# Dual Encoding U-Net for Spatio-Temporal Domain Shift Frame Prediction

arXiv: https://arxiv.org/abs/2110.11140 · HTML: https://mlsanity.com/paper/2110.11140/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 21 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Utilizing UNet for the future traffic map prediction task Traffic4cast challenge 2020](https://mlsanity.com/paper/2012.00125/) (2020)
- [Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab](https://mlsanity.com/paper/1910.13824/) (2019)
- [Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction](https://mlsanity.com/paper/2012.02115/) (2020)
- [Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction](https://mlsanity.com/paper/2012.05207/) (2020)
- [TLab: Traffic Map Movie Forecasting Based on HR-NET](https://mlsanity.com/paper/2011.07728/) (2020)
- [Towards Good Practices of U-Net for Traffic Forecasting](https://mlsanity.com/paper/2012.02598/) (2020)
- [Recurrent Autoencoder with Skip Connections and Exogenous Variables for Traffic Forecasting](https://mlsanity.com/paper/1910.13295/) (2019)
- [Temporal Autoencoder with U-Net Style Skip-Connections for Frame Prediction](https://mlsanity.com/paper/2011.12661/) (2020)

## Built on by (most cited first, 2 of 2)

- [Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes](https://mlsanity.com/paper/2203.17070/) (2022)
- [A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learning](https://mlsanity.com/paper/2605.27884/) (2026)

## Abstract (arXiv)

The landscape of city-wide mobility behaviour has altered significantly over the past 18 months. The ability to make accurate and reliable predictions on such behaviour has likewise changed drastically with COVID-19 measures impacting how populations across the world interact with the different facets of mobility. This raises the question: "How does one use an abundance of pre-covid mobility data to make predictions on future behaviour in a present/post-covid environment?" This paper seeks to address this question by introducing an approach for traffic frame prediction using a lightweight Dual-Encoding U-Net built using only 12 Convolutional layers that incorporates a novel approach to skip-connections between Convolutional LSTM layers. This approach combined with an intuitive handling of training data can model both a temporal and spatio-temporal domain shift (gitlab.com/alchera/alchera-traffic4cast-2021).