Zero-shot Retrieval (T → A+V) on AudioCaps
45.8Recall@1PEAVL
Evaluation Results
| Method | Links | |
|---|---|---|
| PEAVLJoint Query Strategy=Approximated, Model Scale=Large, Training Domain=In-domain2025.12 | 45.8 | |
| PEAVL-OODJoint Query Strategy=Approximated, Model Scale=Large, Training Domain=Out-of-domain2025.12 | 43.4 | |
| PEAVBJoint Query Strategy=Approximated, Model Scale=Base, Training Domain=In-domain2025.12 | 42.7 | |
| PEAVLJoint Query Strategy=Native, Model Scale=Large, Training Domain=In-domain2025.12 | 42.6 | |
| PEAVSJoint Query Strategy=Approximated, Model Scale=Small, Training Domain=In-domain2025.12 | 41.8 | |
| PEAVBJoint Query Strategy=Native, Model Scale=Base, Training Domain=In-domain2025.12 | 41 | |
| PEAVB-OODJoint Query Strategy=Approximated, Model Scale=Base, Training Domain=Out-of-domain2025.12 | 40.4 | |
| PEAVS-OODJoint Query Strategy=Approximated, Model Scale=Small, Training Domain=Out-of-domain2025.12 | 40.2 | |
| PEAVSJoint Query Strategy=Native, Model Scale=Small, Training Domain=In-domain2025.12 | 40.1 | |
| PEAVL-OODJoint Query Strategy=Native, Model Scale=Large, Training Domain=Out-of-domain2025.12 | 38.7 | |
| PEAVB-OODJoint Query Strategy=Native, Model Scale=Base, Training Domain=Out-of-domain2025.12 | 38 | |
| PEAVS-OODJoint Query Strategy=Native, Model Scale=Small, Training Domain=Out-of-domain2025.12 | 36.8 | |
| LanguageBindJoint Query Strategy=Approximated2025.12 | 19.7 | |
| ImageBindJoint Query Strategy=Approximated2025.12 | 7.6 |