Video Prediction On Human36M
評価指標
MAE
MSE
SSIM
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | MAE | MSE | SSIM | Paper Title | Repository |
|---|---|---|---|---|---|
| SimVP | 1510 | 316 | 0.904 | SimVP: Simpler yet Better Video Prediction | |
| SwinLSTM | 1190 | 332 | 0.913 | SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM | - |
| FRNN | 1901.1 | 497.7 | 0.771 | Folded Recurrent Neural Networks for Future Video Prediction | |
| FFINet | 1190 | 233 | 0.912 | Fast Fourier Inception Networks for Occluded Video Prediction | |
| IAM4VP | 1120 | 126 | 0.942 | Implicit Stacked Autoregressive Model for Video Prediction | |
| MIM | 1782.8 | 429.9 | 0.790 | Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics | |
| PhyDNet | 1620 | 369 | 0.901 | Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction | |
| E3D-LSTM | 1660 | 464 | 0.869 | Eidetic 3D LSTM: A Model for Video Prediction and Beyond | - |
| PredRNN | 1895.2 | 484.1 | 0.781 | PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs | - |
0 of 9 row(s) selected.