mlsanityData to 7 Oct 2026

Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks

arXiv 1701.02543 ↗First posted 10 Jan 2017cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

Forecasting the flow of crowds is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, including spatial dependencies (nearby and distant), temporal dependencies (closeness, period, trend), and external conditions (e.g., weather and events). We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast two types of crowd flows (i.e. inflow and outflow) in each and every region of a city. We design an end-to-end structure of ST-ResNet based on unique properties of spatio-temporal data. More specifically, we employ the residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of crowd traffic. ST-ResNet learns to dynamically aggregate the output of the three residual neural networks based on data, assigning different weights to different branches and regions. The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region. We have developed a real-time system based on Microsoft Azure Cloud, called UrbanFlow, providing the crowd flow monitoring and forecasting in Guiyang City of China. In addition, we present an extensive experimental evaluation using two types of crowd flows in Beijing and New York City (NYC), where ST-ResNet outperforms nine well-known baselines.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 4; 2023: 5; 2024: 9; 2025: 5; 2026: 4.

34 papers.

Sort:

By area:

  1. 2024Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlookcited by 33
  2. 2023Building Transportation Foundation Model via Generative Graph Transformercited by 19
  3. 2021Spatiotemporal Data Mining: A Survey on Challenges and Open Problemscited by 13
  4. 2022ST-ExpertNet: A Deep Expert Framework for Traffic Predictioncited by 10
  5. 2024SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecastingcited by 8
  6. 2024Continual Traffic Forecasting via Mixture of Expertscited by 6
  7. 2024PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplinescited by 6
  8. 2021AGSTN: Learning Attention-adjusted Graph Spatio-Temporal Networks for Short-term Urban Sensor Value Forecastingcited by 5
  9. 2023S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Predictioncited by 5
  10. 2021Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flowcited by 4
  11. 2022A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecastingcited by 3
  12. 2025UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplinescited by 3
22 more
  1. 2023DSTCGCN: Learning Dynamic Spatial-Temporal Cross Dependencies for Traffic Forecastingcited by 2
  2. 2025A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Predictioncited by 2
  3. 2022Enhancing crowd flow prediction in various spatial and temporal granularitiescited by 1
  4. 2023Adapting to Skew: Imputing Spatiotemporal Urban Data with 3D Partial Convolutions and Biased Maskingcited by 1
  5. 2024Understanding Pedestrian Movement Using Urban Sensing Technologies: The Promise of Audio-based Sensorscited by 1
  6. 2024Spatiotemporal Forecasting of Traffic Flow using Wavelet-based Temporal Attentioncited by 1
  7. 2024STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processingcited by 1
  8. 2024FRTP: Federating Route Search Records to Enhance Long-term Traffic Predictioncited by 1
  9. 2026MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Modelscited by 1
  10. 2021Listening to the city, attentively: A Spatio-Temporal Attention Boosted Autoencoder for the Short-Term Flow Prediction Problemcited by 0
  11. 2021Bayesian Graph Convolutional Network for Traffic Predictioncited by 0
  12. 2021GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Seriescited by 0
  13. 2021Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structurecited by 0
  14. 2022Predicting Parking Lot Availability by Graph-to-Sequence Model: A Case Study with SmartSantandercited by 0
  15. 2023Multi-graph Spatio-temporal Graph Convolutional Network for Traffic Flow Predictioncited by 0
  16. 2024Temporal Graph Learning Recurrent Neural Network for Traffic Forecastingcited by 0
  17. 2025DG-STMTL: A Novel Graph Convolutional Network for Multi-Task Spatio-Temporal Traffic Forecastingcited by 0
  18. 2025Lightning Prediction under Uncertainty: DeepLight with Hazy Losscited by 0
  19. 2025Graph Convolutional Network With Pattern-Spatial Interactive and Regional Awareness for Traffic Forecastingcited by 0
  20. 2026Bikelution: Federated Gradient-Boosting for Scalable Shared Micro-Mobility Demand Forecastingcited by 0
  21. 2026TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportationcited by 0
  22. 2026A Multi-View Coupled Tensor Decomposition for Lightweight Online Adaptive Traffic Predictioncited by 0