, precise controllability, and stable minute-long streaming. Together with downstream long-tail augmentation and scene editing, these results demonstrate the potential of M$^\text{4}$World for controllable, scalable driving simulation.
Read the full abstract

All authors Ke Cheng, Hanqiao Ye, Lei Shi, Yahui Liu, Yunhan Shen, Jingtao Dong, Zhenke Wang, Wenxuan Ao, Weixiang Xu, Kaining Huang, Shuhan Shen

Computer Vision

Task-Specific Feature Fusion Method for Multi-Task Affective Behavior Analysis

Jiajun Sun and Zhe Gao

The 11th Affective Behavior Analysis in-the-wild (ABAW11) Multi-Task Learning Challenge requires a unified system to predict valence-arousal, categorical expressions, and facial action units from the official s-Aff-Wild2 images. Although these tasks are naturally related through facial behavior, our validation experiments show that they benefit from different visual features, temporal processing strategies, fusion mechanisms, and calibration procedures. In this paper, we study task-adaptive feature fusion for ABAW11 multi-task affective behavior analysis. We first adapt two pretrained visual backbones, DINOv2 ViT-L and DINOv3 ConvNeXt-base, on an external expression-oriented facial image set and then freeze them to extract complementary frame-level features from the official ABAW11 data. On top of these frozen features, we systematically compare frame-level prediction heads, temporal convolutional heads, post-hoc temporal smoothing, LightGBM models, feature concatenation, gated fusion, residual fusion, late logit fusion, threshold calibration, and shared MTL structures. The final system selects task-specific fusion and prediction strategies rather than forcing all tasks to share a single architecture. On the ABAW11 validation set, the selected system achieves an EXPR macro-F1 of 0.4222, an AU macro-F1 of 0.5402, and a mean VA CCC of 0.6717, resulting in an overall validation score of 1.6341. The results suggest that task-adaptive fusion of frozen visual features is a simple and effective strategy for ABAW-style multi-task affective behavior analysis.
Read the full abstract

Computer Vision

Screening Is Effective for Visual Recognition

Shunya Shimomura and Kazuhiro Hotta

Vision Transformer (ViT) has been widely used as a powerful framework for modeling global dependencies among image patches. However, its core component, self-attention assigns softmax-normalized relative weights to all patches, making it difficult to evaluate the relevance between patches independently. In visual recognition, images often contain many background or redundant patches, yet self-attention cannot explicitly reject such irrelevant patches, which may introduce unnecessary information into feature aggregation. To address this limitation, Screening has been proposed in the field of language modeling, where the relevance of each token is independently evaluated based on query-key similarity and low-relevance tokens are explicitly excluded through thresholding. In this work, we propose VisionScreen, a new vision model that extends Screening mechanism to visual recognition. VisionScreen treats image patches as tokens arranged on a two-dimensional grid and extends absolute relevance estimation based on query-key similarity to the two-dimensional spatial domain. This allows each patch to selectively aggregate only content-wise and spatially relevant patches without relying on competition among patches. Experiments on image classification benchmarks demonstrate that the proposed method outperforms conventional ViT. These results suggest that Screening can be effective for visual recognition, offering an alternative to relative feature aggregation based on softmax attention.
Read the full abstract

Computer Vision

Music-to-Dance Generation via Atomic Movements

Xinhao Cai, Yixuan Sun, Minghang Zheng et al. (+4 more)

