Video Retrieval on UCF101 (1)
83.9Top-1 AccSCE
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SCEBackbone=ResNet3D-50, Resp=16, Tp=224^2, Rese=16, Te=256^2, Pretrain=K4002022.12 | 83.9 | 92.2 | 94.9 | — | — | |
| SCEBackbone=ResNet3D-50, Resp=8, Tp=224^2, Rese=8, Te=256^2, Pretrain=K4002022.12 | 81.5 | 89.7 | 92.8 | — | — | |
| ProViCoBackbone=ResNet3D-18, Resp=16, Tp=112^2, Pretrain=K4002022.12 | 81.4 | — | 90.1 | — | — | |
| Supervised SLICInput Size=32 x 128^2, Architecture=R3D-182022.06 | 81 | 84.9 | 86.5 | 88.6 | — | |
| Supervised SLICInput Size=16 x 128^2, Architecture=R3D-182022.06 | 75.3 | 80.5 | 82.8 | 84.9 | — | |
| SCEBackbone=ResNet3D-18, Resp=16, Tp=112^2, Rese=16, Te=128^2, Pretrain=K4002022.12 | 74.5 | 85.9 | 90.5 | — | — | |
| SCEBackbone=ResNet3D-18, Resp=8, Tp=224^2, Rese=8, Te=256^2, Pretrain=K4002022.12 | 74.4 | 85.6 | 90 | — | — | |
| Supervised SLICInput Size=32 x 128^2, Architecture=S3D-232022.06 | 72.5 | 79.1 | 80.9 | 83.9 | — | |
| SLICInput Size=32 x 128^2, Architecture=R3D-182022.06 | 71.6 | 82.4 | 86.6 | 90.3 | — | |
| SLICInput Size=32 x 128^2, Architecture=S3D-232022.06 | 69.8 | 79.2 | 83.2 | 87.2 | — | |
| Supervised SLICInput Size=16 x 128^2, Architecture=S3D-232022.06 | 67.7 | 73.2 | 74.8 | 76 | — | |
| SLICInput Size=16 x 128^2, Architecture=R3D-182022.06 | 66.7 | 77.3 | 82 | 86.4 | — | |
| ViCC-R+FBackbone=S3D, Modality=V2021.06 | 65.1 | 80.2 | 85.4 | 89.8 | — | |
| ProViCoBackbone=ResNet3D-18, Resp=16, Tp=112^2, Pretrain=UCF1012022.12 | 63.8 | 75.1 | 84.8 | — | — | |
| TECBackbone=ResNet3D-18, Resp=16, Tp=128^2, Rese=16, Te=128^2, Pretrain=UCF1012022.12 | 63.6 | 79 | 84.8 | — | — | |
| ViCC-RGBBackbone=S3D, Modality=V2021.06 | 62.1 | 77.1 | 83.7 | 87.9 | — | |
| SLICInput Size=16 x 128^2, Architecture=S3D-232022.06 | 60.9 | 73.5 | 78.6 | 84 | — | |
| ViCC-R+FBackbone=R(2+1)D, Modality=V2021.06 | 59.9 | 77.6 | 84.6 | 90.6 | — | |
| ViCC-RGBBackbone=R(2+1)D, Modality=V2021.06 | 58.6 | 76.2 | 83.1 | 89 | — | |
| TCLRInput Size=16 x 112^2, Architecture=R3D-18, Input Modality=RGB2022.06 | 56.2 | 72.2 | 79 | 85.3 | — | |
| TCLRBackbone=ResNet3D-18, Resp=16, Tp=112^2, Pretrain=UCF1012022.12 | 56.2 | 72.2 | 79 | — | — | |
| CoCLRInput Size=32 x 128^2, Architecture=S3D-23, Input Modality=RGB + Optical Flow2022.06 | 55.9 | 70.8 | 76.9 | 82.5 | — | |
| CoCLRYear=2020, Backbone=S3D, Modality=V2021.06 | 55.9 | 70.8 | 76.9 | 82.5 | — | |
| PCL (VCP)Backbone=R3D-182020.10 | 55.1 | 71.2 | 78.9 | 85.5 | 92.3 | |
| CATEBackbone=ResNet3D-50, Resp=8, Tp=224^2, Rese=32, Te=256^2, Pretrain=K4002022.12 | 54.9 | 68.3 | 75.1 | — | — | |
| TransRankBackbone=ResNet3D-18, Resp=16, Tp=112^2, Pretrain=K2002022.12 | 54 | 71.8 | — | — | — | |
| CoCLRInput Size=32 x 128^2, Architecture=S3D-23, Input Modality=RGB2022.06 | 53.3 | 69.4 | 76.6 | 82 | — | |
