Shih-Yao Lin

EARS: Evidence-Aware Retrieval via Sound and Motion for Budgeted Video Reasoning

Uniform frame sampling can miss brief evidence in sparse-event videos when the VLM sees only K frames. We propose EARS (Evidence-Aware Retrieval via Sound and motion), a training-free, query-free front-end that ranks frames using optical-flow motion and audio energy, then applies temporal non-maximum suppression for di...