ResearchDatasetsViCaSViCaSFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLanguage-Guided Video Instance SegmentationViCaS (val)16.5mAP4Language-Guided Video Instance SegmentationViCaS 1.0 (val)20.5mAP4Video CaptioningViCaS (val)3CA3Video CaptioningViCaS 1.0 (val)3CA3