AI 大模型

视频大模型

视频理解、视频生成、视频语言模型和时序视觉推理。

2025-09-10 至 2025-09-10 共收录 3 篇信号源：cs.CV, eess.IV, cs.MM

1. 视频理解 3 篇

2509.07680 2025-09-10 cs.CV cs.LG 70%

CAViAR: Critic-Augmented Video Agentic Reasoning

Sachit Menon, Ahmet Iscen, Arsha Nagrani, Tobias Weyand, Carl Vondrick, Cordelia Schmid

机构 * Google DeepMind（谷歌DeepMind）； Columbia University（哥伦比亚大学）

专题命中视频理解：video understanding(abstract)；video reasoning(abstract)；分类 cs.CV

2509.00969 2025-09-10 cs.CV 70%

Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors

Xiangchen Wang, Jinrui Zhang, Teng Wang, Haigang Zhang, Feng Zheng

机构 * Southern University of Science and Technology（南方科技大学）； The University of Hong Kong（香港大学）； Shenzhen Polytechnic University（深圳职业技术大学）

专题命中视频理解：video understanding(abstract)；video-language(abstract)；分类 cs.CV

Comments 17 pages, 8 figures, EMNLP2025

2507.02074 2025-09-10 cs.CV cs.AI 57%

Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges

Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma

机构 * Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学）； Department of Civil, Construction and Environmental Engineering, Iowa State University（土木、建设与环境工程系，爱荷华州立大学）

专题命中视频理解：video understanding(abstract)；分类 cs.CV