Computer Vision and Pattern Recognition Papers

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin, Zhihua Wei, Wen Shen arxiv.org/abs/2605.11808 [𝚌𝚜.𝙲𝚅]

OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models Minseok Kang, Minhyeok Lee, Jungho Lee, Minjung Kim, Donghyeong Kim, Dayeon Lee, Heeseung Choi, Ig-jae Kim, … arxiv.org/abs/2605.11803 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸] 💬Code: github.com/minseokii/OTT-…

SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions Markus Essl, Marta Moscati, Mubashir Noman, Muhammad Zaigham Zaheer, Usman Naseem, Shah Nawaz, Markus Schedl arxiv.org/abs/2605.11799 [𝚌𝚜.𝙲𝚅] 💬Accepted at ICIP 2026

Urban Risk-Aware Navigation via VQA-Based Event Maps for People with Low Vision Antoni Valls, Jordi Sanchez-Riera arxiv.org/abs/2605.11782 [𝚌𝚜.𝙲𝚅] 💬Submitted to IEEE T-ITS

Revisiting Shadow Detection from a Vision-Language Perspective Yonghui Wang, Wengang Zhou, Hao Feng, Houqiang Li arxiv.org/abs/2605.11771 [𝚌𝚜.𝙲𝚅]

M⁴-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection Jiyuan Liu, Jia Lin, Xiaofei Zhou, Runmin Cong, Deyang Liu, Zhi Liu arxiv.org/abs/2605.11760 [𝚌𝚜.𝙲𝚅]

Focusable Monocular Depth Estimation Yuxin Du, Tao Lin, Zile Zhong, Runting Li, Xiyao Chen, Jiting Liu, Chenglin Liu, Ying-Cong Chen, Yuqian Fu, Bo Zhao arxiv.org/abs/2605.11756 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

BronchoLumen: Analysis of recent YOLO-based architectures for real-time bronchial orifice detection in video bronchoscopy Yongchao Li, Marian Himstedt arxiv.org/abs/2605.11748 [𝚌𝚜.𝙲𝚅]

WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views SeongMin Jin, Doo Seok Jeong arxiv.org/abs/2605.11743 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶] 💬Accepted as a regular paper at ICML2026

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating Jiyuan Wang, Huan Ouyang, Jiuzhou Lin, Chunyu Lin, Dewen Fan, Boheng Zhang, Haonan Fan, Fei Zuo, Jia Sun, Huaiqing Wang, Honglie Wang, Yiyang Fan, … arxiv.org/abs/2605.11723 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation Sunung Mun, Sunghyun Cho, Jungseul Ok arxiv.org/abs/2605.11722 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙻𝙶]

CAST: Collapse-Aware multi-Scale Topology Fusion for Multimodal Coreset Selection Boran Zhao, Hetian Liu, Zhenxian Hu, Yuqing Yuan, Yu Yan, Pengju Ren arxiv.org/abs/2605.11705 [𝚌𝚜.𝙲𝚅]

ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation Inwoo Hwang, Hojun Jang, Bing Zhou, Jian Wang, Young Min Kim, Chuan Guo arxiv.org/abs/2605.11704 [𝚌𝚜.𝙲𝚅] 💬Project: inwoohwang.me/ScaleMoGen

WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting Lezhong Wang, Mehmet Onurcan Kaya, Siavash Bigdeli, Jeppe Revall Frisvad arxiv.org/abs/2605.11696 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙶𝚁] 💬Project: lez-s.github.io/wildrelight_pr…

Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning Mikako Ochiai, Masatoshi Nagano, Tadahiro Taniguchi arxiv.org/abs/2605.11695 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

DORA: Dynamic Online Reinforcement Agent for Token Merging in Vision Transformers Kaixuan He, Song Chen, Yi Kang arxiv.org/abs/2605.11683 [𝚌𝚜.𝙲𝚅]

ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes Shivam Kumar arxiv.org/abs/2605.11680 [𝚌𝚜.𝙲𝚅] 💬Code: github.com/shivamk3r/shap…

Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning Yaze Zhao, Yicong Liu, Yixiong Zou, Yuhua Li, Ruixuan Li arxiv.org/abs/2605.11659 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸]

Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet, Nguyen Lam Phu Quy, Phu-Hoa Pham, Long Tran-Thanh arxiv.org/abs/2605.11654 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝚁𝙾]

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee, Jeany Son arxiv.org/abs/2605.11651 [𝚌𝚜.𝙲𝚅 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻]