Audio-to-text Retrieval on Clotho V2 (test)
18.78Recall@1WavCaps
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| WavCapsCategory=BM2025.11 | 18.78 | 45.15 | 57.72 | 40.55 | — | |
| CACARA_WC/AC/C/f 0.2Category=CACARA, f-value=0.22025.11 | 17.26 | 40.91 | 53.85 | 37.34 | — | |
| LanguageBindCategory=MM2025.11 | 16.11 | 41.07 | 53.05 | 36.74 | — | |
| MixProLAPZero-shot=true, Training Dataset=ClothoV22026.06 | 15.6 | — | 46.51 | — | 11.19 | |
| CLAP (Microsoft)Category=BM2025.11 | 15.46 | 38.74 | 51.52 | 35.24 | — | |
| CACARA_WC/AC/C/f 0.1Category=CACARA, f-value=0.12025.11 | 15.38 | 37.4 | 49.63 | 34.13 | — | |
| CLAP (LAION)Category=BM2025.11 | 14.64 | 37.28 | 49.68 | 33.87 | — | |
| CACARA_AA/WC/AC/CCategory=CACARA2025.11 | 14.42 | 37.21 | 49.95 | 33.86 | — | |
| CACARA_WC/AC/CCategory=CACARA2025.11 | 14.39 | 35.87 | 48.08 | 32.78 | — | |
| MixProLAPZero-shot=true, Training Dataset=AudioCaps2026.06 | 14.26 | — | 46.89 | — | 9.96 | |
| CLAPZero-shot=true, Training Dataset=ClothoV22026.06 | 13.4 | — | 41.72 | — | 9.65 | |
| CACARA_ASC/AA/WC/AC/C/f 0.2Category=CACARA, f-value=0.22025.11 | 13.21 | 33.63 | 45.67 | 30.84 | — | |
| CACARA_ASC/AA/WC/AC/C/f 0.1Category=CACARA, f-value=0.12025.11 | 13.04 | 33.53 | 46 | 30.86 | — | |
| CLAPZero-shot=true, Training Dataset=AudioCaps2026.06 | 11.67 | — | 36.36 | — | 8.36 | |
| CACARA_ASC/AA/WC/AC/CCategory=CACARA2025.11 | 11.4 | 29.82 | 41.12 | 27.45 | — | |
| VASTCategory=MM2025.11 | 11.02 | 26.64 | 35.48 | 24.38 | — | |
| ImageBindCategory=MM2025.11 | 5.11 | 16.17 | 24.96 | 15.41 | — |