AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning

Yunbo Wang, Haixu Wu, Jianjin Zhang, Zhifeng Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long

TPAMI 2022 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures · 744 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatiotemporal memory flow to ConvLSTM (ablation)ConvLSTM · Moving MNIST (fixed 10k training set)MSE: 103.3 -> 74.0Improved
replace ConvLSTM unit with ST-LSTM (ablation)PredRNN-M-Only · Moving MNIST (fixed 10k training set)MSE: 74.0 -> 56.8Improved
add memory decoupling and reverse scheduled sampling (ablation)PredRNN · Moving MNIST (fixed 10k training set)MSE: 56.8 -> 48.4Improved
add memory decoupling alone (ablation)PredRNN · Moving MNIST (fixed 10k training set)MSE: 56.8 -> 51.1Improved
keep full bottom-up memory flow instead of truncating (ablation)PredRNN · Moving MNIST (fixed 10k training set)MSE: 57.6 -> 56.8Improved
keep full top-down memory flow instead of truncating (ablation)PredRNN · Moving MNIST (fixed 10k training set)MSE: 59.7 -> 56.8Improved
add reverse scheduled sampling to ConvLSTM (ablation)ConvLSTM · Moving MNIST (fixed 10k training set)MSE: 103.3 -> 64.2Improved
use reverse scheduled sampling (2nd strategy, exponential) instead of scheduled sampling (ablation)PredRNN · Moving MNIST (fixed 10k training set)MSE: 56.8 -> 50.6Improved
use sigmoid instead of linear/exponential schedule in 1st RSS strategy (ablation)PredRNN · Moving MNIST (fixed 10k training set)MSE: 51.8 -> 53.9Hurt
add decoupling and RSS to PredRNN++ (ablation)PredRNN++ · Moving MNIST (fixed 10k training set)MSE: 46.5 -> 44.8Improved
add decoupling and RSS to E3D-LSTM (ablation)E3D-LSTM · Moving MNIST (fixed 10k training set)MSE: 44.2 -> 42.1Improved
add decoupling and RSS to MIM (ablation)MIM · Moving MNIST (fixed 10k training set)MSE: 52.0 -> 45.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy