cs.CV · 2026-08-12 · No. 82
Computer Vision and Pattern Recognition, 2026-08-12.
30 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
30 entries-
01
Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
Shiyu Xuan, Zechao Li
cs.CV · cs.AI · cs.CL
GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ability to adapt to unseen interfaces. Although recent methods attempt to adapt models via test-time reinforcement learning, they cannot reflect upon failed exploration. To overcome this, we propose a Test-Time Self-Evolving framework that enables models to improve after deployment without...
-
02
MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment
Changhao Xiang, Shangyu Xing, Zhen Wu, Jianbing Zhang, Xinyu Dai
cs.CV · cs.CL · cs.LG
Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions. However, this image-level alignment suffers from referential ambiguity: models struggle to infer the correspondences between multiple visual objects and textual entities from the global representation, leading to data inefficiency and suboptimal semantic...
-
03
AlbumentationsX: One Augmentation Pipeline for Images and Related Annotations
Vladimir Iglovikov
cs.CV · cs.LG
Augmentation can corrupt a training example when an image and its annotations receive different random changes. A crop must use the same coordinates for the image, mask, boxes, keypoints, stereo views, video frames, or volume. Code paths that choose these values separately can silently misalign the data. AlbumentationsX keeps the transform list, probabilities, annotation settings, and random seed in one Compose object. Each call chooses...
-
04
Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
Ali Saleh, Abdul Karim Gizzini, Mohamad Ghassany, Ali J. Ghandour
cs.CV · cs.AI
Artificial intelligence (AI) has become a powerful approach to solving complex problems in critical domains. Many concerns arise regarding the decision-making process of its models, mainly due to deep neural networks outperforming their peers at the cost of ambiguity in feature extraction and prediction. Consequently, in critical domains such as remote sensing, where high-resolution imagery must be analyzed using black-box models, the lack of...
-
05
A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa
Ismail Ismail Tijjani, Sunusi Muhammad Ibrahim, Amina Ibrahim Khaleel, Lanre Olusegun Akinola, Fatima Isa Jibrin,...
cs.CV · cs.AI
The application of computer vision in agriculture has shown significant potential for improving crop monitoring and precision farming. However, many existing approaches rely on controlled datasets that do not adequately represent realworld farming conditions, particularly in underrepresented regions such as Africa. This study presents a comparative evaluation of six object detection models YOLOv5, YOLOv8, YOLO11, YOLO26, Faster R-CNN, and...
-
06
3D Weighted Geometric Graph Neural Networks for Sheep Facial Pain Assessment
Alam Noor, Luis Almeida, Mohamed Daoudi
cs.CV · cs.AI
Deep learning systems perform mainly within the 2D for a single image domain and take the face as a single-dimension representation, losing sight of the 3D anatomy of sheep and cross-landmark spatial relationships that are intrinsic to the clinically proven Sheep Pain Facial Expression Scale (SPFES). This paper presents the \textbf{3D Sheep Pain Facial Expression System (3D-SPFES)}, a novel, monocular depth-aware geometric graph neural...
-
07
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
Ke Ma, Yamin Mao, Weiming Li, Shuai Tan, Yijie Zhong, Hao Chen, Haofen Wang, Meng Wang
cs.CV · cs.AI · cs.HC · cs.MM
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph...
-
08
Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers
Hongsen Cao, Mona Jaber, Shanxin Yuan, Ahmed Sayed
cs.CV · cs.AI
Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with different spatial demands. We ask which parts of a pruning policy transfer across image classification, semantic segmentation, and object detection. For each pipeline, controlled probes freeze the no-pruning checkpoint and apply a series of parameter-free reduction criteria at one eligible layer at a...
-
09
CARE: Confidence-Aware Reasoning for Reliable Medical VQA
Yuetian Du, Yucheng Wang, Zhenyuan Chen, Luyuan Chen, Rongyu Zhang, Jinjian Zhang, Wei Zhou, Zhijie Xu, Ming Kong,...
cs.CV · cs.AI
Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these models suffer from $\textit{confidence miscalibration}$---a systematic gap between expressed certainty and actual diagnostic accuracy that undermines clinical trust. We propose $\textbf{CARE}$, a $\textbf{C}$onfidence-$\textbf{A}$ware medical $\textbf{RE}$asoning...
-
10
Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes
Zhaoyang Wei, Bowen Jiang, Xumeng Han, Jiashu Li, Xuehui Yu, Yuling Liu, Guorong Li, Zhenjun Han, Jianbin Jiao
cs.CV · cs.AI
While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes under adverse conditions. In these settings, models often rely on implicit inference without sufficient visual evidence, leading to a disconnect between perception and reasoning. Meanwhile, existing outcome-oriented benchmarks evaluate only final predictions and fail to...
-
11
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
Dazhao Du, Shiyan Du, Jian Liu, Yongjian Yu, Bohai Gu, Tao Han, Hualuo Liu, Eric Liu, Yujia Zhang, Xi Chen, Song Guo
cs.CV · cs.AI
Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs) provide a natural interface for this task, but existing work typically assigns one or more labels to an entire clip. Such clip-level recognition overlooks two defining properties of real camera motion: it can change within a shot, and multiple movements can occur...
-
12
VIDS-Seg: Towards Reliable Uncertainty Quantification in Pediatric Cardiac Ultrasound Segmentation
Paul Fischer, Ece Ozkan
cs.CV · cs.LG
Reliable clinical deployment of machine learning requires models that know when they are likely to fail, particularly for subgroups underrepresented in training data. A common case is pediatric care, where models trained on adult cohorts can silently under-perform on children with no indication that something has gone wrong. As retraining with labeled pediatric data is often infeasible, detecting such failures at inference time is a critical...
-
13
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
Dvir Samuel, Guy Bar-Shalom, Fabrizio Frasca, Ethan Fetaya, Yftah Ziser, Gal Chechik, Haggai Maron
cs.CV · cs.LG
Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input. Effective mitigation requires token-level localization, enabling targeted intervention without discarding the entire response. Existing detectors require expensive full-model fine-tuning, rely on external verifiers that ignore the model's generation process, or reduce internal...
-
14
MIRA: Medical Image Reflection for Agentic Diagnosis
Shengzhi Wang, Jun Yang, Kai Wu, Xiaozhong Ji, Yiwen Ye, Ziyang Chen, Mingliang Xiong, Wen Fang, Mingqing Liu,...
cs.CV · cs.AI
Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable diagnosis therefore requires not only acquiring additional observations, but also verifying whether tool actions are necessary and whether the resulting evidence supports the current hypothesis. We introduce MIRA (Medical Image Reflection for Agentic Diagnosis), a medical...
-
15
Modelling Geographic Atrophy Progression using Implicit Neural Representations
Simone Sarrocco, Paul Friedrich, Florentin Bieder, Christina Bornberg, Philippe Valmaggia, Peter Maloca, Philippe Cattin
cs.CV · cs.AI
Age-related Macular Degeneration (AMD) is the major cause of blindness in the Western world. Its late dry phase is characterised by irreversible atrophic areas, namely Geographic Atrophy (GA). Longitudinal Fundus Autofluorescence (FAF) image acquisitions are currently the main tool for assessing lesion growth over time at the image level. However, due to its highly individualised progression, the evolution of late AMD remains poorly...
-
16
Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation
Amit Aflalo, Shahaf E. Finder, Roy Amoyal, Eran Treister, Oren Freifeld
cs.CV · cs.AI
Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field exponentially with the number of decomposition levels while keeping the parameter count linear. However, its reference implementation is severely memory-bound due to excessive data movement through high-bandwidth memory (HBM). We develop an I/O model of WTConv to characterize this bottleneck...
-
17
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
Qiang Wang, Songlin Dong, Shaokun Wang, Jizhou Han, Xiang Song, Chenhao Ding, Yuhang He, Yihong Gong
cs.CV · cs.AI · cs.LG
Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradation under domain shifts. Domain incremental learning (DIL) addresses this challenge by enabling models to continuously adapt while retaining prior knowledge. Among existing DIL approaches, the parameter-isolation paradigm achieves state-of-the-art performance. However, these methods often adopt...
-
18
Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization
Swarnim Maheshwari, Syed Imam Ali, Vineeth N. Balasubramanian
cs.CV · cs.AI · cs.LG
Most image colorization systems operate in $Lab$ space by predicting chroma ($ab$) while preserving an input-derived luminance channel ($L$). While effective on standard benchmarks, this fixed-luminance design restricts brightness changes and becomes unreliable when grayscale formation deviates from natural-image luminance, as in historical orthochromatic photography. We propose a luminance-agnostic colorization framework that formulates...
-
19
MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams
Iñaki Erregue, Kamal Nasrollahi, Sergio Escalera
cs.CV · cs.AI
Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors. To this end, we present MVTrack, an ultrafast tracker for moving objects that operates directly on H.264 bitstreams. MVTrack combines MVDet, a lightweight detector for motion vector fields, with MVLink, a minimalist kinematic association module. On VIRAT, MVTrack outperforms YOLO26n while using 60$\times$ fewer parameters,...
-
20
Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving
Jiaping Wang, Shaobo Li, Zhen Wang
cs.CV · cs.AI
Continuous and reliable localization is essential for autonomous driving. Cross-view visual localization matches ground images with satellite maps, providing complementary localization cues for pipelines that depend on Global Navigation Satellite System (GNSS) signals and high-definition (HD) maps. Most existing cross-view visual localization methods process each frame independently, leaving temporal information underused and limiting...