| SimSiam_PredNext (ImageNet)Pre-training dataset=ImageNet2025.09 | 53.19 | 69.39 | 76.53 | 83.11 | — | |
| ViCC-R+FBackbone=R3D, Modality=V2021.06 | 52.1 | 71.7 | 79.8 | 86 | — | |
| PCL (VCP)Backbone=C3D2020.10 | 50.3 | 67.3 | 75.7 | 83.4 | 91.2 | |
| ViCCBackbone=ResNet3D-18, Resp=16, Tp=128^2, Rese=16, Te=128^2, Pretrain=UCF1012022.12 | 50.3 | 70.9 | 78.7 | — | — | |
| ViCC-RGBBackbone=R3D, Modality=V2021.06 | 50.3 | 70.9 | 78.7 | 85.6 | — | |
| PCL (VCP)Backbone=R3D2020.10 | 48.1 | 64.7 | 73.9 | 82 | 90.6 | |
| TransRankBackbone=ResNet3D-18, Resp=16, Tp=112^2, Pretrain=UCF1012022.12 | 46.5 | 63.7 | — | — | — | |
| PCL (VCP)Backbone=R(2+1)D2020.10 | 42.8 | 59.9 | 69.5 | 78 | 87.6 | |
| IICInput Size=16 x 112^2, Architecture=R3D-18, Input Modality=RGB + Optical Flow2022.06 | 42.4 | 60.9 | 69.2 | 77.1 | — | |
| MFOBackbone=ResNet3D-18, Resp=16, Tp=112^2, Rese=16, Te=112^2, Pretrain=K4002022.12 | 41.5 | 60.6 | 71.2 | — | — | |
| RSPNetBackbone=ResNet3D-18, Resp=16, Tp=112^2, Rese=16, Te=224^2, Pretrain=K4002022.12 | 41.1 | 59.4 | 68.4 | — | — | |
| MemDPC-FlowBackbone=R2D3D2020.10 | 40.2 | 63.2 | 71.9 | 78.6 | — | |
| PCL (VCOP)Backbone=C3D2020.10 | 39 | 59.1 | 67.5 | 76.8 | 87.4 | |
| PCL (VCOP)Backbone=R3D2020.10 | 38.9 | 57.8 | 66.6 | 76.1 | 86 | |
| SimCLR_PredNextPre-training dataset=UCF101 split 12025.09 | 37.09 | 56.01 | 66.38 | 75.2 | — | |
| IICBackbone=R3D-182020.10 | 36.8 | 54.1 | 63.1 | 72 | 83.3 | |
| IICBackbone=R3D2020.10 | 36.5 | 54.1 | 62.9 | 72.4 | 83.4 | |
| IICInput Size=16 x 112^2, Architecture=R3D-18, Input Modality=RGB2022.06 | 36.5 | 54.1 | 62.9 | 72.4 | — | |
| SimSiam_PredNextPre-training dataset=UCF101 split 12025.09 | 36.27 | 55.7 | 65.13 | 74.15 | — | |
| IICBackbone=R(2+1)D2020.10 | 34.7 | 51.7 | 60.9 | 69.4 | 81.9 | |
| SimCLRPre-training dataset=UCF101 split 12025.09 | 34.58 | 55.72 | 65.5 | 74.7 | — | |
| PCL (3DRotNet)Backbone=R3D-182020.10 | 33.7 | 53.5 | 64.1 | 73.4 | 85 | |
| PacePredBackbone=C3D2020.10 | 31.9 | 49.7 | 59.2 | 68.9 | 80.2 | |
| IICBackbone=C3D2020.10 | 31.9 | 48.2 | 57.3 | 67.1 | 79.1 | |
| SimSiamPre-training dataset=UCF101 split 12025.09 | 27.84 | 48.53 | 59.79 | 71.56 | — | |
| RTTBackbone=R3D-182020.10 | 26.1 | 48.5 | 59.1 | 69.6 | 82.8 | |
| RTTYear=2020, Backbone=R3D, Modality=V2021.06 | 26.1 | 48.5 | 59.1 | 69.6 | — | |
| Büchler2020.01 | 25.7 | 36.2 | 42.2 | 49.2 | 59.5 | |
| ST OrderYear=2018, Backbone=CaffeNet, Modality=V2021.06 | 25.7 | 36.2 | 42.2 | 49.2 | — | |
| PacePredBackbone=R(2+1)D2020.10 | 25.6 | 42.7 | 51.3 | 61.3 | 74 | |
| Var. PSPYear=2020, Backbone=R3D, Modality=V2021.06 | 24.6 | 41.9 | 51.3 | 62.7 | — | |
| PacePredBackbone=R3D-182020.10 | 23.8 | 38.1 | 46.4 | 56.6 | 69.8 | |
