From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning
从静态到动态:探索自监督图像到视频表示迁移学习
机构 * School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院) ; State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所人工智能安全国家重点实验室) ; Beijing Academy of Artificial Intelligence(北京人工智能研究院) ; Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) ; School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院) ; School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院)
AI总结 本文提出Co-Settle框架,通过轻量投影层调整表示空间,平衡视频内时间一致性和跨视频语义分离性,实验显示在多个视频任务上提升效果。
Comments Accepted at CVPR 2026