arXivDaily arXiv每日学术速递 周一至周五更新

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。

2025-08-04 至 2025-08-04 共收录 7 信号源:cs.CV, eess.IV, cs.MM

1. 视频生成 3 篇

2508.00312 2025-08-04 cs.CV cs.AI 79%

GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection

Suhang Cai, Xiaohao Peng, Chong Wang, Xiaojie Cai, Jiangbo Qian

机构 * China Telecom Corporation Limited Wenzhou Branch(中国电信有限公司温州支公司) Faculty of Electrical Engineering and Computer Science, Ningbo University(宁波大学电子工程与计算机科学学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00397 2025-08-04 cs.CV 70%

Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency

Xi Xue, Kunio Suzuki, Nabarun Goswami, Takuya Shintate

机构 * NABLAS Inc.(NABLAS公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00299 2025-08-04 cs.CV cs.AI cs.RO 57%

Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence

Danzhen Fu, Jiagao Hu, Daiguo Zhou, Fei Wang, Zepeng Wang, Wenhua Liao

机构 * MiLM Plus, Xiaomi Inc.(小米公司)

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

Comments ICCV 2025 Workshop (HiGen)

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 视频扩散模型 1 篇

2508.00289 2025-08-04 cs.CV 88%

TITAN-Guide: Taming Inference-Time AligNment for Guided Text-to-Video Diffusion Models

Christian Simon, Masato Ishii, Akio Hayakawa, Zhi Zhong, Shusuke Takahashi, Takashi Shibuya, Yuki Mitsufuji

机构 * Sony Group Corporation(索尼集团公司) Sony AI(索尼人工智能)

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

Comments Accepted to ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 动作与事件理解 2 篇

2507.19924 2025-08-04 cs.CV 70%

HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly

Chang Liu, Yunfan Ye, Fan Zhang, Qingyang Zhou, Yuchuan Luo, Zhiping Cai

机构 * National University of Defense Technology(国防科技大学) Hunan University(湖南大学)

专题命中 动作与事件理解 :video generation(abstract);video understanding(abstract);分类 cs.CV

Comments ICCV 2025. Project page: https://dejian-lc.github.io/humansam/

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00795 2025-08-04 cs.RO 50%

Video Generators are Robot Policies

Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Sruthi Sudhakar, Paarth Shah, Rares Ambrus, Carl Vondrick

机构 * Columbia University(哥伦比亚大学) Toyota Research Institute(丰田研究院)

专题命中 动作与事件理解 :video generation(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 视频数据与评测 1 篇

2508.00144 2025-08-04 cs.CV 79%

World Consistency Score: A Unified Metric for Video Generation Quality

Akshat Rakheja, Aarsh Ashdhir, Aryan Bhattacharjee, Vanshika Sharma

机构 * Equal contribution(共同贡献)

专题命中 视频数据与评测 :video generation(title,abstract);分类 cs.CV

Comments 27 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