ResearchTasksOverall Audio-Visual Question AnsweringOverall Audio-Visual Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMUSIC-AVQA (test)Spatio-Temporal Grounded Audio-Visual Network71.52Overall Accuracy21Feb 26, 2026