-
21
MedUP: Awakening Unified Understanding and Perception in Medical Vision-Language Models
Yuan Wang, Hualiang Wang, Yixin Chen, Songtao Jiang, Shujian Gao, Jiaming Lin, Siming Fu, Jian Wu, Zuozhu Liu
cs.CV · cs.AI
Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging. Existing approaches either verbalize regions as coordinate strings or rely on external modules that decouple perception from understanding, creating representation gaps for region-language alignment. We present MedUP, a Med-VLM that natively unifies perception and understanding within a...
-
22
InSight-doc: Agentic Visual Perception for Long-Document Understanding
Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, Lanqing Hong, Yongxiang Huang, Nevin L. Zhang
cs.CV · cs.CL · cs.LG
Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose InSight-doc, an agentic visual perception framework that treats visual resolution as an adaptive reasoning-time resource. InSight-doc starts from low resolution and selectively zooms into high-resolution regions for finer evidence, without relying on any external retriever. To train...
-
23
$π$-SUB: A Physics-Informed Synthetic Underwater Benchmark Dataset for Underwater Image Enhancement
Namritha Lasyapriya Maddali, Rajini Makam, Suresh Sundaram, Narasimhan Sundararajan
cs.CV · cs.AI
This paper presents $π$-SUB, a physics-informed framework for generating synthetic underwater benchmark datasets that bridges the synthetic-to-real gap for Underwater Image Enhancement (UIE). The proposed framework extends the classical underwater image formation model by incorporating depth-dependent downwelling irradiance, biologically resolved absorption, and environmental scattering across all ten Jerlov water types, together with...
-
24
A HamNoSys-Guided Dataset and Baselines for Fine-Grained Isolated Handshape Recognition in Sign Language
Ushnish Sarkar, Suvajit Patra, Bhaswar Chattopadhyay, Pranab Singha Roy, Tapas Samanta
cs.CV · cs.AI
Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically defined visual inventories with signer-aware evaluation remain limited. This work introduces a benchmark grounded in the language-independent Hamburg Notation System (HamNoSys). Methods: A balanced dataset of 144,000 RGB images was collected from 15 participants for 160 handshape classes defined...
-
25
Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
Sangwoo Jo, Donggeun Ko, Jayeon Kang, Youngsang Kwak, Jaehwa Kwak, Sungjoon Choi
cs.CV · cs.AI · cs.LG
Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations. Recent approaches attempt to balance this tradeoff via posterior sampling or multi-stage generative pipelines, yet remain computationally expensive and architecturally complex. To overcome these limitations,...
-
26
Dynamic Context Adapters: Efficiently Infusing History into Vision-and-Language Models
Yuhang Song, Bor-Jiun Lin, Jiaxu Liu, Te-Chuan Chiu, Anh Nguyen, Chun-Yi Lee
cs.CV · cs.AI
Historical context integration presents a fundamental challenge for Vision-Language Models (VLMs) in sequential decision-making tasks. Current VLMs process visual inputs independently, which creates critical limitations for downstream applications that require temporal understanding. Direct incorporation of historical frames into Transformer inputs produces quadratic attention complexity and excessive memory consumption. Existing approaches...
-
27
Rethinking Text-Based Image Retrieval in Specific Domain
Jingyang Tan, Sheng Yang, Yuanpeng Chen, Jian Wang, Nianjin Ye, Chen Xing, Lanpeng Jia
cs.CV · cs.AI
Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress. However, existing benchmarks are predominantly constructed on an exclusive single-match assumption between query and images. While effective in general scenarios, this assumption fails to reflect practical system performance in specific domains (e.g., surveillance), where a single query often corresponds to...
-
28
Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training
Yingsheng Liu, Haiming Li, Jingmin Zhu, Jiajun Sun, Victoria Mar, Monika Janda, H. Peter Soyer, Zongyuan Ge, Zhen Yu
cs.CV · cs.AI
While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware...
-
29
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning
Caoyuan Ma, Wenpu Liu, Weichu Xie, Tian Gu, Shilei Zhao, Lingxi Min, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang,...
cs.CV · cs.AI
Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language backbones. We propose SafeCap, a reinforcement-learning framework that aligns LVLMs through learned self-captioning. SafeCap trains a policy model to first generate a safety-relevant image caption and then produce a final answer; the caption is further optimized by whether it enables a...
-
30
FUSE: Frame-Unified Stress Estimation from Facial Video
Stefanos Gkikas, Thomas Kassiotis, Yang Guo, Guangliang Li, Giorgos Giannakakis
cs.CV · cs.AI
Automatic stress detection from facial video offers a practical path to non-intrusive affect monitoring, yet existing video-based approaches commonly decompose full recordings into short temporal windows before classification. This design introduces additional choices regarding window length, overlap, and aggregation, while limiting direct analysis of temporal information across the entire recording. In this study, we present FUSE...
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.