arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision

2026-06-08 至 2026-06-08 共收录 10
2606.06534 2026-06-08 eess.IV cs.AI 新提交

Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foundation Models

基于视觉基础模型的注意力一致纵向医学视觉问答

Jialin Wu, Qianru Zhang, Georges El Fakhri, Xiaofeng Liu

机构 * University of California, San Diego(加州大学圣地亚哥分校) Yale Biomedical Imaging Institute(耶鲁大学生物医学成像研究所)

AI总结 提出一种注意力引导的编码器-解码器框架,通过轻量级配准和自适应掩码生成,结合辅助损失函数,实现胸部X光片的纵向医学视觉问答,在Medical-Diff-VQA基准上取得优异性能。

Comments Accepted to CVPR 2026 Workshop PHAROS-AIF-MIH

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026, pp. 6448-6458

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.07503 2026-06-08 cs.CV 新提交

Differences in Detection: Explainability Where it Matters

检测中的差异:可解释性在关键之处

Johannes Theodoridis, Johannes Maucher, Andreas Schilling

机构 * University of Tübingen(图宾根大学) Institute for Applied AI(应用人工智能研究所) Hochschule der Medien Stuttgart(斯图加特媒体大学)

AI总结 提出DnD方法,通过匹配算法直接比较两个目标检测模型,揭示个体与共享错误,并引导可解释性方法聚焦于度量相关示例。

Comments Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2026 - How Do Vision Models Work? (HOW)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.07288 2026-06-08 cs.CV cs.GR 新提交

ExMesh: EXplicit Mesh Reconstruction with Topology Adaptation

ExMesh: 具有拓扑自适应的显式网格重建

Chuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang, Wenfei Yang, Tianzhu Zhang

机构 * University of Science and Technology of China(中国科学技术大学) National Key Laboratory of Deep Space Exploration, Deep Space Exploration Laboratory(国家空间科学探测重点实验室,深空探测实验室)

AI总结 提出ExMesh框架,通过可微优化与离散拓扑更新直接优化显式网格,引入自适应顶点分裂合并和实时UV维护,实现从粗到细的优化,兼顾精度、效率和网格简洁性。

Comments Accepted at the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.07280 2026-06-08 cs.CV 新提交

Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation

几何感知超图推理用于点云分割中的新类别发现

Zihao Zhang, Aming Wu, Yang Li, Yahong Han, Jialie Shen

机构 * School of Artificial Intelligence, College of Intelligence and Computing, Tianjin University(人工智能学院、智能计算学院、天津大学) School of Computer Science and Information Engineering, Hefei University of Technology(计算机科学与信息工程学院、合肥工业大学) Department of Computer Science City St George’s, University of London(伦敦大学城市圣乔治学院计算机科学系)

AI总结 提出超图框架建模高阶关联,结合几何感知原型,实现点云分割中从已知到新类别的协同推理,提升分割精度。

Comments Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06853 2026-06-08 cs.CV cs.AI 新提交

MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models

MotionEnhancer: 利用视频扩散模型增强运动感知的视觉-语言模型

Yifan Xu, Chao Zhang, Ruifei Ma, Fei Gao, Zhifei Yang, Jiaxing Qi, Zhipeng Chen

机构 * School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院) Beijing Digital Native Digital City Research Center(北京数字原生数字城研究中心) School of Computer Science, Peking University(北京大学计算机学院) School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)

AI总结 提出MotionEnhancer,通过从视频扩散模型中提取运动先验并利用注意力对齐增强视觉-语言模型的运动理解能力,无需额外参数或架构修改,在运动级视频理解基准上取得一致提升。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06048 2026-06-08 cs.CV 版本更新

LLM-Conditioned Synthesis of Pathological Gaits via Structured Gait-Language Representations

基于结构化步态-语言表示的LLM条件病理步态合成

Mritula Chandrasekaran, Sanket Kachole, Jarek Francik, Dimitrios Makris

机构 * University of California, Berkeley(加州大学伯克利分校) Stanford University(斯坦福大学) University of Toronto(多伦多大学) MIT Media Lab(麻省理工学院媒体实验室)

