ResearchTasksCross-modal Vision-Language RetrievalCross-modal Vision-Language RetrievalFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedPitts30La-BLIP50.2R@18Feb 26, 2026MSLS (val)La-CLIP38R@18Feb 26, 2026AmstertimeLa-SigLIP-V213.8R@18Feb 26, 2026