Audio-to-Text Retrieval on EPIC-Sounds
50.3mAPAuroLA
Evaluation Results
| Method | Links | |
|---|---|---|
| AuroLAPre-training setting=Full AudioVerse training2026.02 | 50.3 | |
| AuroLAPre-training setting=PT2026.02 | 34.3 | |
| ReCLAPPre-training setting=Standard2026.02 | 32.5 | |
| PE-AVPre-training setting=PT2026.02 | 29.5 | |
| WavCapsPre-training setting=Standard2026.02 | 27.5 | |
| CLAP (fusion)Pre-training setting=Standard, Model Variant=Fusion2026.02 | 23.2 | |
| OnePeacePre-training setting=PT2026.02 | 19.2 | |
| VASTPre-training setting=PT2026.02 | 16.2 |