| Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval | ✓ Link | 27.69 | 57.03 | 70.39 | 40.14 | PaSST-RoBERTa & Estimated Audio–Caption Correspondences | 2024-08-21 |
| InternVideo2: Scaling Foundation Models for Multimodal Video Understanding | ✓ Link | 27.2 | | | | InternVideo2-6B | 2024-03-22 |
| VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset | ✓ Link | 26.9 | 53.2 | 66.1 | | VAST | 2023-05-29 |
| Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets | ✓ Link | 26.07 | 55.27 | 69.30 | 38.56 | PaSST–RoBERTa & GPT-augment | 2023-08-08 |
| ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities | ✓ Link | 22.4 | 49.0 | 62.7 | | ONE-PEACE | 2023-05-18 |
| VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset | ✓ Link | 17.5 | 42.7 | 55.3 | | VALOR | 2023-04-17 |
| Audio Retrieval with Natural Language Queries | ✓ Link | 9.6±0.3 | | 40.1±0.7 | | CE (pretraining:AudioCaps) | 2021-05-05 |
| Audio Retrieval with Natural Language Queries | ✓ Link | 8.6±0.4 | | 39.3±0.7 | | MoEE (pretraining:AudioCaps) | 2021-05-05 |
| Audio Retrieval with Natural Language Queries | ✓ Link | 6.7±0.4 | | 33.2±0.3 | | CE | 2021-05-05 |
| Audio Retrieval with Natural Language Queries: A Benchmark Study | ✓ Link | 6.5±0.6 | | 32.8±2.1 | | MMT | 2021-12-17 |
| Audio Retrieval with Natural Language Queries: A Benchmark Study | ✓ Link | 6.4±0.5 | | 32.5±1.7 | | CE(pretraining:SoundDescs) | 2021-12-17 |
| Audio Retrieval with Natural Language Queries | ✓ Link | 6.0±0.1 | | 32.3±0.3 | | MoEE | 2021-05-05 |