Music-to-Text Retrieval on MusicCaps
24.6R@1MTC (AudioSet)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MTC (AudioSet)Label=Tag, Evaluation Protocol=audio-language alignment2026.03 | 24.6 | — | — | |
| Contrastive-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.03 | 19.8 | — | — | |
| Contrastive-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.03 | 19 | — | — | |
| Multi-Task (Ours)Label=Tag*, Caption*, Evaluation Protocol=audio-language alignment2026.03 | 15.8 | — | — | |
| MTC (Ours-UTS)Label=Tag*, Evaluation Protocol=audio-language alignment2026.03 | 15.6 | — | — | |
| Captioning-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.03 | 14.4 | — | — | |
| Captioning-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.03 | 14.2 | — | — | |
| PAR (Ours-UTS)Label=Tag Sequence*, Evaluation Protocol=audio-language alignment2026.03 | 12.2 | — | — | |
| CyCLAP2023.10 | 6.37 | 18.98 | 29.45 | |
| CyCLAPS2023.10 | 6.34 | 20.06 | 30.08 | |
| CLAP2023.10 | 6.05 | 18.42 | 28.33 | |
| CLAPS2023.10 | 5.99 | 18.66 | 28.85 |