ResearchTasksAudio-visual event recognitionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAVE (test)MaxSim71.64AV Accuracy20Jun 11, 2026Kinetics-Sounds (test)ExFMem72.71AV Score14Feb 26, 2026MIT-MUSIC (test)MinSim91.35AV Accuracy14Feb 26, 2026