Papers › PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
Yunbo Wang, Haixu Wu, Jianjin Zhang, Zhifeng Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long
The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems. This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment. Concretely, besides the original memory cell of LSTM, this network is featured by a zigzag memory flow that propagates in both bottom-up and top-down directions across all layers, enabling the learned visual dynamics at different levels of RNNs to communicate. It also leverages a memory decoupling loss to keep the memory cells from learning redundant features. We further propose a new curriculum learning strategy to force PredRNN to learn long-term dynamics from context frames, which can be generalized to most sequence-to-sequence models. We provide detailed ablation studies to verify the effectiveness of each component. Our approach is shown to obtain highly competitive results on five datasets for both action-free and action-conditioned predictive learning scenarios.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Prediction | KTH | PredRNN-V2 | Cond | 10 | #21 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | PredRNN-V2 | LPIPS | 0.139 | #21 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | PredRNN-V2 | PSNR | 28.37 | #21 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | PredRNN-V2 | Pred | 20 | #21 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | PredRNN-V2 | SSIM | 0.839 | #21 of 31 | Archive leaderboard | report |
| Video Prediction | Moving MNIST | PredRNN-V2 | LPIPS | 0.071 | #28 of 31 | Archive leaderboard | report |
| Video Prediction | Moving MNIST | PredRNN-V2 | MSE | 48.4 | #28 of 31 | Archive leaderboard | report |
| Video Prediction | Moving MNIST | PredRNN-V2 | SSIM | 0.891 | #28 of 31 | Archive leaderboard | report |
| Weather Forecasting | SEVIR | PredRNN | MSE | 3.9014 | #4 of 8 | Archive leaderboard | report |
| Weather Forecasting | SEVIR | PredRNN | mCSI | 0.4080 | #4 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections