作者位次 #5/7SIGIR 2026Oral· Information Retrieval (Full)
Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
Houlun Chen · Xin WANG · Guangyao Li · Yuwei Zhou · Yihan Chen · Jia Jia · Wenwu Zhu
摘要
Long video understanding (LVU) is challenging due to rich and complicated multimodal clues in long temporal range. Current methods adopt reasoning to improve the model's ability to analyze complex video clues in long videos via text-form reasoning. However, the existing literature suffers from th...