Papers › PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

1 Dec 2017Conference 2017 12archive 2025-07-28

Yunbo Wang Mingsheng Long Jianmin Wang Zhifeng Gao Philip S. Yu

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures. This paper models these structures by presenting a predictive recurrent neural network (PredRNN). This architecture is enlightened by the idea that spatiotemporal predictive learning should memorize both spatial appearances and temporal variations in a unified memory pool. Concretely, memory states are no longer constrained inside each LSTM unit. Instead, they are allowed to zigzag in two directions: across stacked RNN layers vertically and through all RNN states horizontally. The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously. PredRNN achieves the state-of-the-art prediction performance on three video prediction datasets and is a more general framework, that can be easily extended to other predictive learning tasks by integrating with other architectures.

PaperPDFCode

Code

chengtan9907/simvpv2 pytorchApache-2.0 report

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

Video Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Prediction Moving MNIST PredRNN MAE 126.1 #30 of 31 Archive leaderboard report
Video Prediction Moving MNIST PredRNN MSE 56.8 #30 of 31 Archive leaderboard report
Video Prediction Moving MNIST PredRNN SSIM 0.867 #30 of 31 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

LSTMSigmoid ActivationTanh Activation

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