作者位次 #2/5ACL 2026Findings· Findings of ACL
A rrow GEV : Grounding Events in Video via Learning the Arrow of Time
Fangxu Yu · Ziyao Lu · Liqiang Niu · Fandong Meng · Jie Zhou
摘要
Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches predominantly train models to associate events with timestamps in the forward video only. This paradigm hinders VLMs fr...