一作CVPR 2026Poster· Computer Vision & Pattern Recognition
Prototypical Action Reasoning Facilitated by Vision-Language Alignment for Egocentric Action Anticipation
Jiang Shao · Xinbo Zhao · Wenyin Tuo · Xiaochun Zou
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Jiang Shao · Xinbo Zhao · Wenyin Tuo · Xiaochun Zou
Kun Wang · an Jiaotong University) · Hao Liu · Jiang Shao · an Jiaotong University)
Video Moment Retrieval (VMR) aims to retrieve temporal moments in videos that align with natural language queries, a task requiring cross-modal reasoning between video and text. Among various supervision paradigms, point-supervised VMR has emerged as a practical solution, leveraging single-frame...