Cross-modal Retrieval (Video to Audio) on AudioSet Eval Subset
0.395R@1VAB-Encodec
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VAB-EncodecDirection=Video -> Audio2024.09 | 0.395 | 0.654 | 0.746 | |
| VAB-DACDirection=Video -> Audio2024.09 | 0.355 | 0.618 | 0.724 | |
| ImageBindDirection=Video -> Audio2024.09 | 0.221 | 0.432 | 0.526 | |
| CAV-MAEDirection=Video -> Audio2024.09 | 0.188 | 0.395 | 0.501 | |
| LanguageBindDirection=Video -> Audio2024.09 | 0.064 | 0.202 | 0.283 |