Music-driven dance generation aims to produce human motion that is both rhythmically synchronized and semantically consistent with music. While recent neural approaches have achieved impressive visual realism, they typically model motion as a continuous signal and neglect its compositional nature, making generated dances structurally incoherent and difficult to control. In this work, we introduce a structure-aware framework that models choreography as a sequence of atomic movements-semantically interpretable motion events that serve as the building blocks of dance. To construct this atomic movement vocabulary, we first segment large-scale dance data and cluster them into atomic movement groups. We then employ a large language model to semantically relabel and refine the clusters, yielding a set of interpretable and reusable atomic movements. Based on these atomic movement annotations, we design a two-stage generation framework that mirrors the human choreography process. In the atomic movement planning stage, the model predicts the type, duration, and timing of atomic movements conditioned on the input music, forming a symbolic dance allocation. In the completion stage, a transition-aware generator synthesizes smooth and stylistically coherent motion conditioned on the planned structure. Extensive experiments demonstrate that our method produces dances with significantly improved structural coherence, rhythmic alignment, and perceptual naturalness compared to existing baselines, while providing enhanced interpretability and controllable editing through explicit structural representation.
Read the full abstract

All authors Xinhao Cai, Yixuan Sun, Minghang Zheng, Qingchao Chen, Xin Jin, Song-chun Zhu, Yang Liu

Computer Vision

CF-Net: Conflict Fusion with Speaker Normalisation and Certainty Weighting for Ambivalence/Hesitancy Recognition

Tung Hung Bui, Hong Hai Nguyen and Van Thong Huynh

Detecting ambivalence and hesitancy (AH) in unconstrained video is challenging because the target signal is inherently ambiguous and expressed through subtle cross-modal incongruence rather than prototypical affect. We present CF-Net, a deep multimodal network submitted to the 3rd Edition of the AH Video Recognition Challenge (ABAW 11th, ECCV 2026), targeting the BAH dataset. CF-Net encodes visual, audio, and transcript streams with frozen SigLIP2, HuBERT, and DistilBERT backbones, normalises backbone features per speaker to reduce identity leakage, and fuses them via a ConflictFusion module that explicitly computes pairwise cross-modal incongruence. Training combines certainty-weighted focal loss, manifold mixup, and modality dropout; an auxiliary certainty-regression head uses ambiguity annotations to stabilise learning on genuinely borderline samples. CF-Net achieves a Macro F1 of 0.7155 on the BAH validation set and 0.7364 (AP = 0.7439) on the private challenge test set.
Read the full abstract

Computer Vision

PlumeQuant: Uncertainty-aware consistency assessment of methane plume masks and emission-rate estimates

Parisa Masnadi Khiabani, Wolfgang Jentner, Alireza Rangrazjeddi et al. (+4 more)

Imaging spectrometers increasingly distribute source-resolved methane plume products in which the plume mask, integrated mass enhancement (IME), plume length, emission rate, and uncertainty are physically and algorithmically linked. Using 63 EMIT-derived Carbon Mapper plume records from 27 scenes, we show that these published scalar quantities do not uniquely constrain the plume boundary: substantially different yet plausible masks reproduce the same IME, plume length, and emission rate. Genetic-algorithm (GA) ensembles conditioned on the published IME and plume length make this equifinality explicit: the high-confidence core selected by nearly all target-consistent masks covers a median of 13% of the plausible footprint envelope, and ambiguity is largest for weak, low-overlap plumes. The diagnostics come from PlumeQuant, which recomputes IME, plume length, emission rate, and five-term uncertainty from distributed product components under stated conventions and evaluates four mask representations: the distributed reference mask, a transparent Carbon Mapper-informed analogue (CM-like), the GA ensemble, and optional expert edits. The CM-like mask is generated per plume without access to the reference mask or published quantities, with settings fixed once on a scene-disjoint 44-plume development split. It reproduced published IME with +0.72% median difference and emission rate with +0.16% (6.98% mean absolute), reached 0.843 median intersection-over-union against the reference masks, and matched the published uncertainty scale (median ratio 1.01). Holdout mean absolute errors were 7.6% (IME), 9.5% (length), and 6.1% (rate). These are product-level consistency diagnostics, not independent validation. They flag weak, offset, or ambiguous plumes for expert review.
Read the full abstract

All authors Parisa Masnadi Khiabani, Wolfgang Jentner, Alireza Rangrazjeddi, Michael C. Wimberly, Binbin Weng, David Ebert, Charles Nicholson

