Text-to-audio Retrieval on Clotho V2 (test)
16.56R@1CLAP
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CLAPZero-shot=true, Training Dataset=ClothoV22026.06 | 16.56 | — | 48.86 | — | 25.11 | |
| MixProLAPZero-shot=true, Training Dataset=ClothoV22026.06 | 15.62 | — | 50.01 | — | 25.08 | |
| CLAPZero-shot=true, Training Dataset=AudioCaps2026.06 | 14.56 | — | 45.55 | — | 23.18 | |
| MixProLAPZero-shot=true, Training Dataset=AudioCaps2026.06 | 12.33 | — | 41.47 | — | 20.06 | |
| CLAP (Microsoft)Category=BM2025.11 | 4.61 | 16.9 | 26.43 | 15.98 | — | |
| WavCapsCategory=BM2025.11 | 4.38 | 18.76 | 28.61 | 17.25 | — | |
| CACARA_WC/AC/C/f 0.2Category=CACARA, f-value=0.22025.11 | 4.03 | 15.6 | 24.78 | 14.8 | — | |
| CACARA_WC/AC/C/f 0.1Category=CACARA, f-value=0.12025.11 | 3.92 | 14.99 | 23.1 | 14 | — | |
| CACARA_WC/AC/CCategory=CACARA2025.11 | 3.88 | 14.69 | 22.49 | 13.69 | — | |
| CLAP (LAION)Category=BM2025.11 | 3.77 | 15.27 | 23.79 | 14.28 | — | |
| LanguageBindCategory=MM2025.11 | 3.75 | 16.38 | 24.65 | 14.93 | — | |
| CACARA_AA/WC/AC/CCategory=CACARA2025.11 | 2.9 | 12.17 | 19.4 | 11.49 | — | |
| CACARA_ASC/AA/WC/AC/C/f 0.2Category=CACARA, f-value=0.22025.11 | 2.59 | 10.07 | 16.62 | 9.76 | — | |
| CACARA_ASC/AA/WC/AC/C/f 0.1Category=CACARA, f-value=0.12025.11 | 2.56 | 9.84 | 16.15 | 9.52 | — | |
| VASTCategory=MM2025.11 | 2.3 | 8.73 | 13.99 | 8.34 | — | |
| CACARA_ASC/AA/WC/AC/CCategory=CACARA2025.11 | 2.22 | 8.71 | 14.42 | 8.45 | — | |
| ImageBindCategory=MM2025.11 | 1.51 | 5.57 | 9.15 | 5.41 | — |