Text-to-Audio Retrieval on HD-EPIC
10.7mAPAuroLA
Evaluation Results
| Method | Links | |
|---|---|---|
| AuroLAPre-training setting=Full AudioVerse training2026.02 | 10.7 | |
| ReCLAPPre-training setting=Standard2026.02 | 9.8 | |
| WavCapsPre-training setting=Standard2026.02 | 9.8 | |
| AuroLAPre-training setting=PT2026.02 | 9.5 | |
| VASTPre-training setting=PT2026.02 | 7.2 | |
| CLAP (fusion)Pre-training setting=Standard, Model Variant=Fusion2026.02 | 6.5 | |
| PE-AVPre-training setting=PT2026.02 | 5.9 | |
| OnePeacePre-training setting=PT2026.02 | 5.8 |