cs.CV · 2026-08-11 · No. 81
Computer Vision and Pattern Recognition, 2026-08-11.
24 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
24 entries-
01
Multimodal Model Diffing for Feature Discovery and Control
Hunar Batra, Lachin Naghashyar, Ashkan Khakzar, Philip Torr, Christian Schroeder de Witt, Constantin Venhoff, Ronald Clark
cs.CV · cs.AI · cs.CL · cs.LG
Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control. While applicable to post-hoc inspection, hidden states that are decomposed into interpretable feature directions using sparse autoencoders (SAEs) neither readily isolate which features are changed by multimodal training, nor are they directly useful for targeted...
-
02
Space-Creating versus Dead Possession: An Off-Ball Possession-Quality Index for Broadcast Football
Seongjin Choi
cs.CV · cs.CY · cs.LG
Ball possession is the most-cited and most-misleading number in football: 60% recycled in one's own half is not 60% spent pinning the opponent back. Existing event-based possession-value frameworks (expected threat, VAEP, on-ball value) price on-ball actions but ignore the off-ball question a sterile possession poses: did holding the ball create space, or was the circulation dead? We answer this in two layers. First, an event-side...
-
03
Financial Numerical Prediction and Allocation as Token Generation
Xu Ouyang, Moontae Lee
cs.CV · cs.LG
Financial prediction typically relies on task-specific regression, ranking, or policy heads, separating the language model from the numerical object ultimately evaluated. We investigate whether a causal language model can instead represent forecasts and decisions directly through constrained token generation. FinATOM introduces a unified, head-free interface for three-step stock-return forecasting and dynamic five-ETF allocation. The...
-
04
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
Diandian Zhang, Tingyu Song, Lin Fu, Zheyuan Yang, Yilun Zhao
cs.CV · cs.AI
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four core disciplines: Natural Science, Healthcare, Humanities & Social Sciences, and Engineering. Each example requires models to generate temporally rich videos that demand scientific reasoning and knowledge-grounded synthesis,...
-
05
MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation
Haoyu Yang, Meixing Shi, Zengjie Chen, Haoran Sun, Haitao Leng, Xiaoming Shi, Yuxiang Cai, Yankai Jiang
cs.CV · cs.AI
Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack precise localization, whereas medical segmenters typically rely on explicit target categories or precise spatial prompts. This divide is reinforced by a supervision mismatch: segmentation datasets provide precise masks but little language supervision, whereas medical...
-
06
Modern Backbones Improve Multi-task DETR for Mammography Classification and Lesion Localization
Dinh Tan Nguyen, Quang-Hien Kha, Le-Hoang Nguyen, Minh-Toan Dinh, Xuan-Huy Nguyen, Dac Phu Ho, Cao Truong Tran, Sai...
cs.CV · cs.AI
Joint exam-level prediction and candidate-region localization may improve the usefulness of AI support in mammography. We study this setting using a multi-task DETR framework, where shared representations support both image-level malignancy prediction and lesion localization, and evaluate its performance on OPTIMAM and a biopsy-confirmed SGM1k cohort. Across both datasets, modern backbones consistently outperformed older ResNet-style...
-
07
C$^2$A: Coupling Spatial Evidence with Clinical Priors via Co-occurrence Aware Class Attention for Multi-Label Chest X-Ray Classification
Akash Gogineni, Nagur Shareef Shaik, Aasrith Mandava, Adnan Masood, Dong Hye Ye
cs.CV · cs.LG · eess.IV · eess.SP
Thoracic pathologies rarely occur in isolation, yet standard multi-label classifiers rely on shared global descriptors, discarding \emph{where} findings lie and \emph{how} they co-occur. We propose \textbf{C$\mathbf{^2}$A} (Co-occurrence Aware Class Attention), a classification head that explicitly couples spatial evidence with clinical priors. First, C$^2$A casts pooling as an expectation over learned per-class spatial attention maps,...
-
08
Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing
Nagur Shareef Shaik, Jeongwoo Park, Yeong-Jin Kim, Jaeuk Jung, Hyunjung Oh, Dong Hye Ye
cs.CV · cs.LG · eess.IV · eess.SP
Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation to every image regardless of the underlying disease distribution. We propose a novel architecture that resolves this via sparse conditional computation, pairing a Guided Context Gating (GCG) spatial attention front-end with a sparsely-routed Mixture-of-Experts (MoE) block operating over feature...
-
09
DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation
Zian Li, Litong Gong, Borui Liao, Pengfei Liu, Xinyu Wang, Xinyuan Wei, Yifan Gao, Tiezheng Ge, Muhan Zhang
cs.CV · cs.AI
Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation alleviates this cost, yet exposes a quality--diversity trade-off between its two dominant paradigms: trajectory-level distillation (e.g., sCM) favors diversity, whereas distribution-level distillation (e.g., DMD) favors quality. Targeting extreme two-step video...
-
10
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
Haiyang Yan, Jinyue Guo, Yanchao Zhang, Bingqing Wang, Zhenchen Li, Jing Liu, Jiazheng Liu, Linlin Li, Hua Han
cs.CV · cs.AI
Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience. However, the sparse and elongated morphology of neurons poses significant challenges to existing segmentation methods. These methods struggle to preserve both local details and global topology, leading to fragmented results. To address this, we propose NeuroRefiner, a multi-agent system that formalizes the human expert workflow involving iterative global...
-
11
LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection
Peter Lorenz, Anjith George, Marcel Sébastien
cs.CV · cs.LG
Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks. While PAD methods achieve strong performance within individual datasets, their performance degrades under cross-dataset evaluation. Variations in sensors or lighting conditions can reduce the effectiveness of detectors from near-perfect to nearly random. Foundation models (FMs) have emerged as a promising alternative because typical PAD...
