ResearchDatasetsAVISegFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAudio-Visual Sound SegmentationAVISeg (test)44.12FSLA12Audio-Visual Instance SegmentationAVISeg54.65FSLA8Video Instance SegmentationAVISeg (test)42.78FSLA7Audio-referred visual groundingAVISeg (test)18.55FSLA4