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

2026-08-04 至 2026-08-04 共收录 7
2608.01794 2026-08-04 cs.CV cs.AI cs.CL 新提交

Illuminating Visual Identity in Universal Multimodal Embeddings

揭示通用多模态嵌入中的视觉身份

Jiawei Cao, Junyi Feng, Jiashen Hua, Ziheng Huang, Bing Deng, Kaijie Wu, Chaochen Gu, Jieping Ye

机构 * Shanghai Jiao Tong University(上海交通大学) Alibaba Group(阿里巴巴集团)

AI总结 该研究针对通用多模态嵌入缺乏视觉身份判别能力的问题,提出视觉身份判别统一形式化,构建MVEB基准,设计身份感知采样的学习框架,提升了UMEs的身份判别能力。

Comments Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.01730 2026-08-04 cs.CV 新提交

Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency

学习关注何处与如何判断:具备质量感知显著性的分辨率无关图像质量评估

Hakan Emre Gedik, Shashank Gupta, Alan Bovik

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Colorado Boulder(科罗拉多大学博尔德分校)

AI总结 提出基于CLIP的多尺度补丁驱动模型ReLIQS,解决无参考图像质量评估的分辨率适配、计算效率等问题,在多类基准上泛化能力优于主流基线且成本相当或更低。

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
2608.00356 2026-08-04 cs.CV 新提交

The 1st AI Children Challenge

第一届AI儿童挑战赛

Boyi Li, Yifan Shen, Houze Yang, Xu Cao, Guojun Yun, Li Gao, Turong Chen, Long Xu, Jianguo Cao, Meihuan Huang

机构 * PediaMed AI University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) The Hong Kong Polytechnic University(香港理工大学)

AI总结 该第一届AI儿童挑战赛推出儿童步态视觉分析赛道,设EVGS评分、脑瘫步态模式分类任务,提供对应数据集与真值以推动AI在儿童医疗领域的应用。

Journal ref In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5564-5570. 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05372 2026-08-04 cs.CV cs.AI

Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models

两步即可:基于一致性模型的高效3D点云异常检测

Pranav A, Shashank B, Pranav Siddappa, Dominik Seuss, Minal Moharir, Subramanya KN

机构 * R.V. College of Engineering(R.V. 工程学院) Technical University of Applied Sciences Würzburg-Schweinfurt(Würzburg-Schweinfurt 应用科学大学)

AI总结 本文提出基于一致性学习的重建异常检测方法,通过简化推理过程提升效率,实现低延迟的3D点云异常检测,适用于资源受限设备。

Comments Accepted to CVPR 2026, at the 9th Workshop on Efficient Deep Learning for Computer Vision (ECV). To be published in the IEEE/CVF CVPR 2026 Workshop Proceedings

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026, pp. 3479-3487

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.00086 2026-08-04 cs.CV cs.AI cs.CL cs.LG 版本更新

Hierarchical Pre-Training of Vision Encoders with Large Language Model

基于大语言模型的视觉编码器分层预训练

Eugene Lee, Ting-Yu Chang, Jui-Huang Tsai, Jiajie Diao, Chen-Yi Lee

机构 * University of Cincinnati(辛辛那提大学) National Yang Ming Chiao Tung University(国立阳明交通大学)

AI总结 本文提出HIVE框架,通过引入视觉编码器与大语言模型间的分层交叉注意力机制,提升视觉语言对齐,改进特征融合与表征学习,实验表明其在图像分类和多模态任务中表现优异。

Comments 17 pages, 14 figures, accepted to Computer Vision and Pattern Recognition Conference (CVPR) Workshops 2026. 5th MMFM Workshop: What is Next in Multimodal Foundation Models?

Journal ref In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7415-7424) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.26775 2026-08-04 cs.LG cs.AI cs.CL cs.CV

Learning to Select Visual In-Context Demonstrations

学习选择视觉上下文示例

Eugene Lee, Yu-Chi Lin, Jiajie Diao

机构 * University of Cincinnati(辛辛那提大学) University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

AI总结 本文提出LSD方法,通过强化学习构建最优演示集,提升多模态大语言模型在视觉回归任务中的表现,揭示了学习选择在视觉上下文学习中的必要性。

Comments 21 pages, 12 figure, accepted to Computer Vision and Pattern Recognition Conference (CVPR) 2026 Findings Track

Journal ref In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9455-9465) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.02457 2026-08-04 cs.CV 版本更新

PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding

PatchAlign3D: 本地特征对齐用于密集3D形状理解

Souhail Hadgi, Bingchen Gong, Ramana Sundararaman, Emery Pierson, Lei Li, Peter Wonka, Maks Ovsjanikov

机构 * École polytechnique(巴黎政治学院) University of Virginia(弗吉尼亚大学) KAUST(王国立阿联酋科技大学)

AI总结 PatchAlign3D通过点云直接生成语言对齐的片段特征,实现高效零样本3D部分分割,优于传统渲染方法。

Comments CVPR 2026. Project website: https://souhail-hadgi.github.io/patchalign3dsite/

详情

展开后加载摘要…

URL PDF HTML 收藏