Computer Vision and Pattern Recognition arXiv

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR Henry Gagnier, Sophie Gagnier, Ashwin Kirubakaran arxiv.org/abs/2603.13238 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙲𝙻]

Gloss-Free Sign Language Translation: An Unbiased Evaluation of Progress in the Field Ozge Mercanoglu Sincan, Jian He Low, Sobhan Asasi, Richard Bowden arxiv.org/abs/2603.13240 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙲𝙻]

Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation Mingyu Kim, Young-Heon Kim, Mijung Park arxiv.org/abs/2603.13300 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision Kirill Borodin, Kirill Kondrashov, Nikita Vasiliev, Ksenia Gladkova, Inna Larina, Mikhail Gorodnichev, Grach Mkrtchian arxiv.org/abs/2603.13306 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶]

Information-Theoretic Constraints for Continual Vision-Language-Action Alignment Libang Zhao, Qixin Zeng, Hongyin Zhang, Donglin Wang arxiv.org/abs/2603.13335 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

MultiSolSegment: Multi-channel segmentation of overlapping features in electroluminescence images of photovoltaic cells Ojas Sanghi (Sandia National Laboratories), Norman Jost (Sandia National Laboratories), … arxiv.org/abs/2603.13337 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition Zhexian Huang, Bo Zhao, Hui Ma, Zhishu Liu, Jie Zhang, Ruixin Zhang, Shouhong Ding, Zitong Yu arxiv.org/abs/2603.13340 [𝚌𝚜.𝙲𝚅]

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning Zhenyu Zhang, Yixiong Zou, Yuhua Li, Ruixuan Li, Guangyao Chen arxiv.org/abs/2603.13341 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

DDS-UDA: Dual-Domain Synergy for Unsupervised Domain Adaptation in Joint Segmentation of Optic Disc and Optic Cup Yusong Xiao, Yuxuan Wu, Li Xiao, Gang Qu, Haiye Huo, Yu-Ping Wang arxiv.org/abs/2603.13345 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

Post Training Quantization for Efficient Dataset Condensation Linh-Tam Tran, Sung-Ho Bae arxiv.org/abs/2603.13346 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval Fengbin Zhu, Zijing Cai, Yuzhe Wang, Pengyang Shao, Wenjie Wang, Fuli Feng, Richang Hong, Tat-Seng Chua arxiv.org/abs/2603.13349 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shifts Xi Chen, Maojun Zhang, Yu Liu, Shen Yan arxiv.org/abs/2603.13352 [𝚌𝚜.𝙲𝚅]

AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification Hamza Mooraj, George Pantazopoulos, Alessandro Suglia arxiv.org/abs/2603.13354 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶]

Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality Taewook Ha, Woojin Cho, Dooyoung Kim, Woontack Woo arxiv.org/abs/2603.13355 [𝚌𝚜.𝙲𝚅]

Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection Patricia L. Suarez, Leo Thomas Ramos, Angel D. Sappa arxiv.org/abs/2603.13357 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution Hua Liu, Yanbin Wei, Fei Xing, Tyler Derr, Haoyu Han, Yu Zhang arxiv.org/abs/2603.13360 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶]

BrainCast: A Spatio-Temporal Forecasting Model for Whole-Brain fMRI Time Series Prediction Yunlong Gao, Jinbo Yang, Li Xiao, Haiye Huo, Yang Ji, Hao Wang, Aiying Zhang, Yu-Ping Wang arxiv.org/abs/2603.13361 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸 𝚜𝚝𝚊𝚝.𝙼𝙻]

IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders Farida Mohsen, Tala Zaim, Ali Al-Zawqari, Ali Safa, Samir Belhaouari arxiv.org/abs/2603.13363 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach Ning Liao, Xiaoxing Wang, Xiaohan Qin, Junchi Yan arxiv.org/abs/2603.13364 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

WaveComm: Lightweight Communication for Collaborative Perception via Wavelet Feature Distillation Erdemt Bao, Jin Yang arxiv.org/abs/2603.13365 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]