List your company

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

0.395R@1VAB-Encodec
0.050760.140130.22950.31887Sep 27, 2024

Evaluation results

MethodLinks
VAB-EncodecDirection=Video -> Audio2024.090.3950.6540.746
VAB-DACDirection=Video -> Audio2024.090.3550.6180.724
ImageBindDirection=Video -> Audio2024.090.2210.4320.526
CAV-MAEDirection=Video -> Audio2024.090.1880.3950.501
LanguageBindDirection=Video -> Audio2024.090.0640.2020.283