ResearchDatasetsVGGSound-AVELVGGSound-AVELFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsEvent Classification (V → A)VGGSound-AVEL 90K50.8Precision11Cross-modal classification (Audio to Visual)VGGSound-AVEL UCF to VGG 40K66.5Precision4Cross-dataset domain transfer (Visual to Audio)VGGSound-AVEL 40K AVE to AVVP56.3Segment-level F14