Research map / Graph learning / Knowledge and temporal graphs
Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
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 |
|---|---|---|---|
| Use ST-ResNet L12-E-BN instead of DeepST | TaxiBJ crowd-flow prediction · TaxiBJ | RMSE: 18.18 -> 16.69 | Helped |
| Use ST-ResNet with 4 residual units instead of DeepST-CPTM | BikeNYC crowd-flow prediction · BikeNYC | RMSE: 7.43 -> 6.33 | Helped |
| Add batch normalization to ST-ResNet L12-E (ablation) | ST-ResNet on TaxiBJ · TaxiBJ | RMSE: 16.89 -> 16.69 | Helped |
| Increase the residual-unit count from 2 to 4 (ablation) | ST-ResNet with external factors on TaxiBJ · TaxiBJ | RMSE: 17.67 -> 17.51 | Helped |
| Increase the residual-unit count from 4 to 12 (ablation) | ST-ResNet with external factors on TaxiBJ · TaxiBJ | RMSE: 17.51 -> 16.89 | Helped |
| Use two convolutions per residual unit instead of one (ablation) | ST-ResNet L12-E on TaxiBJ · TaxiBJ | RMSE: 17.40 -> 16.89 | Helped |
| Add external factors, including meteorology, holidays, and metadata (ablation) | ST-ResNet L12 on TaxiBJ · TaxiBJ | RMSE: 17.00 -> 16.89 | Helped |
| Use parametric-matrix fusion instead of direct summation (ablation) | ST-ResNet L12-E on TaxiBJ · TaxiBJ | RMSE: 17.96 -> 16.89 | Helped |
Closest papers by meaning
- DeepSTN+: Context-Aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis (AAAI 2019 · similarity 0.91)
- Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting (AAAI 2025 · similarity 0.85)
- Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting (AAAI 2024 · similarity 0.85)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · similarity 0.85)
- Decomposed Spatio-Temporal Mamba for Long-Term Traffic Prediction (AAAI 2025 · similarity 0.84)
- Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder (AAAI 2024 · similarity 0.84)
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.