Text-to-Audio Retrieval on VALOR
36.4Recall@1PE-AV
Evaluation results
| Method | Links | |
|---|---|---|
| PE-AVModel category=Audio-visual-text model2026.02 | 36.4 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=30 FPS2025.12 | 35.1 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=16 Frames2025.12 | 35 | |
| PEAV L-OODA-Enc Params.=1.1B, Data (M)=114, Sampling=30 FPS, OOD=true2025.12 | 34.2 | |
| PEAV BA-Enc Params.=.2B, Data (M)=124, Sampling=16 Frames2025.12 | 31.9 | |
| PEAV BA-Enc Params.=0.2B, Data (M)=124, Sampling=30 FPS2025.12 | 30.8 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=16 Frames2025.12 | 29.8 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=30 FPS2025.12 | 29.3 | |
| PEAV L (PT)A-Enc Params.=1.1B, Data (M)=92, Sampling=30 FPS, PT=true2025.12 | 24 | |
| AuroLAModel category=Audio-text model2026.02 | 14.8 | |
| MS-CLAPModel category=Audio-text model2026.02 | 8 | |
| AFlamingo2Model category=Audio-text model2026.02 | 7.4 | |
| AFlamingo2A-Enc Params.=0.3B, Data (M)=82025.12 | 7.3 | |
| CLAPModel category=Audio-text model2026.02 | 6.5 | |
| LangBindA-Enc Params.=0.3B, Data (M)=102025.12 | 6.5 | |
| M2D-CLAPA-Enc Params.=.09B, Data (M)=22025.12 | 6.3 | |
| M2D-CLAPModel category=Audio-text model2026.02 | 5.9 | |
| MS-CLAP23’A-Enc Params.=.08B, Data (M)=0.12025.12 | 5.9 | |
| CLAPA-Enc Params.=.03B, Data (M)=32025.12 | 5.8 | |
| LanguageBindModel category=Audio-visual-text model2026.02 | 5.6 | |
| CLAP-FusionA-Enc Params.=.03B, Data (M)=32025.12 | 5.5 | |
| CLAP (fusion)Model category=Audio-text model2026.02 | 5.4 | |
| ImageBindA-Enc Params.=.09B, Data (M)=32025.12 | 5.4 | |
| ImageBindModel category=Audio-visual-text model2026.02 | 4.9 |