Audio captioning on Clotho
Metric: CIDEr (higher is better)
Metric: CIDEr (higher is better)
| # | Model↕ | CIDEr▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ZerAuCap | 14 | No | Zero-shot audio captioning with audio-language m... | 2023-11-14 | Code |
| 2 | VAST | 0.519 | Yes | VAST: A Vision-Audio-Subtitle-Text Omni-Modality... | 2023-05-29 | Code |
| 3 | SLAM-AAC | 0.515 | Yes | SLAM-AAC: Enhancing Audio Captioning with Paraph... | 2024-10-12 | Code |
| 4 | LOAE | 0.513 | Yes | Enhancing Automated Audio Captioning via Large L... | 2024-06-19 | Code |
| 5 | MQ-Cap | 0.496 | No | Enhancing Retrieval-Augmented Audio Captioning w... | 2024-10-14 | - |
| 6 | Audio Flamingo (Pengi trainset) | 0.489 | Yes | Audio Flamingo: A Novel Audio Language Model wit... | 2024-02-02 | Code |
| 7 | Ensemble-RL | 0.468 | Yes | - | - | Code |
| 8 | Qwen-Audio | 0.441 | Yes | Qwen-Audio: Advancing Universal Audio Understand... | 2023-11-14 | Code |
| 9 | VALOR | 0.423 | Yes | VALOR: Vision-Audio-Language Omni-Perception Pre... | 2023-04-17 | Code |
| 10 | Ensemble | 0.4 | Yes | - | - | - |
| 11 | Ensemble | 0.319 | No | The NTT DCASE2020 Challenge Task 6 system: Autom... | 2020-07-01 | - |
| 12 | RNN-GRU-EncDec + VGGish + Word2Vec | 0.18 | No | Audio Captioning using Gated Recurrent Units | 2020-06-05 | - |