List your company

Cross-modal Retrieval (Audio to Video) on VGGSound Eval Subset

34.9Recall@1VAB-Encodec
5.36413.03220.728.368Sep 27, 2024

Evaluation results

MethodLinks
VAB-EncodecDirection=Audio -> Video2024.0934.962.773.1
VAB-DACDirection=Audio -> Video2024.0933.162.773.8
ImageBindDirection=Audio -> Video2024.0920.743.253.4
CAV-MAEDirection=Audio -> Video2024.0912.830.440.3
LanguageBindDirection=Audio -> Video2024.096.522.733.5