-
12
Structure-Enhanced Features and Quality-Aware Dynamic Anchor Scoring for Robust Lane Detection
Weize Cai, Yongqi Dong, Zhida Shao, Yichen Liu, Zixin Fu
cs.CV · cs.AI · cs.LG · eess.IV · eess.SP
Lane detection requires recovering thin, elongated, and frequently occluded lane structures under challenging driving conditions. While anchor-based detectors provide efficient candidate generation, their performance is limited by two coupled issues: backbone features often lose structural continuity along partially visible lanes, and classification confidence may decouple from line-level localization quality, allowing inaccurate anchors to...
-
13
Illusion or Integrity? Geometrical Consistency Metric for AIGC Video Quality Evaluation
Yifei Xue, Yuanchen Fei, Hao Zhang, Chenzhi Nie, Tie ji, Yizhen Lao
cs.CV · cs.AI
Recently, AI-driven video generation has attracted considerable attention. This surge increases the demand for reliable video quality assessment (VQA) metrics to evaluate AI-generated content (AIGC) videos and guide model optimization. Existing studies assess video quality through visual harmony, video-text consistency, and domain-specific alignment, yet lack quantitative metrics for measuring fidelity to physical laws. To address this...
-
14
From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation
Zeyuan Ma, Jiaxin Chen, Di Huang
cs.CV · cs.AI
UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egocentric visual observations. Current approaches suffer from three coupled issues: weak grounding of instruction-relevant landmarks in visual observations, insufficient exploitation of long-horizon history, and unstable decisions under local traps or repeated exploration. To address these issues,...
-
15
XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher
Lazar Đoković, Aimee Lin
cs.CV · cs.LG
We present a reproducibility study of XFeat, a lightweight local feature extractor and matcher designed to identify corresponding points across images efficiently on resource-constrained hardware. We re-implement the architecture based on the paper and supplementary material, re-evaluate the authors' released checkpoint alongside our re-implementation, and conduct additional architectural ablations to examine design choices that were not...
-
16
Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance
Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng
cs.CV · cs.AI
All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model. Recent works have achieved remarkable progress by learning degradation-adaptive prompts or network architectures. However, these methods typically apply a uniform restoration strategy across the entire image, neglecting the fact that different...
-
17
RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation
Boxiong Wang, Hui Kang, Geng Sun, Jiahui Li, Chao Yu, Daxin Tian
cs.CV · cs.AI
Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments. Although recent end-to-end UAV vision-language-action (UAV-VLA) policies reduce reliance on separately designed perception, planning, and control modules, their behavior-cloning objectives provide limited corrective supervision for interactive closed-loop...
-
18
Sign Language Recognition Using Original and Synthetic Depth Image Based Point Cloud Data Models
Rustem Ozakar, Eyup Gedikli
cs.CV · cs.AI
Research regarding the sign language recognition mostly relies on RGB images, whileas sign language datasets that provide depth images are limited. Point clouds obtained from depth images can be used for sign language recognition with neural networks like PointNet. In recent years, various neural networks are used for generating realistic depth images from monocular RGB images. In this work, synthetic depth images were created from RGB images...
-
19
FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking
Yueyang Cang, Xiaoteng Zhang, Zhiyuan Ning, Yuchen He, Li Shi
cs.CV · cs.AI
Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates, prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate corresponding processing stages. We propose \textbf{FeedbackTrack}, a visual-cortex-inspired framework that introduces sparse,...
-
20
Deep Learning based Detection of Fishing Vessels and Fishing Monitoring using Nightlight Images
Shantakar Mohanty, Prasun Kumar Gupta, Raian Vargas Maretto
cs.CV · cs.AI · cs.LG · eess.IV · stat.AP
The demand for maritime surveillance has given rise to the need for monitoring fishing vessel activities, particularly in addressing the challenge of "dark vessels" that operate without Automatic Identification System (AIS) transmission. This study presents a novel approach for detecting small-scale fishing vessels using nighttime light (NTL) imagery from the SDGSAT-1 satellite, combined with deep learning techniques to enhance fishing...
-
21
UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillation
Xuewan He, Tong Chu, Zihan Cheng, Yuchen Su, Qianxin Xia, Guoming Lu, Jielei Wang, Wen Li
cs.CV · cs.AI
Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating the need for access to the original training dataset. Existing DFKD methods rely heavily on architecture-specific statistical priors (e.g., Batch Normalization statistics) to guide data synthesis, however, such architecture-dependent priors are often absent in modern...
-
22
GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views
Jiahui Cui, Yan Zhao, Kan Wei, Enze Zhu, Peirong Zhang, Lei Wang, Yiru Wang
cs.CV · cs.AI · cs.IR · cs.MM
Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation. However, the inherent wide field of view and overhead perspective of drone scenarios impose dual challenges on vision-language understanding. At the macro level, overwhelming background clutter in visual representations leads to Cross-Modal Focus Misalignment, where the model prioritizes global environmental similarities over specific...
-
23
Did the Grid Erase the Event? EndoClock for Auditing Medical World-Model Pipelines
Yarin Udi, Tom Sharon-Shahak, Roee Masad, Dan Pri-Tal
cs.CV · cs.LG
Medical world models commonly learn from multimodal recordings synchronized onto a fixed-rate grid. This preprocessing resamples each native stream onto a shared time axis. Each stream has an observation clock that governs when observations are emitted or updated. When this clock depends on the latent or acquisition state, it is endogenous. In such settings, synchronization may not be neutral and can erase task-relevant evidence before the...
-
24
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Yuhan Li, Fangao Zeng, Sicong Kang, Mengfei Xu, Hao Zhou, Wei Li, Pipei Huang, Bingbing Ni
cs.CV · cs.AI
Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.