ICCV - arXivDaily 期刊&会议

2412.17812 2025-08-04 cs.CV cs.GR

FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads

Weijie Lyu, Yi Zhou, Ming-Hsuan Yang, Zhixin Shu

机构 * University of California, Merced（加州大学梅尔塞德斯分校）； Adobe Research（Adobe研究）

Comments ICCV 2025 Camera-Ready Version. Project Page: https://weijielyu.github.io/FaceLift

2412.13180 2025-08-04 cs.CV

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

Mark Endo, Xiaohan Wang, Serena Yeung-Levy

机构 * Stanford University（斯坦福大学）

Comments ICCV 2025, project page: https://web.stanford.edu/~markendo/projects/feather

2412.05101 2025-08-04 cs.CV

The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation

Ruoyu Wang, Huayang Huang, Ye Zhu, Olga Russakovsky, Yu Wu

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院）； Department of Computer Science, Princeton University（普林斯顿大学计算机科学系）

Comments ICCV 2025 Highlight

2412.02837 2025-08-04 cs.CV

$\texttt{BATCLIP}$: Bimodal Online Test-Time Adaptation for CLIP

Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky, Rogerio Feris, Yunhui Guo

机构 * The University of Texas at Dallas（德克萨斯大学达拉斯分校）； MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室）

Comments ICCV 2025

2411.13587 2025-08-04 cs.RO cs.AI

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Taowen Wang, Cheng Han, James Chenhao Liang, Wenhao Yang, Dongfang Liu, Luna Xinyu Zhang, Qifan Wang, Jiebo Luo, Ruixiang Tang

机构 * Rochester Institute of Technology（罗切斯特技术研究所）； University of Missouri - Kansas City（密苏里大学-凯撒城分校）； U.S. Naval Research Laboratory（美国海军研究实验室）； Lamar University（拉马尔大学）； Meta AI ； University of Rochester（罗切斯特大学）； Rutgers University（新泽西罗格斯大学）

Comments ICCV camera ready; Github: https://github.com/William-wAng618/roboticAttack Homepage: https://vlaattacker.github.io/

2411.10086 2025-08-04 cs.CV

CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation

Dengke Zhang, Fagui Liu, Quan Tang

机构 * South China University of Technology（南方科技大学）； Pengcheng Laboratory（鹏城实验室）

Comments Accepted to ICCV 2025 Oral

2406.08451 2025-08-04 cs.CV

GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices

Quanfeng Lu, Wenqi Shao, Zitao Liu, Lingxiao Du, Fanqing Meng, Boxuan Li, Botong Chen, Siyuan Huang, Kaipeng Zhang, Ping Luo

机构 * Shanghai AI Laboratory（上海人工智能实验室）； The University of Hong Kong（香港大学）； Nanjing University（南京大学）； Shanghai Jiao Tong University（上海交通大学）； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））

Comments 22 pages, 14 figures, ICCV 2025, a cross-app GUI navigation dataset