atlas

Research map / Video / Video segmentation and tracking

PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

NeurIPS 2017 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 605 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 zigzag spatiotemporal memory flow (ablation)ConvLSTM (128 × 4) · Moving MNIST-2MSE/frame: 103.3 -> 74.0Helped
replace ConvLSTM with ST-LSTM units (ablation)PredRNN with spatiotemporal memory M · Moving MNIST-2MSE/frame: 74.0 -> 56.8Helped
replace ConvLSTM with ST-LSTM units (ablation)PredRNN with spatiotemporal memory M · Moving MNIST-3MSE/frame: 118.2 -> 93.4Helped
PredRNN instead of VPN baselinevideo prediction · Radar echoMSE/frame: 60.7 -> 44.2Helped
PredRNN instead of VPN baselinevideo prediction · Radar echomemory usage: 11513 MB -> 2367 MBHelped
spatiotemporal memory only vs VPN baseline (ablation)PredRNN · Moving MNIST-2CE/frame: 110.1 vs 118.5No clear effect

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