| Accurate Grid Keypoint Learning for Efficient Video Prediction | ✓ Link | 144.2 | 0.837 | 27.11 | 0.092 | 10 | 10 | 40 | 2.0 | | | Grid-keypoints | 2021-07-28 |
| Stochastic Adversarial Video Prediction | ✓ Link | 145.7 | 0.806 | 26.00 | 0.116 | 10 | 10 | 40 | 7.3 | | | SAVP-VAE (from Grid-keypoints) | 2018-04-04 |
| Stochastic Video Generation with a Learned Prior | ✓ Link | 157.9 | 0.800 | 23.91 | 0.129 | 10 | 10 | 40 | 22.8 | | | SVG-LP (from Grid-keypoints) | 2018-02-21 |
| Stochastic Adversarial Video Prediction | ✓ Link | 183.7 | 0.699 | 23.79 | 0.126 | 10 | 10 | 40 | 17.6 | | | SAVP (from Grid-keypoints) | 2018-04-04 |
| Stochastic Variational Video Prediction | ✓ Link | 209.5 | 0.782 | 25.87 | 0.232 | 10 | 10 | 40 | 8.3 | | | SV2P time-invariant (from Grid-keypoints) | 2017-10-30 |
| Stochastic Latent Residual Video Prediction | ✓ Link | 222 ± 3 | 0.8697±0.0046 | 29.69±032 | 0.0736±0.0029 | 10 | 10 | 30 | | | | SRVP | 2020-02-21 |
| SLAMP: Stochastic Latent Appearance and Motion Prediction | ✓ Link | 228 ± 5 | 0.8646±0.0050 | 29.39±0.30 | 0.0795±0.0034 | 10 | 10 | 30 | | | | SLAMP | 2021-08-05 |
| Stochastic Variational Video Prediction | ✓ Link | 253.5 | 0.772 | 25.70 | 0.260 | 10 | 10 | 40 | 8.3 | | | SV2P time-invariant (from Grid-keypoints) | 2017-10-30 |
| Stochastic Adversarial Video Prediction | ✓ Link | 374 ± 3 | 0.7564±0.0062 | 26.51±0.29 | 0.1120±0.0039 | 10 | 10 | 30 | | | | SAVP (from SRVP) | 2018-04-04 |
| Stochastic Video Generation with a Learned Prior | ✓ Link | 377 ± 6 | 0.8438±0.0054 | 28.06±0.29 | 0.0923±0.0038 | 10 | 10 | 30 | | | | SVG-LP (from SRVP) | 2018-02-21 |
| Unsupervised Learning of Object Structure and Dynamics from Videos | ✓ Link | 395.0 | 0.766 | 24.29 | 0.124 | 10 | 10 | 40 | 2.3 | | | Struct-VRNN (from Grid-keypoints) | 2019-06-19 |
| Stochastic Variational Video Prediction | ✓ Link | 636 ± 1 | 0.838 | 28.19±0.31 | 0.2049±0.0053 | 10 | 10 | 30 | | | | SV2P (from SRVP) | 2017-10-30 |
| MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks | ✓ Link | | 0.951 | 27.81 | 0.029 | | | | | 23.18 | | MSPred | 2022-03-17 |
| Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction | ✓ Link | | 0.893 | 29.85 | | 10 | | 20 | | | | WAM | 2020-02-23 |
| Eidetic 3D LSTM: A Model for Video Prediction and Beyond | ✓ Link | | 0.879 | 29.31 | | 10 | | 20 | | | | E3d-LSTM | 2019-05-01 |
| Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning | ✓ Link | | 0.879 | 27.5 | 159.8 | 10 | | 40 | | | | LMC | 2021-04-02 |
| Mutual Suppression Network for Video Prediction using Disentangled Features | | | 0.876 | 27.08 | | 10 | | 20 | | | | MSNET | 2018-04-13 |
| PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning | ✓ Link | | 0.865 | 28.47 | | 10 | | 20 | | | | PredRNN++ | 2018-04-17 |
| Stochastic Adversarial Video Prediction | ✓ Link | | 0.852 | 27.77 | | 10 | | 20 | | | | SAVP-VAE | 2018-04-04 |
| VarNet: Exploring Variations for Unsupervised Video Prediction | ✓ Link | | 0.843 | 28.48 | | 10 | | 20 | | | | VarNet | 2018-10-01 |
| PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning | ✓ Link | | 0.839 | 28.37 | 0.139 | 10 | | 20 | | | | PredRNN-V2 | 2021-03-17 |
| Z-Order Recurrent Neural Networks for Video Prediction | | | 0.817 | 27.58 | | 10 | | 20 | | | | Znet | 2019-07-08 |
| Convolutional Tensor-Train LSTM for Spatio-temporal Learning | ✓ Link | | 0.815 | 27.62 | 0.196 | 10 | | 20 | | | | Conv-TT-LSTM | 2020-02-21 |
| Decomposing Motion and Content for Natural Video Sequence Prediction | ✓ Link | | 0.806 | 26.29 | | 10 | | 20 | | | | MCnet + Residual | 2017-06-25 |
| Decomposing Motion and Content for Natural Video Sequence Prediction | ✓ Link | | 0.804 | 25.95 | | 10 | | 20 | | | | MCnet | 2017-06-25 |
| Dynamic Filter Networks | ✓ Link | | 0.794 | 27.26 | | 10 | | 20 | | | | DFN | 2016-05-31 |
| Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model | ✓ Link | | 0.790 | 26.97 | | 10 | | 20 | | | | TrajGRU | 2017-06-12 |
| Folded Recurrent Neural Networks for Future Video Prediction | ✓ Link | | 0.771 | 26.12 | | 10 | | 20 | | | | fRNN | 2017-12-01 |
| Video Pixel Networks | ✓ Link | | 0.746 | 23.76 | | 10 | | 20 | | | | VPN | 2016-10-03 |
| Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting | ✓ Link | | 0.712 | 23.58 | 0.231 | 10 | | 20 | | | | ConvLSTM | 2015-06-13 |
| Diverse Video Generation using a Gaussian Process Trigger | ✓ Link | | | | | | | | | | 0.483 | DVG | 2021-07-09 |