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. 视频扩散模型 3 篇

2509.05323 2025-09-10 cs.AI cs.MM 85%

Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArts

Adam Cole, Mick Grierson

机构 * University of the Arts London（伦敦艺术大学）

专题命中视频扩散模型：video diffusion(title,abstract)；video generation(abstract)；text-to-video(abstract)；分类 cs.MM

Comments 3rd international workshop on eXplainable AI for the Arts (XAIxArts) at the ACM Creativity and Cognition Conference June 2025

2509.07484 2025-09-10 cs.CV 83%

LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors

Wenshuo Gao, Xicheng Lan, Luyao Zhang, Shuai Yang

机构 * Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, \ University, Beijing, China ； Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China

专题命中视频扩散模型：video diffusion(title,abstract)；text-to-video(abstract)；分类 cs.CV

Comments 5 pages, ICIPW 2025, Website: https://gaowenshuo.github.io/LINR-bridge/

2509.07472 2025-09-10 cs.CV 70%

ANYPORTAL: Zero-Shot Consistent Video Background Replacement

Wenshuo Gao, Xicheng Lan, Shuai Yang

机构 * Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China（王轩计算机技术研究所，多媒体信息处理国家重点实验室，北京大学，北京）

专题命中视频扩散模型：video generation(abstract)；video diffusion(abstract)；分类 cs.CV

Comments 8 pages, ICCV 2025, Website: https://gaowenshuo.github.io/AnyPortal/