作者位次 #9/12ACL 2026Poster· Natural Language Processing
V ideo P ro: Adaptive Program Reasoning for Long Video Understanding
Chenglin Li · Feng Han · Yikun Wang · Ruilin Li · Shuai Dong · Haowen Hou · Haitao Li · Qianglong Chen · Feng Tao · Jingqi Tong · Yin Zhang · Jiaqi Wang
摘要
Understanding long videos remains challenging due to the sparsity of visual evidence relevant to a given query. Prior work has explored program-based visual grounding, typically relying on executable programs generated by auxiliary large language models. However, when scaling to long videos, exis...