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。

2025-10-21 至 2025-10-21 共收录 8 篇信号源：cs.CV, eess.IV, cs.MM

1. 视频理解 2 篇

2506.22967 2025-10-21 cs.CV cs.LG cs.MM 73%

ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment

Amir Aghdam, Vincent Tao Hu, Björn Ommer

机构 * Department of Computer Science, Temple University（Temple大学计算机科学系）； Munich Center for Machine Learning（慕尼黑机器学习中心）

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

Comments Accepted to TMLR 2025 - Project page: https://amir-aghdam.github.io/act-align/

2510.16209 2025-10-21 cs.CV 57%

StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales

Nyle Siddiqui, Rohit Gupta, Sirnam Swetha, Mubarak Shah

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

2. 视频生成 3 篇

2510.16833 2025-10-21 cs.CV cs.GR 79%

From Mannequin to Human: A Pose-Aware and Identity-Preserving Video Generation Framework for Lifelike Clothing Display

Xiangyu Mu, Dongliang Zhou, Jie Hou, Haijun Zhang, Weili Guan

机构 * Harbin Institute of Technology（哈尔滨工业大学）

专题命中视频生成：video generation(title,abstract)；分类 cs.CV

2510.14588 2025-10-21 cs.CV cs.AI 79%

STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding

Zhifei Chen, Tianshuo Xu, Leyi Wu, Luozhou Wang, Dongyu Yan, Zihan You, Wenting Luo, Guo Zhang, Yingcong Chen

机构 * HKUST(GZ)（香港科技大学（珠海））； HKUST（香港科技大学）； XMU（厦门大学）； MIT（麻省理工学院）

专题命中视频生成：video generation(title,abstract)；分类 cs.CV

Comments Code, model, and demos can be found at https://envision-research.github.io/STANCE/

2411.17041 2025-10-21 cs.CV cs.AI cs.LG 79%

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM

Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye

机构 * Graduate School of AI, KAIST（人工智能研究生院，韩国科学技术院）

专题命中视频生成：text-to-video(title,abstract)；分类 cs.CV

Comments ICCV 2025 accepted

3. 视频扩散模型 2 篇

2510.15874 2025-10-21 cs.GR 82%

Sketch-based Fluid Video Generation Using Motion-Guided Diffusion Models in Still Landscape Images

Hao Jin, Haoran Xie

专题命中视频扩散模型：video generation(title,abstract)；video diffusion(abstract)

Comments 2 pages, 5 figures. SIGGRAPH 2025 Poster

2502.03621 2025-10-21 cs.CV 70%

DynVFX: Augmenting Real Videos with Dynamic Content

Danah Yatim, Rafail Fridman, Omer Bar-Tal, Tali Dekel

机构 * Weizmann Institute of Science（魏兹曼科学研究所）

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

Comments Project page: https://dynvfx.github.io

4. 视频问答 1 篇

2510.17364 2025-10-21 cs.CV cs.LG 57%

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs

Vaggelis Dorovatas, Soroush Seifi, Gunshi Gupta, Rahaf Aljundi

机构 * Toyota Motor Europe（丰田欧洲公司）； Archimedes RU, Athena RC（阿奇米德 RU、阿泰纳 RC）； University of Oxford（牛津大学）

专题命中视频问答：long video(abstract)；分类 cs.CV

Comments NeurIPS 2025