Paper summary
Paper summary: OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
OmniCompass is a manually annotated benchmark for video grounding and understanding, with a vision track and an audio-visual track (when, where and what); across 50 MLLMs, the best scores are only around 40%.
- Each track tests three questions: when does the target appear (temporal grounding), where is it (spatial grounding), and what happens (QA).
- Even the best models score about 40% on the vision track.