Computer Vision

Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment

Geng Li, Haiwen Li, Rui Chen et al. (+3 more)

Video aesthetic assessment (VAA) aims to predict how aesthetically pleasing a video is, yet remains far less explored than other visual assessment tasks. Its progress is hindered not only by the scarcity of large-scale benchmarks, but also by the intrinsic subjectivity of aesthetic judgment, which is shaped by human perception. In this paper, we revisit VAA from a psychological perspective and propose Peak-End-Net, a lightweight and interpretable framework inspired by the peak-end rule, which suggests that people tend to judge a temporal experience mainly according to its salient moments and the ending. Building on this intuition, we first transfer knowledge from image aesthetic assessment (IAA) to VAA by introducing a pretrained IAA head to produce frame-wise aesthetic priors, which serve as surrogate signals for identifying aesthetically salient moments and guiding peak-end rule-based temporal aggregation. To further capture how a video evolves aesthetically over time, we design an aesthetic rhythm encoder that models temporal progression beyond isolated moments. Additionally, we refine the overall assessment through a dynamic gated fusion mechanism to improve robustness under distribution shift. Our method is built on a frozen vision transformer (ViT) and requires only a small number of trainable parameters, making it scalable and parameter-efficient. Extensive experiments on two existing VAA benchmarks, including in-domain evaluation on VADB and cross-domain testing on DIVIDE-3K, demonstrate that our approach achieves state-of-the-art performance, affirming the value of psychologically grounded modeling for VAA. Our code and models are available at https://github.com/AMAP-ML/Peak-End-Net.
Read the full abstract

All authors Geng Li, Haiwen Li, Rui Chen, Jing Tang, Lei Sun, Xiangxiang Chu

Computer Vision

A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data

Brunnhilde Ponsi, Thomas Carlier, Lara Marteau et al. (+5 more)

Arrhythmogenic left ventricular cardiomyopathy is a genetic myocardial disease difficult to diagnose due to the lack of gold standard criteria. Simultaneous PET/MR imaging, combined with multiparametric quantitative analysis, could facilitate the identification of different profiles related to the phenotype and progression of cardiomyopathy. This preliminary study focuses on a methodological strategy for dealing with PET/MRI data, including inter-patient data linkage and regional analysis. Two-step clustering was applied to T1 and T2 maps, LGE, and 18F-FDG-PET images of 99 patients genetically diagnosed with arrhythmogenic left ventricular cardiomyopathy. Each patient's images were independently z-scored and summed into a single volume, which was clustered into supervoxels. Thirty-two inter-patient groups of supervoxels were obtained by spectral clustering. An "abnormality" score was assigned to each cluster and modality, and used to visualise abnormal regions likely associated with disease. They enabled the generation of automated textual and bullseye health reports for each patient, which were compared with cardiac imager assessments using balanced accuracy in repeated nested cross-validation. This approach was further validated on a larger cohort of 167 numerical phantoms. The reports generated by clustering accurately identified most of the cardiac physicians' observations (BA = 0.76 $\pm$ 0.04 in repeated nested cross-validation on patients, and BA $\ge$ 0.8 on phantoms). Furthermore, the identified abnormal clusters closely matched their visual observations, facilitating the identification of varying degrees of fibrosis or inflammation on the images. This approach enables a more systematic handling of multimodal PET/MRI data to characterise myocardial heterogeneity in arrhythmogenic left ventricular cardiomyopathy patients.
Read the full abstract

All authors Brunnhilde Ponsi, Thomas Carlier, Lara Marteau, Aurélien Monnet, Thomas Eugène, Jean-Michel Serfaty, Nicolas Piriou, Hatem Necib

Computer Vision

SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning

Cheng Tang, Junzhi Ning, Min Cen et al. (+9 more)

