Efficient Visual State Space Model for Image Deblurring
机构 * Nanjing University of Science and Technology（南京理工大学） ； University of California, Merced（加州大学默塞德分校） ； Google（谷歌）
Comments CVPR 2025
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Human-Robot Navigation using Event-based Cameras and Reinforcement Learning
机构 * Department of Electrical Engineering, Universidad de Chile（智利大学电气工程系） ； Advanced Mining Technology Center (AMTC), Universidad de Chile（智利大学先进采矿技术中心） ； Institute of Engineering Sciences, Universidad de O’Higgins（奥希金斯大学工程科学研究所）
Comments https://ibugueno.github.io/hr-navigation-using-event-cameras-and-rl/
Journal ref 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Fifth International Workshop on Event-Based Vision
Towards Scalable SOAP Note Generation: A Weakly Supervised Multimodal Framework
机构 * Department of Computer Science, University of Maryland, Baltimore County（计算机科学系，马里兰大学巴尔的摩县分校） ； Department of Dermatology, Johns Hopkins University School of Medicine（皮肤科系，约翰霍普金斯大学医学院）
Comments Accepted at IEEE/CVF Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
HalLoc: Token-level Localization of Hallucinations for Vision Language Models
机构 * Seoul National University（首尔国立大学）
Comments CVPR 2025
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos
机构 * Qualcomm AI Research（高通人工智能研究）
Comments CVPR 2025 Workshop on Autonomous Driving
Improving Personalized Search with Regularized Low-Rank Parameter Updates
机构 * Georgia Tech（佐治亚理工学院） ； Adobe Research（Adobe研究） ； CIIRC CTU（查理大学CIIRC） ； UIUC（伊利诺伊大学厄巴纳-香槟分校）
Comments CVPR 2025 Highlight. Code: http://github.com/adobe-research/polar-vl
Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model
机构 * Communication University of China（中国通信大学）
Comments This paper has been accepted by CVPR Workshop 2025
Federated Unsupervised Visual Representation Learning via Exploiting General Content and Personal Style
机构 * Duke University（杜克大学）
Comments Reformat to CVPR format
Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes
机构 * University of Michigan（密歇根大学） ； University of Pennsylvania（宾夕法尼亚大学）
Comments CVPR 2025, Project page: https://www.yimingdou.com/hearing_hands/ , Code: https://github.com/Dou-Yiming/hearing_hands/
UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
机构 * Department of Automation, Tsinghua University（自动化系，清华大学）
Comments Accepted to CVPR 2025
Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025
机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） ； Pengcheng Laboratory（鹏城实验室） ； Shandong Jianzhu University（山东建筑大学）
Comments The champion solution for the Ego4D Long-Term Action Anticipation Challenge at the CVPR EgoVis Workshop 2025
Question-Aware Gaussian Experts for Audio-Visual Question Answering
机构 * Sungkyunkwan University（成均馆大学） ； Purdue University（普渡大学）
Comments CVPR 2025. Code is available at https://github.com/AIM-SKKU/QA-TIGER
Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
机构 * State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统国家重点实验室） ； Tongyi Lab, Alibaba Group（阿里云实验室）
Comments 10 pages, 6 figures, CVPR 2025
Synthetic Human Action Video Data Generation with Pose Transfer
机构 * SSPS（社会学系） ； Stanford University（斯坦福大学）
Journal ref Synthetic Data for Computer Vision Workshop @ CVPR 2025
ScaleLSD: Scalable Deep Line Segment Detection Streamlined
机构 * Wuhan University（武汉大学） ； Ant Group（蚂蚁集团） ； NC State University（北卡罗来纳州立大学）
Comments accepted to CVPR 2025; 17 pages, appendices included
CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation
机构 * CFCS, School of Computer Science, Peking University（计算机学院，北京大学） ； PKU-Agibot Lab（北京大学Agibot实验室）
Comments CVPR 2025 Highlight
SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach
机构 * SEED, Electronic Arts（SEED电子艺术公司） ； Electronic Arts（电子艺术公司）
Comments Accepted to CVPR 2025 Human Motion Generation Workshop. 10 pages, 3 figures, 5 Tables, and 40 References
BG-HOP: A Bimanual Generative Hand-Object Prior
机构 * Carnegie Mellon University（卡内基梅隆大学）
Comments Presented at Agents in Interaction, from Humans to Robots, CVPR 2025
SmartEraser: Remove Anything from Images using Masked-Region Guidance
机构 * University of Science and Technology of China（中国科学技术大学） ； Microsoft Research Asia（微软亚洲研究院）
Comments Project at: https://longtaojiang.github.io/smarteraser.github.io/
Journal ref The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025
Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
机构 * École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院） ； Stanford University（斯坦福大学） ； ETH Zurich（苏黎世联邦理工学院）
Comments CVPR 2025
ORIDa: Object-centric Real-world Image Composition Dataset
机构 * Yonsei University（延世大学）
Comments Accepted at CVPR 2025
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
机构 * School of Software（软件学院） ； BNRist ； Department of Automation, Tsinghua University（自动化系，清华大学） ； Hangzhou Zhuoxi Institute of Brain and Intelligence（杭州卓溪脑科学与智能研究院） ； GRG Banking Equipment Co., Ltd.（GRG银行设备有限公司） ； South China University of Technology（华南理工大学）
Comments CVPR 2025
Open World Scene Graph Generation using Vision Language Models
Comments Accepted in CVPR 2025 Workshop (CVinW)
Zero-Shot Gaze-based Volumetric Medical Image Segmentation
机构 * Research Center of the Artificial Intelligence Institute（人工智能研究所研究中心）
Comments Accepted to MMFM-BIOMED Workshop @ CVPR 2025
SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models
机构 * Johns Hopkins University（约翰霍普金斯大学） ； DEVCOM Army Research Laboratory（国防部陆军研究实验室）
Comments CVPR 2025 highlight
Multimodal Rationales for Explainable Visual Question Answering
机构 * University of Twente（特文特大学） ； University of Bath（巴斯大学）
Comments Accepted to CVPR workshops 2025
Aligning Proteins and Language: A Foundation Model for Protein Retrieval
机构 * Carnegie Mellon University（卡内基梅隆大学） ； Purdue University（普渡大学）
Comments 4 pages for body, 3 pages for appendix, 11 figures. Accepted to CVPR 2025 Workshop on Multimodal Foundation Models for Biomedicine: Challenges and Opportunities(MMFM-BIOMED)
Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
机构 * Johns Hopkins Applied Physics Laboratory（约翰霍普金斯应用物理实验室） ； Johns Hopkins University（约翰霍普金斯大学） ； Human Language Technology Center of Excellence（人类语言技术卓越中心） ； DEVCOM Army Research Laboratory（陆军研究实验室）
Comments Accepted at CVPR 2025. 13 pages, 4 figures. Approved for public release: distribution unlimited
TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigation
机构 * George Mason University（乔治·马歇尔大学）
Comments Accepted to CVPR 2025 Workshop - Foundation Models Meet Embodied Agents
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
机构 * Snap Inc. ； Northeastern University（东北大学） ； Rutgers University（罗格斯大学）
Comments https://snap-research.github.io/snapgen-v/
Journal ref CVPR 2025
