ResearchTasksAudio-to-Text Retrieval (via Vision pivot)FollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMSRVTT to AVE (test)LB+BB29.2mAP6Feb 26, 2026AVE to MSRVTT (test)IB+BB35.3mAP6Feb 26, 2026