作者位次 #3/3ECCV 2026SpotlightHumanOmni-Speaker: Identifying Who said What and WhenDetao Bai · Xihan Wei · Zhiheng Ma多模态社会与人本Multimodal, Video & Document UnderstandingOpenReview
作者位次 #7/8ECCV 2026PosterVDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-ReflectionQiang Wang · XINYUAN GAO · SongLin Dong · Jizhou Han (Xi' · Jiangyang Li · Yuhang He · Zhiheng Ma · Yihong Gong多模态智能体与工具Video Understanding, Generation and Multimodal LearningOpenReview