Text-to-Video Retrieval on DiDeMo 28s (test)
38.1R@1MAC
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MACArchitecture=V,T, # Pairs=5.5M, # Frames=82022.12 | 38.1 | 65.7 | 76.8 | |
| BridgeFormerArchitecture=V,T,Vmcq, # Pairs=5.5M, # Frames=82022.12 | 37 | 62.2 | 73.9 | |
| MACArchitecture=V,T, # Pairs=5.5M, # Frames=42022.12 | 36.7 | 64.5 | 75.3 | |
| MILESArchitecture=V,T,Vema, # Pairs=5.5M, # Frames=82022.12 | 36.6 | 63.9 | 74 | |
| ALPROArchitecture=V,T,C,Vpem, # Pairs=5.5M, # Frames=82022.12 | 35.9 | 67.5 | 78.8 | |
| OA-TransArchitecture=V,T,Vdet, # Pairs=5.5M, # Frames=82022.12 | 34.8 | 64.4 | 75.1 | |
| All-in-oneArchitecture=U, # Pairs=122.5M, # Frames=92022.12 | 32.7 | 61.4 | 73.5 | |
| FrozenArchitecture=V,T, # Pairs=5.5M, # Frames=42022.12 | 31 | 59.8 | 72.4 | |
| HD-VILAArchitecture=V,T,C, # Pairs=103M, # Frames=142022.12 | 28.8 | 57.4 | 69.1 | |
| ClipBERTArchitecture=V,T,C, # Pairs=5.6M, # Frames=82022.12 | 20.4 | 48 | 60.8 | |
| CEArchitecture=V,T,Vexpert, # Pairs=-, # Frames=-2022.12 | 16.1 | 41.1 | — |