Research map / Graph learning / Knowledge and temporal graphs
Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
Inhwan Bae, Jin-Hwi Park, Hae-Gon Jeon
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 GP-Graph group hierarchy | STGCNN · ETH/UCY average | FDE: 0.76 -> 0.49 | Improved |
| add GP-Graph group hierarchy | SGCN · ETH/UCY average | FDE: 0.65 -> 0.39 | Improved |
| add GP-Graph group hierarchy | STAR · ETH/UCY average | ADE: 0.26 -> 0.26 | No clear effect |
| add GP-Graph group hierarchy | PECNet · SDD | ADE: 10.0 -> 9.1 | Improved |
| add GP-Graph group hierarchy | SGCN · GCS | ADE: 11.2 -> 7.8 | Improved |
| add GP-Graph group hierarchy | STGCNN · ETH/UCY average | COL: 5.02 -> 3.32 | Improved |
| add GP-Graph group hierarchy | PECNet · SDD | COL: 0.22 -> 0.23 | No clear effect |
| replace gPool with group pooling&unpooling (ablation) | GP-Graph-SGCN · ETH/UCY average | FDE: 0.45 -> 0.39 | Improved |
| replace SAGPool with group pooling&unpooling (ablation) | GP-Graph-SGCN · ETH/UCY average | FDE: 0.49 -> 0.39 | Improved |
| add inter-group graph with group pooling to member graph (ablation) | GP-Graph-SGCN · ETH/UCY average | ADE: 0.32 -> 0.25 | Improved |
| add agent-wise graph (ablation) | GP-Graph-SGCN · ETH/UCY average | ADE: 0.25 -> 0.24 | Improved |
| add weight sharing among interaction graphs (ablation) | GP-Graph-SGCN · ETH/UCY average | ADE: 0.24 -> 0.23 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SGCN — SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction (CVPR 2021) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction (CVPR 2020 · similarity 0.92)
- Higher-order Relational Reasoning for Pedestrian Trajectory Prediction (CVPR 2024 · similarity 0.89)
- A Unified Environmental Network for Pedestrian Trajectory Prediction (AAAI 2024 · 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)
- MS-TIP: Imputation Aware Pedestrian Trajectory Prediction (ICML 2024 · similarity 0.87)
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.
