Research map / Large language models / AI and society
Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process
Haosheng Zou, Hang Su, Shihong Song, Jun Zhu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 SA-GAIL training, social-aware LSTMs, and collision avoidance | Pedestrian trajectory prediction · Central Station test | normADE: 2.39% -> 1.98% | Improved |
| Add vicinity tensors with SA-LSTM | Vanilla LSTM · Central Station test | normADE: 2.39% -> 2.14% | Improved |
| Add collision avoidance | Vanilla LSTM · Central Station test | normADE: 2.39% -> 2.20% | Improved |
| Add SA-LSTM to the full SA-GAIL method (ablation) | Full SA-GAIL (no code) · Central Station test | normADE: 2.21% -> 1.98% | Improved |
| Add collision avoidance to the full SA-GAIL method (ablation) | Full SA-GAIL (no code) · Central Station test | normADE: 2.09% -> 1.98% | Improved |
| Use GAIL training (ablation) | Full SA-GAIL (no code) · Central Station test | normADE: 2.17% -> 1.98% | Improved |
| Add collision avoidance | Vanilla LSTM · Central Station test | ADE: 14.57 -> 13.11 | Improved |
| Add collision avoidance | Vanilla LSTM · Central Station test | FDE: 27.78 -> 26.19 | Improved |
| Add SA-LSTM to the full SA-GAIL method (ablation) | Full SA-GAIL (no code) · Central Station test | ADE: 13.17 -> 11.98 | Improved |
| Add collision avoidance to the full SA-GAIL method (ablation) | Full SA-GAIL (no code) · Central Station test | ADE: 12.61 -> 11.98 | Improved |
| Use GAIL training (ablation) | Full SA-GAIL (no code) · Central Station test | ADE: 12.95 -> 11.98 | Improved |
| Add vicinity tensors with SA-LSTM | Vanilla LSTM · Central Station test | FDE: 27.78 -> 25.51 | Improved |
Closest papers by meaning
- Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks (CVPR 2018 · similarity 0.87)
- Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks (NeurIPS 2019 · similarity 0.86)
- Forecasting Interactive Dynamics of Pedestrians With Fictitious Play (CVPR 2017 · similarity 0.86)
- Diffusing States and Matching Scores: A New Framework for Imitation Learning (ICLR 2025 · similarity 0.84)
- Social Physics Informed Diffusion Model for Crowd Simulation (AAAI 2024 · similarity 0.84)
- Continuous Locomotive Crowd Behavior Generation (CVPR 2025 · similarity 0.83)
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.