Reinforcement learning with verifiable rewards (RLVR) drives multimodal reasoning, but answer-level correctness does not guarantee that a vision-language model grounds its predictions in visual evidence. Existing visual-intervention methods contrast policy behavior on original and modified images, yet assign supervision by the type of intervention rather than its observed effect. This assumption fails: identical operators produce heterogeneous outcomes across samples. We propose SIVA-RL, a Sensitivity-Invariance Visual Alignment framework that replaces operator-conditioned regularization with sample-wise, outcome-conditioned supervision. SIVA-RL constructs localized interventions through token-aligned, distance-constrained within-image PatchSwap. A frozen audit policy then scores each clean-intervention pair, and the observed reward drop becomes soft routing weights. Large-drop pairs drive sensitivity alignment, low-drop pairs drive clean-anchored invariance alignment, and ambiguous pairs are down-weighted. This design decouples intervention construction from supervision assignment and is compatible with both GRPO and DAPO backbones. Across nine multimodal reasoning benchmarks spanning mathematical, logical, and vision-dependent tasks, SIVA-RL improves 3B and 7B models over matched RL baselines in every setting. It yields an 8.79 percentage-point gain on vision-dependent reasoning and up to 14.9% relative overall improvement across all four GRPO- and DAPO-based configurations.
Read the full abstract

All authors Cheng Tang, Junzhi Ning, Min Cen, Wei Li, Xinyi Zeng, Pinxian Zeng, Rongbin Li, Qiming Zhu, Yuqiang Li, Junjun He, Yirong Chen, Ming Hu

Computer Vision

Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data

Thang-Anh-Quan Nguyen, Moussab Bennehar, Luis Guillermo Roldao Jimenez et al. (+5 more)

Reliable perception under diverse weather conditions remains a major challenge for autonomous driving systems. A common strategy to improve robustness is either to synthesize adverse weather conditions for training perception models or to apply weather-removal techniques to recover clean inputs. However, existing approaches typically rely on synthetic data augmentation or physics-based, task-specific models that require paired training data and often struggle to generate realistic weather effects or generalize robustly to out-of-domain scenarios. Toward this problem, we present Cyclone, a unified framework for weather editing based on latent diffusion, equipped with cycle-consistent constraints and knowledge from image-text models. Cyclone enables the generation of multiple weather conditions across diverse scenes while eliminating the need for paired data. Experimental results show that our approach produces more realistic, structure-preserving outputs than existing baselines and leads to consistent improvements across several downstream driving perception tasks. Furthermore, we demonstrate that Cyclone can be distilled to a video diffusion model for temporally consistent weather editing.
Read the full abstract

All authors Thang-Anh-Quan Nguyen, Moussab Bennehar, Luis Guillermo Roldao Jimenez, Nathan Piasco, Dzmitry Tsishkou, Laurent Caraffa, Jean-Philippe Tarel, Roland Brémond

Computer Vision

Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement

Yanyi Wu, Xu Zhang, Junkai Chen et al. (+6 more)

Low-Light Image Enhancement (LLIE) requires a careful balance among noise suppression, color fidelity, and efficiency. Recent HVI-based methods alleviate color entanglement by decoupling intensity and chromaticity, yet how reliably the two streams are fused again is an overlooked factor that largely determines the final quality. We observe that the confidence of cross-stream attention is strongly layer-dependent, so the fixed-quota selection of Top-K sparse attention is mismatched to it, discarding informative dependencies in some layers while retaining noisy ones in others. Motivated by this observation, we propose TCA-Net, a network built around Thresholded Cross-Attention that targets reliable intensity-chromaticity fusion in the HVI space rather than introducing yet another color representation. At its core, TCA replaces the rigid Top-K quota with a fixed confidence threshold whose retained cardinality is input- and layer-adaptive, retaining only high-confidence cross-stream interactions while suppressing unreliable ones. Around this core, two complementary designs clean up the fusion before and after it: a Phase-guided Fourier Interaction Module provides a structure-aware brightness initialization for the intensity stream prior to fusion, and a Decoupled Dual-Stream Guidance Module constructs residual intensity features to suppress chromaticity leakage during reconstruction. A Scale-Aware Consistency Regularization further improves structural robustness under scale perturbations during training. Extensive experiments on LOL-v1, LOL-v2, Sony-Total-Dark, and LSRW-Huawei demonstrate that TCA-Net delivers competitive restoration accuracy, improved color fidelity, and a compact parameter size.
Read the full abstract

