ResearchDatasetsVIPVIPFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsVideo Part SegmentationVIP0.408mIoU48Video Instance ParsingVIP (val)39.7mIoU20Human Part PropagationVIP (val)41mIoU12Identity-Preserving Text-to-Video GenerationVIP-200K (test)0.631FaceSim-Arc10Spatial TasksVIP40.6mIoU9Video Instance ParsingVIP38.4mIoU6Instance Segmentation PropagationVIP0.241APvol5Semantic Segmentation PropagationVIP37.9mIoU5