Video retrieval on UCF101
90.7Top-1 AccSigLIP2-g-opt
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SigLIP2-g-optV-Enc Params=1.1B, Resolution=384, Frame/ fps=8, Zero-shot Protocol=true2025.12 | 90.7 | — | — | — | — | |
| PE-GV-Enc Params=1.9B, Video Data=22M, Resolution=448, Frame/ fps=8, Zero-shot Protocol=true2025.12 | 90.7 | — | — | — | — | |
| PEAV-LV-Enc Params=0.5B, Video Data=124M, Resolution=336, Frame/ fps=30*, Zero-shot Protocol=true2025.12 | 90.4 | — | — | — | — | |
| PEAV-BV-Enc Params=0.4B, Video Data=124M, Resolution=336, Frame/ fps=16, Zero-shot Protocol=true2025.12 | 89.7 | — | — | — | — | |
| PEAV-BV-Enc Params=0.4B, Video Data=124M, Resolution=336, Frame/ fps=30*, Zero-shot Protocol=true2025.12 | 89.5 | — | — | — | — | |
| PEAV-LV-Enc Params=0.5B, Video Data=124M, Resolution=336, Frame/ fps=16, Zero-shot Protocol=true2025.12 | 89.2 | — | — | — | — | |
| PEAV-SV-Enc Params=0.3B, Video Data=124M, Resolution=336, Frame/ fps=30*, Zero-shot Protocol=true2025.12 | 89.2 | — | — | — | — | |
| InternVideo2V-Enc Params=1.0B, Video Data=102M, Resolution=224, Frame/ fps=8, Zero-shot Protocol=true2025.12 | 88.8 | — | — | — | — | |
| PEAV-SV-Enc Params=0.3B, Video Data=124M, Resolution=336, Frame/ fps=16, Zero-shot Protocol=true2025.12 | 87.8 | — | — | — | — | |
| PE-LV-Enc Params=0.3B, Video Data=22M, Resolution=336, Frame/ fps=8, Zero-shot Protocol=true2025.12 | 87.1 | — | — | — | — | |
| SigLIP2-L/16V-Enc Params=0.3B, Resolution=384, Frame/ fps=8, Zero-shot Protocol=true2025.12 | 86.7 | — | — | — | — | |
| LanguageBindV-Enc Params=0.3B, Video Data=10M, Resolution=224, Frame/ fps=16, Zero-shot Protocol=true2025.12 | 81.3 | — | — | — | — | |
| ImageBindV-Enc Params=0.6B, Video Data=3M, Resolution=224, Frame/ fps=16, Zero-shot Protocol=true2025.12 | 77.1 | — | — | — | — | |
| FAMEBackbone=R(2+1)D, Pre-train Dataset=Kinetics-4002021.09 | 64.6 | 77.7 | 82.9 | 87.6 | 94.2 | |
| ASCNetBackbone=R3D-18, Pre-train Dataset=Kinetics-4002021.09 | 58.9 | 76.3 | 82.2 | 87.5 | 93.4 | |
| GDTBackbone=R(2+1)D, Pre-train Dataset=Kinetics-4002021.09 | 57.4 | 73.4 | 80.8 | 88.1 | 92.9 | |
| TCLRBackbone=R(2+1)D-18, Pre-training=UCF1012021.01 | 56.9 | 72.2 | 79 | 84.6 | — | |
| TCLRBackbone=R3D-18, Pre-training=UCF1012021.01 | 56.2 | 72.2 | 79 | 85.3 | — | |
| TCLRBackbone=C3D, Pre-training=UCF1012021.01 | 48.6 | 67.6 | 75.5 | 82.5 | — | |
| SSTLBackbone=R3D-18, Pre-training=Kinetics-4002021.01 | 44.5 | 57.4 | 63.5 | 70 | — | |
| CACLNet=C3D, Pre-trained=Kinetics4002022.05 | 44.2 | 63.1 | 71.9 | 80.4 | 89.4 | |
| CACLNet=C3D2022.05 | 43.2 | 61.1 | 69.9 | 78.2 | 88.2 | |
| MLRepBackbone=R3D-18, Pre-train Dataset=Kinetics-4002021.09 | 41.5 | 60 | 71.2 | 80.1 | — | |
| CACLNet=R(2+1)D2022.05 | 41.5 | 59.7 | 68.4 | 77.6 | 87.8 | |
| RSPNetArchitecture=ResNet-182020.10 | 41.1 | 59.4 | 68.4 | 77.8 | 88.7 | |
| RSPNetBackbone=R3D-18, Venue=AAAI-21, Pre-training=UCF1012021.01 | 41.1 | 59.4 | 68.4 | 77.8 | — | |
| CACLNet=R3D2022.05 | 41.1 | 59.2 | 67.3 | 75.2 | 85.9 | |
| MFOBackbone=R3D-18, Venue=ICCV-21, Pre-training=UCF1012021.01 | 39.6 | 57.6 | 69.2 | 78 | — | |
| STSBackbone=C3D, Venue=TPAMI-21, Pre-training=Kinetics-4002021.01 | 39.1 | 59.2 | 68.8 | 77.6 | — | |
| STSBackbone=R3D-18, Venue=TPAMI-21, Pre-training=Kinetics-4002021.01 | 38.3 | 59.9 | 68.9 | 77.2 | — | |
| STSBackbone=R(2+1)D-18, Venue=TPAMI-21, Pre-training=Kinetics-4002021.01 | 38.1 | 58.9 | 68.1 | 77 | — | |
| RSPNetArchitecture=C3D2020.10 | 36 | 56.7 | 66.5 | 76.3 | 87.7 | |
| RSPNetBackbone=C3D, Venue=AAAI-21, Pre-training=UCF1012021.01 | 36 | 56.7 | 66.5 | 76.3 | — | |
| RSPNetNet=C3D2022.05 | 36 | 56.7 | 66.5 | 76.3 | 87.7 | |
| PaceArchitecture=C3D2020.10 | 31.9 | 49.7 | 59.2 | 68.9 | 80.2 | |
| Pace PredBackbone=C3D, Venue=ECCV-20, Pre-training=UCF1012021.01 | 31.9 | 49.7 | 59.2 | 68.9 | — | |
| Pace PredNet=C3D2022.05 | 31.9 | 49.7 | 59.2 | 68.9 | 80.2 | |
| TempTransBackbone=R3D-18, Pre-train Dataset=Kinetics-4002021.09 | 26.1 | 48.5 | 59.1 | 69.6 | 82.8 | |
| Temp TransBackbone=R3D-18, Venue=ECCV-20, Pre-training=UCF1012021.01 | 26.1 | 48.5 | 59.1 | 69.6 | — | |
| Buchler et al.Architecture=CaffeNet2020.10 | 25.7 | 36.2 | 42.2 | 49.2 | 59.5 | |
| Pace PredBackbone=R(2+1)D-18, Venue=ECCV-20, Pre-training=UCF1012021.01 | 25.6 | 42.7 | 51.3 | 61.3 | — | |
| Pace PredNet=R(2+1)D2022.05 | 25.6 | 42.7 | 51.3 | 61.3 | 74 | |
| Var. PSPBackbone=R3D-18, Venue=Access-21, Pre-training=UCF1012021.01 | 24.6 | 41.9 | 51.3 | 62.7 | — | |
| Pace PredBackbone=R3D-18, Venue=ECCV-20, Pre-training=UCF1012021.01 | 23.8 | 38.1 | 46.4 | 56.6 | — | |
| Pace PredNet=R3D2022.05 | 23.8 | 38.1 | 46.4 | 56.6 | 69.8 | |
| CSJBackbone=R3D-18, Pre-training=Kinetics-4002021.01 | 21.5 | 33.5 | 53.2 | 64.9 | — | |
| MemDPCBackbone=R3D-18, Venue=ECCV-20, Pre-training=UCF1012021.01 | 20.2 | 40.4 | 52.4 | 64.7 | — | |
| OPNArchitecture=OPN2020.10 | 19.9 | 28.7 | 34 | 40.6 | 51.6 | |
| VCPArchitecture=R(2+1)D2020.10 | 19.9 | 33.7 | 42 | 50.5 | 64.4 | |
| VCPBackbone=R(2+1)D-18, Venue=AAAI-20, Pre-training=UCF1012021.01 | 19.9 | 33.7 | 42 | 50.5 | — | |
| VCPBackbone=R3D-18, Venue=AAAI-20, Pre-training=UCF1012021.01 | 18.6 | 33.6 | 42.5 | 53.5 | — | |
| VCPBackbone=C3D, Venue=AAAI-20, Pre-training=UCF1012021.01 | 17.3 | 31.5 | 42 | 52.6 | — | |
| DSMBackbone=C3D, Venue=AAAI-21, Pre-training=UCF1012021.01 | 16.8 | 33.4 | 43.4 | 54.6 | — | |
| DSMNet=C3D2022.05 | 16.8 | 33.4 | 43.4 | 54.6 | 70.7 | |
| ClipOrderArchitecture=R3D2020.10 | 14.1 | 30.3 | 40 | 51.1 | 66.5 | |
| VCOPBackbone=R3D-18, Venue=CVPR-20, Pre-training=UCF1012021.01 | 14.1 | 30.3 | 40.4 | 51.1 | — | |
| VCOPNet=R3D2022.05 | 14.1 | 30.3 | 40 | 51.1 | 66.5 | |
| SpeedNetArchitecture=S3D-G2020.10 | 13 | 28.1 | 37.5 | 49.5 | 65 | |
| SpeedNetBackbone=S3D-G, Pre-train Dataset=Kinetics-4002021.09 | 13 | 28.1 | 37.5 | 49.5 | 65 | |
| VCOPBackbone=C3D, Venue=CVPR-20, Pre-training=UCF1012021.01 | 12.5 | 29 | 39 | 50.6 | — | |
| VCOPNet=C3D2022.05 | 12.5 | 29 | 39 | 50.6 | 66.9 | |
| VCOPBackbone=R(2+1)D-18, Venue=CVPR-20, Pre-training=UCF1012021.01 | 10.7 | 25.9 | 35.4 | 47.3 | — | |
| VCOPNet=R(2+1)D2022.05 | 10.7 | 25.9 | 35.4 | 47.3 | 63.9 |