Dual-track spatio-temporal learning for urban flow prediction with adaptive normalization

DOI10.1016/J.ARTINT.2024.104065WikidataQ130071801 ScholiaQ130071801MaRDI QIDQ6494354

Xiao Yu Li, Yongshun Gong, Yilong Yin, Yu Zheng, Wei Liu, Liqiang Nie

Publication date: 30 April 2024

Published in: Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

contrastive learningregional and global correlationsspatio-temporal learningspatio-temporal normalizationurban flow prediction

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Predicting citywide crowd flows using deep spatio-temporal residual networks
• Multi-view graph convolutional networks with attention mechanism
• Estimation and Hypothesis Testing of Cointegration Vectors in Gaussian Vector Autoregressive Models
• Expanding the prediction capacity in long sequence time-series forecasting
• \(\mathrm{AutoSTG}^+\): an automatic framework to discover the optimal network for spatio-temporal graph prediction

This page was built for publication: Dual-track spatio-temporal learning for urban flow prediction with adaptive normalization