Audio-to-Text Retrieval on VALOR
35.1Recall@1PE-AV
Evaluation Results
| Method | Links | |
|---|---|---|
| PE-AVModel category=Audio-visual-text model2026.02 | 35.1 | |
| AuroLAModel category=Audio-text model2026.02 | 14.4 | |
| AFlamingo2Model category=Audio-text model2026.02 | 7.3 | |
| LanguageBindModel category=Audio-visual-text model2026.02 | 6.5 | |
| M2D-CLAPModel category=Audio-text model2026.02 | 6.3 | |
| MS-CLAPModel category=Audio-text model2026.02 | 5.9 | |
| CLAPModel category=Audio-text model2026.02 | 5.8 | |
| CLAP (fusion)Model category=Audio-text model2026.02 | 5.5 | |
| ImageBindModel category=Audio-visual-text model2026.02 | 5.4 |