ResearchDatasetsLV-VISFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsVideo Instance SegmentationLV-VIS30.3AP9Video Multimodal InterpretationLV-VIS (val)26AP6Video CaptioningLV-VIS19.3METEOR5Controllable Video SegmentationLV-VIS (test)87.8J&F Score3