ResearchDatasetsAVUTAVUTFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAudio-Visual UnderstandingAVUT AV-Human0.783Accuracy12Audio-Visual UnderstandingAVUT85.6Score8Audio-Visual QAAVUT66.57Accuracy6Omni-modal UnderstandingAVUT-Human78.6Overall Score3