Audio-to-Text Retrieval on HD-EPIC
32.2mAPAuroLA
Evaluation Results
| Method | Links | |
|---|---|---|
| AuroLAPre-training setting=Full AudioVerse training2026.02 | 32.2 | |
| AuroLAPre-training setting=PT2026.02 | 27.8 | |
| ReCLAPPre-training setting=Standard2026.02 | 26.6 | |
| PE-AVPre-training setting=PT2026.02 | 23.8 | |
| CLAP (fusion)Pre-training setting=Standard, Model Variant=Fusion2026.02 | 20 | |
| WavCapsPre-training setting=Standard2026.02 | 19.1 | |
| OnePeacePre-training setting=PT2026.02 | 17.6 | |
| VASTPre-training setting=PT2026.02 | 15.7 |