AI总结 提出一种多模态LLM引导框架,通过结构化文本描述合成病理步态3D数据,利用运动标记化、病理感知语言条件、LLM语义增强和语言到步态生成,改善下游分类性能。

Comments Accepted at CVPR MOMA Workshop 2026 and selected for spotlight presentation at the workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05360 2026-06-08 cs.HC cs.AI 版本更新

OGA-AID: Clinician-in-the-loop AI Report Drafting Assistant for Multimodal Observational Gait Analysis in Post-Stroke Rehabilitation

OGA-AID:用于中风后康复多模态观察性步态分析的临床医生在环AI报告起草助手

Khoi T. N. Nguyen, Nghia D. Nguyen, Hui Yu Koh, Patrick W. H. Kwong, Karen Sui Geok Chua, Ananda Sidarta, Baosheng Yu

机构 * Rehabilitation Research Institute of Singapore, Nanyang Technological University, Singapore(新加坡康复研究中心,南洋理工大学,新加坡) Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore(李光前医学院,南洋理工大学,新加坡) The Grainger College of Engineering, University of Illinois Urbana-Champaign, United States(伊利诺伊大学厄巴纳-香槟分校格雷格学院,美国) Department of Rehabilitation Sciences, The Hong Kong Polytechnic University, Hong Kong(香港理工大学康复科学系,香港) VinUni-Illinois Smart Health Center, VinUniversity, Vietnam(Vin大学Vin-伊利诺伊智能健康中心,越南) Institute of Rehabilitation Excellence, Tan Tock Seng Hospital, NHG Health, Singapore(卓越康复研究所,坦托克桑格医院,NHG健康,新加坡)

AI总结 提出OGA-AID,一种临床医生在环的多智能体大语言模型系统,通过协调三个专业智能体合成患者运动记录、运动学轨迹和临床资料,生成结构化步态评估报告,在真实患者数据上优于单次多模态基线,并展示了AI辅助分析与人类临床判断的互补关系。

Comments 2026 CV4Clinic CVPR Workshop Proceedings

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19888 2026-06-08 cs.LG

Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations

基于正交变换的联邦学习与个性化方法:通过黑盒基础模型

Eun Gyung Kong, Je Won Yeom, Yonghoon Jeon, Taesup Kim

机构 * Seoul National University(首尔国立大学) Mobilint, Inc.(Mobilint公司) Kakao Healthcare Corp.(Kakao医疗公司)

AI总结 本文提出FedOT框架,通过正交变换实现联邦学习中的鲁棒泛化与有效个性化,在异构环境中提升性能,优于基线方法。

Comments 31 pages, 5 figures

Journal ref Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24567-24576, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12795 2026-06-08 cs.RO 版本更新

ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model

ActiveGrasp: 基于校准能量模型的信息引导主动抓取

Boshu Lei, Wen Jiang, Kostas Daniilidis

机构 * University of Pennsylvania(宾夕法尼亚大学) Archimedes, Athena RC(阿基米德、阿提卡RC)

AI总结 针对密集杂乱环境中的抓取问题,提出一种校准能量模型生成抓取姿态,并基于抓取分布的信息增益主动选择视角,在有限视角下高效抓取目标物体。

Comments CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.00636 2026-06-08 cs.CV 版本更新

T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences

T2LM:基于多句子的长期3D人体运动生成

Taeryung Lee, Fabien Baradel, Thomas Lucas, Kyoung Mu Lee, Gregory Rogez

机构 * IPAI & ASRI(IPAI与ASRI) Dept. of ECE, Seoul National University(电子工程系,首尔国立大学) NAVER LABS Europe(NAVER欧洲实验室)

AI总结 提出T2LM框架,利用1D卷积VQVAE和Transformer文本编码器,无需顺序数据即可从多句子生成连续长期3D人体运动,优于先前方法且与单动作SOTA竞争。

Comments CVPR 2024 HuMoGen Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