Cross-modal Retrieval (Audio to Video) on VGGSound Eval Subset
34.9Recall@1VAB-Encodec
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VAB-EncodecDirection=Audio -> Video2024.09 | 34.9 | 62.7 | 73.1 | |
| VAB-DACDirection=Audio -> Video2024.09 | 33.1 | 62.7 | 73.8 | |
| ImageBindDirection=Audio -> Video2024.09 | 20.7 | 43.2 | 53.4 | |
| CAV-MAEDirection=Audio -> Video2024.09 | 12.8 | 30.4 | 40.3 | |
| LanguageBindDirection=Audio -> Video2024.09 | 6.5 | 22.7 | 33.5 |