作者位次 #4/6ACL 2026Findings· Findings of ACL
L ong I nsight B ench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding.
ZhaoYang Han · Qihan Lin · Hao Liang · Bowen Chen · Zhou Liu · Wentao Zhang
摘要
We introduce \textbf{LongInsightBench} , the first benchmark designed to assess models’ ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual, audio, and text} modalities. Our benchmark excels in thr...