Research map / Probabilistic and scientific modeling / Molecules and proteins
Social Interpretable Tree for Pedestrian Trajectory Prediction
Liushuai Shi, Le Wang, Chengjiang Long, Sanping Zhou, Fang Zheng, Nanning Zheng, Gang Hua
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 |
|---|---|---|---|
| Use SIT instead of STAR | ETH-UCY AVG · ETH-UCY AVG | ADE: 0.26 -> 0.23 | Improved |
| Use SIT instead of PECNet | ETH-UCY AVG · ETH-UCY AVG | FDE: 0.48 -> 0.38 | Improved |
| Use SIT instead of PECNet | Stanford Drone · Stanford Drone, K=20 | ADE: 9.96 -> 9.13 | Improved |
| Use SIT instead of PECNet | Stanford Drone · Stanford Drone, K=20 | FDE: 15.88 -> 15.42 | Improved |
| Use SIT instead of Social-STGCNN for long-horizon prediction | ETH-UCY · ETH-UCY, T_pred=16 | ADE: 0.54 -> 0.49 | Improved |
| Use SIT instead of Social-STGCNN for long-horizon prediction | ETH-UCY · ETH-UCY, T_pred=20 | ADE: 0.71 -> 0.55 | Improved |
| Use SIT instead of Social-STGCNN for long-horizon prediction | ETH-UCY · ETH-UCY, T_pred=24 | ADE: 0.92 -> 0.68 | Improved |
| Add teacher forcing during refinement (ablation) | SIT · SDD ablation | FDE: 15.57 -> 15.42 | Improved |
| Add the classification loss (ablation) | SIT · SDD ablation | ADE: 9.52 -> 9.13 | Improved |
| Add the classification loss (ablation) | SIT · SDD ablation | FDE: 16.69 -> 15.42 | Improved |
| Use teacher forcing, classification loss, and coarse ground truth together (ablation) | SIT · SDD ablation | ADE: 13.43 -> 9.13 | Improved |
| Use teacher forcing, classification loss, and coarse ground truth together (ablation) | SIT · SDD ablation | FDE: 25.09 -> 15.42 | Improved |
Closest papers by meaning
- Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction (CVPR 2020 · similarity 0.88)
- Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks (NeurIPS 2019 · similarity 0.88)
- SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latents (AAAI 2024 · similarity 0.88)
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.87)
- SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction (CVPR 2025 · similarity 0.86)
- Higher-order Relational Reasoning for Pedestrian Trajectory Prediction (CVPR 2024 · similarity 0.85)
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.
