Text-to-Audio Retrieval on Clotho V2
27.2R@1 (%)InternVideo2-6B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| InternVideo2-6BEvaluation protocol=Finetuning2024.03 | 27.2 | — | — | |
| VAST2023.05 | 26.9 | 53.2 | 66.1 | |
| VAST2023.05 | 26.9 | — | — | |
| VASTEvaluation protocol=Finetuning2024.03 | 26.9 | — | — | |
| MiCo2024.06 | 23.3 | — | — | |
| ONE-PIECE2023.05 | 22.4 | 49 | 62.7 | |
| CNN14-BERTAudio encoder=CNN14, Text encoder=BERT2023.05 | 21.5 | 47.9 | 61.9 | |
| Method [18]2023.05 | 21.5 | — | — | |
| SOTA2024.06 | 21.5 | — | — | |
| HTSAT-BERTAudio encoder=HTSAT, Text encoder=BERT2023.05 | 19.7 | 45.7 | 59.4 | |
| InternVideo2-6BEvaluation protocol=Zero-shot2024.03 | 17.4 | — | — | |
| LAION2023.05 | 16.1 | 38.3 | 51.1 | |
| LanguageBindEvaluation protocol=Zero-shot2024.03 | 12.1 | — | — |