Cross-modal Retrieval (Audio to Video) on AudioSet Eval Subset
37.5R@1VAB-Encodec
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VAB-EncodecDirection=Audio -> Video2024.09 | 37.5 | 64 | 73.7 | |
| VAB-DACDirection=Audio -> Video2024.09 | 37 | 61.8 | 70.8 | |
| ImageBindDirection=Audio -> Video2024.09 | 20.8 | 42.6 | 51.6 | |
| CAV-MAEDirection=Audio -> Video2024.09 | 15.1 | 34 | 43 | |
| LanguageBindDirection=Audio -> Video2024.09 | 4.4 | 15 | 22.5 |