Research map / Graph learning / Knowledge and temporal graphs
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
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 |
|---|---|---|---|
| Use S-RNN instead of AIO-HMM | Driving maneuver anticipation · All maneuvers | precision (%): 77.4 -> 82.2 | Helped |
| Use S-RNN instead of AIO-HMM | Driving maneuver anticipation · All maneuvers | recall (%): 71.2 -> 75.9 | Helped |
| Use S-RNN instead of AIO-HMM | Driving maneuver anticipation · Lane change | precision (%): 83.8 -> 92.7 | Helped |
| Use S-RNN instead of AIO-HMM | Driving maneuver anticipation · Turns | recall (%): 75.2 -> 78.6 | Helped |
| Add separately modeled edgeRNNs (ablation) | S-RNN · Driving maneuver anticipation: Turns | precision (%): 75.2 -> 81.2 | Helped |
| Add separately modeled edgeRNNs (ablation) | S-RNN · Driving maneuver anticipation: Turns | recall (%): 75.3 -> 78.6 | Helped |
| Add separately modeled edgeRNNs (ablation) | S-RNN · Driving maneuver anticipation: Lane change | recall (%): 86.0 -> 84.4 | Hurt |
| Add separately modeled edgeRNNs (ablation) | S-RNN · Driving maneuver anticipation: All maneuvers | precision (%): 78.0 -> 82.2 | Helped |
| Add separately modeled edgeRNNs (ablation) | S-RNN · Driving maneuver anticipation: All maneuvers | recall (%): 71.1 -> 75.9 | Helped |
Closest papers by meaning
- Recurrent Space-time Graph Neural Networks (NeurIPS 2019 · similarity 0.89)
- Scalable Spatiotemporal Graph Neural Networks (AAAI 2023 · similarity 0.88)
- Efficient Unlearning for Spatio-temporal Graph (Student Abstract) (AAAI 2025 · similarity 0.87)
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · similarity 0.87)
- Over-squashing in Spatiotemporal Graph Neural Networks (NeurIPS 2025 · similarity 0.86)
- Recurrent neural network dynamical systems for biological vision (NeurIPS 2024 · similarity 0.86)
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.