Audio Captioning on Clotho V2
52CIDErAF-Next-Instruct
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| AF-Next-Instruct2026.04 | 52 | — | — | — | — | |
| VAST2023.05 | 51.9 | 19 | 19.3 | 40.8 | — | |
| VAST2023.05 | 51.9 | — | — | — | — | |
| MiCo2024.06 | 50.8 | — | — | — | — | |
| Audio Flamingo 32026.04 | 50 | — | — | — | — | |
| CNN14-BART2023.05 | 48.8 | 18 | 18.5 | 40 | — | |
| Method [18]2023.05 | 48.8 | — | — | — | — | |
| SOTA2024.06 | 48.8 | — | — | — | — | |
| Audio Flamingo2024.02 | 46.5 | — | — | — | — | |
| HTSAT-BART2023.05 | 46.2 | 16.8 | 18.4 | 38.3 | — | |
| Chu et al., 20232024.02 | 44.1 | — | — | — | — | |
| Kimi-Audio-InstructDecoder Size=7B2025.08 | — | — | — | — | 48.01 | |
| MiDashengLMDecoder Size=7B2025.08 | — | — | — | — | 49.2 | |
| Qwen2.5-OmniDecoder Size=7B2025.08 | — | — | — | — | 47.55 |