List your company

Vision-to-Audio Retrieval on AudioSet Eval

39.5Recall@1VAB-Encodec
5.07614.01322.9531.887Apr 9, 2026

Evaluation results

MethodLinks
VAB-EncodecEvaluation Protocol=Fine-tuned2026.0439.565.474.6
TG-DPEvaluation Protocol=Zero-shot2026.0437.459.268.1
CAV-MAE SyncEvaluation Protocol=Zero-shot2026.0435.258.367.6
DenseAVEvaluation Protocol=Zero-shot2026.0426.349.958.5
ImageBindEvaluation Protocol=Zero-shot2026.0422.143.252.6
AVSiamEvaluation Protocol=Zero-shot2026.0419.7——
CAV-MAE Scale+++Evaluation Protocol=Zero-shot2026.0418.839.550.1
CAV-MAEEvaluation Protocol=Zero-shot2026.0416.138.649.3
LanguageBindEvaluation Protocol=Zero-shot2026.046.420.228.3