ResearchTasksText-to-Audio Retrieval (via Vision pivot)Text-to-Audio Retrieval (via Vision pivot)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAVE to MSRVTT (test)IB+BB34.1mAP12Feb 26, 2026