Research map / Video / Video segmentation and tracking
PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add zigzag spatiotemporal memory flow (ablation) | ConvLSTM (128 × 4) · Moving MNIST-2 | MSE/frame: 103.3 -> 74.0 | Helped |
| replace ConvLSTM with ST-LSTM units (ablation) | PredRNN with spatiotemporal memory M · Moving MNIST-2 | MSE/frame: 74.0 -> 56.8 | Helped |
| replace ConvLSTM with ST-LSTM units (ablation) | PredRNN with spatiotemporal memory M · Moving MNIST-3 | MSE/frame: 118.2 -> 93.4 | Helped |
| PredRNN instead of VPN baseline | video prediction · Radar echo | MSE/frame: 60.7 -> 44.2 | Helped |
| PredRNN instead of VPN baseline | video prediction · Radar echo | memory usage: 11513 MB -> 2367 MB | Helped |
| spatiotemporal memory only vs VPN baseline (ablation) | PredRNN · Moving MNIST-2 | CE/frame: 110.1 vs 118.5 | No clear effect |
Closest papers by meaning
- PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning (ICML 2018 · similarity 0.92)
- Flexible Spatio-Temporal Networks for Video Prediction (CVPR 2017 · similarity 0.88)
- Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning (CVPR 2023 · similarity 0.88)
- Unsupervised Transfer Learning for Spatiotemporal Predictive Networks (ICML 2020 · similarity 0.88)
- Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics (CVPR 2019 · similarity 0.88)
- Wavelet-Driven Spatiotemporal Predictive Learning: Bridging Frequency and Time Variations (AAAI 2024 · similarity 0.87)
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.