| Pace PredYear=2020, Backbone=R3D, Modality=V2021.06 | 23.8 | 38.1 | 46.4 | 56.6 | — | |
| PRPBackbone=C3D2020.10 | 23.2 | 38.1 | 46 | 55.7 | 68.4 | |
| PRPBackbone=R3D2020.10 | 22.8 | 38.5 | 46.7 | 55.2 | 69.1 | |
| VCPBackbone=R3D-182020.10 | 22.1 | 33.8 | 42 | 51.3 | 64.7 | |
| PRPBackbone=R(2+1)D2020.10 | 20.3 | 34 | 41.9 | 51.7 | 64.2 | |
| MemDPCBackbone=R2D3D2020.10 | 20.2 | 40.4 | 52.4 | 64.7 | — | |
| MemDPCInput Size=40 x 128^2, Architecture=R3D-18, Input Modality=RGB2022.06 | 20.2 | 40.4 | 52.4 | 64.7 | — | |
| MemDPCBackbone=ResNet3D-18, Resp=40, Tp=224^2, Rese=40, Te=224^2, Pretrain=UCF1012022.12 | 20.2 | 40.4 | 52.4 | — | — | |
| MemDPCYear=2020, Backbone=R2D3D, Modality=V2021.06 | 20.2 | 40.4 | 52.4 | 64.7 | — | |
| OPN2020.01 | 19.9 | 28.7 | 34 | 40.6 | 51.6 | |
| VCPBackbone=R(2+1)D2020.01 | 19.9 | 33.7 | 42 | 50.5 | 64.4 | |
| VCPBackbone=R(2+1)D2020.10 | 19.9 | 33.7 | 42 | 50.5 | 64.4 | |
| OPNYear=2017, Backbone=VGG, Modality=V2021.06 | 19.9 | 28.7 | 34 | 40.6 | — | |
| VCPYear=2020, Backbone=R(2+1)D, Modality=V2021.06 | 19.9 | 33.7 | 42 | 50.5 | — | |
| Jigsaw2020.01 | 19.7 | 28.5 | 33.5 | 40 | 49.4 | |
| ST-PuzzleYear=2019, Backbone=R3D, Modality=V2021.06 | 19.7 | 28.5 | 33.5 | 40 | — | |
| VCPBackbone=R3D2020.01 | 18.6 | 33.6 | 42.5 | 53.5 | 68.1 | |
| VCPBackbone=R3D2020.10 | 18.6 | 33.6 | 42.5 | 53.5 | 68.1 | |
| VCPInput Size=16 x 112^2, Architecture=R3D-18, Input Modality=RGB2022.06 | 18.6 | 33.6 | 42.5 | 53.5 | — | |
| VCPBackbone=C3D2020.01 | 17.3 | 31.5 | 42 | 52.6 | 67.7 | |
| VCPBackbone=C3D2020.10 | 17.3 | 31.5 | 42 | 52.6 | 67.7 | |
| randomBackbone=C3D2020.01 | 16.7 | 27.5 | 33.7 | 41.4 | 53 | |
| RandomBackbone=C3D2020.10 | 16.7 | 27.5 | 33.7 | 41.4 | 53 | |
| PCL (VCOP)Backbone=R(2+1)D2020.10 | 16.6 | 33.3 | 43.1 | 55.5 | 72.6 | |
| RandomBackbone=R3D-182020.10 | 15.3 | 25.1 | 32.1 | 40.8 | 53.7 | |
| 3DRotNetBackbone=R3D-182020.10 | 14.2 | 25.2 | 33.5 | 43.7 | 59.5 | |
| VCOPBackbone=R3D2020.01 | 14.1 | 30.3 | 40.4 | 51.1 | 66.5 | |
| VCOPBackbone=R3D2020.10 | 14.1 | 30.3 | 40 | 51.1 | 66.5 | |
| VCOPInput Size=16 x 112^2, Architecture=R3D-18, Input Modality=RGB2022.06 | 14.1 | 30.3 | 40.4 | 51.1 | — | |
| VCOPYear=2019, Backbone=R3D, Modality=V2021.06 | 14.1 | 30.3 | 40.4 | 51.1 | — | |
| VCOPBackbone=C3D2020.01 | 12.5 | 29 | 39 | 50.6 | 66.9 | |
| VCOPBackbone=C3D2020.10 | 12.5 | 29 | 39 | 50.6 | 66.9 | |
| VCOPBackbone=R(2+1)D2020.01 | 10.7 | 25.9 | 35.4 | 47.3 | 63.9 | |
| VCOPBackbone=R(2+1)D2020.10 | 10.7 | 25.9 | 35.4 | 47.3 | 63.9 | |
| randomBackbone=R(2+1)D2020.01 | 10.6 | 20.7 | 27.4 | 37.4 | 53.1 | |
| RandomBackbone=R(2+1)D2020.10 | 10.6 | 20.7 | 27.4 | 37.4 | 53.1 | |
| randomBackbone=R3D2020.01 | 9.9 | 18.9 | 26 | 35.5 | 51.9 | |
| RandomBackbone=R3D2020.10 | 9.9 | 18.9 | 26 | 35.5 | 51.9 |