Video-to-Audio Retrieval on AudioCaps V→A
88.3Recall@1PEAV L
Evaluation Results
| Method | Links | |
|---|---|---|
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=30 FPS2025.12 | 88.3 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=16 Frames2025.12 | 86.1 | |
| PEAV L-OODA-Enc Params.=1.1B, Data (M)=114, Sampling=30 FPS, OOD=true2025.12 | 86.1 | |
| PEAV BA-Enc Params.=0.2B, Data (M)=124, Sampling=30 FPS2025.12 | 83.7 | |
| PEAV L (PT)A-Enc Params.=1.1B, Data (M)=92, Sampling=30 FPS, PT=true2025.12 | 83.3 | |
| PEAV BA-Enc Params.=.2B, Data (M)=124, Sampling=16 Frames2025.12 | 80.6 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=30 FPS2025.12 | 77.4 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=16 Frames2025.12 | 75.4 | |
| ImageBindA-Enc Params.=.09B, Data (M)=32025.12 | 51.3 | |
| LangBindA-Enc Params.=0.3B, Data (M)=102025.12 | 9.1 |