ResearchBenchmarksCross-modal Retrieval (Audio to Image) on iNaturalist Species-level Retrieval seenCross-modal Retrieval (Audio to Image) on iNaturalist Species-level Retrieval seenFollow50.3Top-1 AccuracyBioVITA-2.001611.576725.15538.7333Mar 25, 2026Evaluation resultsMethodMethodLinksTop-1 AccuracyTop-5 AccuracyBioVITATraining Stage=Stage2Training Stage=Stage22026.0350.377.4BioVITATraining Stage=Stage1Training Stage=Stage12026.0347.872.8TaxaBind2026.0313.335.8ImageBind2026.031.88.7Random2026.030.010.05