Research map / Architectures and efficiency / RNNs and normalization
Dynamic Traffic Modeling From Overhead Imagery
Check 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 road segmentation and orientation estimation as auxiliary tasks to speed prediction (ablation) | LinkNet-34 traffic speed model · NYC test set | RMSE: 10.87 -> 10.66 | Helped |
| Add road segmentation to speed and orientation estimation (ablation) | LinkNet-34 traffic speed model · NYC test set | RMSE: 10.78 -> 10.66 | Helped |
| Add orientation estimation to speed and road segmentation (ablation) | LinkNet-34 traffic speed model · NYC test set | RMSE: 10.73 -> 10.66 | Helped |
| Use region aggregation rather than replicating segment labels across the road (ablation) | LinkNet-34 traffic speed model · NYC test set | RMSE: 11.10 -> 10.66 | Helped |
| Add location context (ablation) | Image-only traffic speed model · NYC test set | RMSE: 11.35 -> 10.95 | Helped |
| Add time context (ablation) | Image-only traffic speed model · NYC test set | RMSE: 11.35 -> 10.68 | Helped |
| Add time context to image and location inputs (ablation) | LinkNet-34 traffic speed model · NYC test set | RMSE: 10.95 -> 10.66 | Helped |
| Add location context to image and time inputs (ablation) | LinkNet-34 traffic speed model · NYC test set | RMSE: 10.68 -> 10.66 | Helped |
| Add overhead imagery to location and time metadata (ablation) | Traffic speed model · NYC test set | RMSE: 13.14 -> 10.66 | Helped |
| Use orientation-weighted angle-dependent speed averaging instead of uniform weights (ablation) | Traffic speed model · Overall, NYC test set | RMSE: 11.145 -> 11.134 | Helped |
| Add location and time context (ablation) | Image-only traffic speed model · Overall, NYC test set | RMSE: 11.903 -> 11.134 | Helped |
Closest papers by meaning
- Spatio-Temporal Graph Structure Learning for Traffic Forecasting (AAAI 2020 · similarity 0.87)
- Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting (AAAI 2019 · similarity 0.86)
- DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting (ICML 2022 · similarity 0.86)
- Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning (AAAI 2025 · similarity 0.86)
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts (ICLR 2024 · similarity 0.84)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (AAAI 2025 · 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.