Video-to-Audio Retrieval on Internal V→A
50.3Recall@1PEAV L-OOD
Evaluation Results
| Method | Links | |
|---|---|---|
| PEAV L-OODA-Enc Params.=1.1B, Data (M)=114, Sampling=30 FPS, OOD=true2025.12 | 50.3 | |
| PEAV L (PT)A-Enc Params.=1.1B, Data (M)=92, Sampling=30 FPS, PT=true2025.12 | 47.8 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=30 FPS2025.12 | 46.5 | |
| PEAV BA-Enc Params.=0.2B, Data (M)=124, Sampling=30 FPS2025.12 | 44.6 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=30 FPS2025.12 | 40.5 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=16 Frames2025.12 | 23.9 | |
| PEAV BA-Enc Params.=.2B, Data (M)=124, Sampling=16 Frames2025.12 | 20.4 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=16 Frames2025.12 | 17.9 | |
| ImageBindA-Enc Params.=.09B, Data (M)=32025.12 | 2.8 | |
| LangBindA-Enc Params.=0.3B, Data (M)=102025.12 | 1.4 |