Audio-to-Vision Retrieval on AudioSet Eval
37.5Recall@1VAB-Encodec
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VAB-EncodecEvaluation Protocol=Fine-tuned2026.04 | 37.5 | 64 | 73.7 | |
| TG-DPEvaluation Protocol=Zero-shot2026.04 | 37.1 | 59.7 | 68.2 | |
| CAV-MAE SyncEvaluation Protocol=Zero-shot2026.04 | 27.9 | 52.4 | 62.2 | |
| ImageBindEvaluation Protocol=Zero-shot2026.04 | 20.8 | 42.6 | 51.6 | |
| DenseAVEvaluation Protocol=Zero-shot2026.04 | 20.8 | 42.6 | 51.6 | |
| AVSiamEvaluation Protocol=Zero-shot2026.04 | 17.6 | — | — | |
| CAV-MAE Scale+++Evaluation Protocol=Zero-shot2026.04 | 15.1 | 34 | 43 | |
| CAV-MAEEvaluation Protocol=Zero-shot2026.04 | 9.5 | 22.6 | 32.4 | |
| LanguageBindEvaluation Protocol=Zero-shot2026.04 | 4.4 | 15 | 22.5 |