All authors Yanyi Wu, Xu Zhang, Junkai Chen, Laibin Chang, Jiaqi Ma, Shi Chen, Linwei Zhu, Jianglei Di, Huan Zhang

Computer Vision

The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides

Robyn Larracy, Anant Gupta, Gourav Gupta et al. (+8 more)

The International StepUP Competition Series was launched to advance research in pressure-based footstep biometrics through a standardized and challenging evaluation framework. Using the large-scale StepUP-P150 dataset (with more than 200,000 high-resolution dynamic footsteps from 150 individuals) and a previously unreleased test set, the 2nd edition of the competition addressed three key challenges: (1) generalization to unseen users with limited enrollment data, (2) robustness to domain shift caused by variations in footwear and walking speed and (3) effective fusion of paired left-right footsteps. While the first two challenges built on the inaugural competition, this edition introduced more extreme cross-domain conditions and moved beyond isolated footsteps to stride-level verification, enabling new opportunities for representation learning and inter-step information fusion. The competition attracted 26 registrants from academia and industry, with a best equal error rate of 8.00% achieved by the ArogyaPandit Research Team using a spatiotemporal CNN combined with an ensemble-based scoring strategy. The top solutions showcase the value of harnessing temporal patterns and of incorporating inference-time normalization and calibration strategies to improve scoring. However, the results also reveal that recognizing users in unseen personal footwear remains a challenge, especially in the presence of distractors with similar characteristics.
Read the full abstract

All authors Robyn Larracy, Anant Gupta, Gourav Gupta, Ethan Eddy, Maxime Devanne, Cyril Meyer, Jin-Chern Chiou, Yueh-Shan Lee, Zong-Han Lu, Aaron Tabor, Erik Scheme

Computer Vision

Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding

Guoliang You and Xiaomeng Chu

Computed tomography (CT) vision-language pretraining from paired volumes and radiology reports is a scalable yet challenging task. Existing methods commonly adopt global scan-report contrast, which is scalable but obscures heterogeneous organ evidence. Meanwhile, direct organ-level alignment remains coarse, since the same anatomy can exhibit multiple distinct radiological appearances. Therefore, pretraining requires a finer alignment unit: the organ-conditioned radiological pattern. In this work, we propose OCP-CT, an organ-conditioned pattern-token alignment framework for CT vision-language pretraining. Specifically, OCP-CT preserves a stable global CT-report contrastive branch and introduces an organ pattern interface: sparse Mixture-of-Experts (MoE) routes image and text tokens according to latent radiological patterns, learnable slots query the routed tokens into continuous pattern tokens, and paired token contrast aligns image-text pattern tokens with structured soft targets built from report-derived clinical similarity. On the publicly available CT-RATE and RAD-ChestCT benchmarks, OCP-CT achieves average AUROCs of 84.5% and 69.9% for zero-shot abnormality diagnosis, respectively. Compared with the strongest prior reported results, these results yield absolute AUROC gains of 6.7 and 0.8 percentage points.
Read the full abstract

Computer Vision · Cross-listed from cs.LG

PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter

Runze Gan, Qing Li, Simon J. Godsill et al. (+2 more)

Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based on Poisson measurement models offer a training-free solution but struggle to achieve accuracy and efficiency under severe clutter, large object populations, and full-resolution Doppler point clouds. We address this with PiVoT, a fast, clutter-resilient multi-object tracker for both positional and Doppler measurements. PiVoT performs end-to-end detection and tracking of a large and time-varying number of objects without external clustering or detectors, through joint inference of object states, shapes, existence probabilities, data association, and measurement rates. Its efficiency is driven by several variational inference innovations, such as theoretically justified birth pruning, quadratic-to-linear complexity reductions for exact updates, and a computationally efficient Doppler Poisson model. Experiments show that PiVoT substantially outperforms existing Bayesian trackers in challenging scenes, while also demonstrating exceptional scalability to a thousand objects, robustness to clutter visually inseparable from objects, and real-time operation on full-scale modern automotive radar datasets, where it attains performance comparable to a deep-learning detection benchmark as a training-free joint detector and tracker.
Read the full abstract

All authors Runze Gan, Qing Li, Simon J. Godsill, Mike E. Davies, James R. Hopgood

Computer Vision

Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild

Ting Lei, Jialin Liu, Zhu Xu et al. (+2 more)

Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories. While such paradigms achieve strong performance on closed-set benchmarks, they fundamentally entangle interaction understanding with dataset-specific supervision, limiting their ability to generalize to open-world and compositional scenarios. Recent HOI detectors attempt to leverage MLLMs through prompting strategies to transfer interaction-specific knowledge. However, such prompt-based approaches primarily focus on extracting discriminative representations from pretrained models, while underexploring their inherent multimodal reasoning capabilities. As a result, they struggle to provide informative contextual reasoning for ambiguous and open-world interaction scenarios. In this work, we present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild. Instead of learning interaction classifiers, AgentHOI modularly orchestrates complementary vision foundation modules to perform open-ended semantic reasoning and spatial grounding in a coordinated manner. To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms: (1) Context-aware Multi-round Reasoning, which progressively refines interaction hypotheses to ensure exhaustive and compositional HOI discovery, and (2) Multifaceted Interaction Localization, which enhances grounding precision by generating instance-specific descriptions that integrate semantic, spatial, and appearance cues. Extensive experiments demonstrate that AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings, despite requiring no HOID data for training.
Read the full abstract

All authors Ting Lei, Jialin Liu, Zhu Xu, Yuxin Peng, Yang Liu

Computer Vision

Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models

Zhuoyuan Fu, Zeshang Li, Yiqiong Zhang et al. (+5 more)

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in 2D medical image understanding, their extension to 3D volumetric imaging remains hindered by prohibitive annotation costs and dataset opacity. Current data formats, predominantly consisting of rigid Visual Question Answering (VQA) pairs or unstructured final clinical reports, typically fail to capture explicit clinical reasoning. To address this limitation, we introduce a large-scale structured reasoning dataset constructed via a novel slice-wise data synthesis paradigm. Inspired by the genuine diagnostic workflow of radiologists, this paradigm models visual cognition by decomposing the complex 3D reading process, translating global clinical priors into fine-grained, per-slice observations that are subsequently synthesized into an interpretable Chain-of-Thought (CoT). Crucially, this synthesized reasoning framework enforces essential clinical principles: sequential spatial tracking, multi-slice spatial awareness for artifact mitigation, and differential exclusion. To validate this approach, we instruction-tune a standard 2D-pretrained MLLM baseline using the synthesized data to enhance its volumetric comprehension. Comprehensive evaluations across multiple 3D medical benchmarks demonstrate that our method yields significant performance improvements over the 2D baseline. Furthermore, the resulting model exhibits robust spatial reasoning capabilities and rivals resource-intensive native 3D architectures, effectively bridging the performance gap. Ultimately, this data-centric strategy unlocks deep volumetric understanding and highly interpretable clinical logic without requiring computationally expensive 3D-specific pre-training. The complete repository, including datasets and training workflows, is publicly available at https://github.com/2020420145009/hounsfield.
Read the full abstract

All authors Zhuoyuan Fu, Zeshang Li, Yiqiong Zhang, Hangui Lin, Yan Shu, Yan Li, Binyang Li, Yaru Zhao