作者位次 #4/8ACL 2026Poster· Natural Language Processing
Agentic Very Long Video Understanding
Aniket Rege · Arka Sadhu · Yuliang Li · Kejie Li · Ramya Korlakai Vinayak · Yuning Chai · Yong Jae Lee · Hyo Jin Kim
摘要
The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding—one that goes beyond short, isolated events to encompass the continuous, longitudinal stream of egocentric video. Achieving this vision requir...