作者位次 #6/11ACL 2026Poster· Natural Language Processing
R esponse- G 1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Ke Ma · Jiaqi Tang · Bin Guo · Xueting Han · Ruonan Xu · Qingfeng He · Ziheng Wang · Xu Wang · Qifeng Chen · Zhiwen Yu · Yunhao Liu
摘要
Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce Response-G1, a novel framework that establishes explicit, struct...