ResearchTasksVideo Multimodal InterpretationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOVIS (val)SG-FSCFormer28.7AP7Mar 24, 2026LV-VIS (val)SG-FSCFormer26AP6Mar 24, 2026