Research map / Probabilistic and scientific modeling / Molecules and proteins
Sparse Instance Conditioned Multimodal Trajectory Prediction
Yonghao Dong, Le Wang, Sanping Zhou, Gang Hua
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 sparse instance, memory refinement and clustering to the baseline (ablation) | SICNet · ETH-UCY (avg) | ADE/FDE: 0.46/0.94 -> 0.19/0.33 | Improved |
| add clustering post-process on top of sparse instance and refinement (ablation) | SICNet · ETH-UCY (avg) | ADE/FDE: 0.22/0.39 -> 0.19/0.33 | Improved |
| use mask threshold 0.2 instead of 0 or 1 (ablation) | SICNet · ETH-UCY (avg) | ADE: 0.21 (mu=0) -> 0.19 (mu=0.2) | Improved |
| use sparse instance instead of goal or full instance as the condition (ablation) | SICNet · ETH-UCY (avg) | ADE/FDE | Improved |
| use SICNet instead of MemoNet with small best-of-K | SICNet · SDD (K=10) | ADE/FDE: 11.26/19.64 -> 10.27/18.13 | Improved |
| SICNet vs MemoNet on SDD final displacement error at K=20 | SICNet · SDD (best-of-20) | FDE: 12.66 -> 13.65 | Hurt |
| SICNet vs PCCSNet at K=5 on SDD ADE | SICNet · SDD (K=5) | ADE: 12.57 -> 12.82 | Hurt |
Closest papers by meaning
- Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision (AAAI 2021 · similarity 0.87)
- SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction (CVPR 2021 · similarity 0.87)
- Sparse Trajectory Prediction (TPAMI 2025 · similarity 0.87)
- A Unified Environmental Network for Pedestrian Trajectory Prediction (AAAI 2024 · similarity 0.86)
- Towards Predicting Any Human Trajectory In Context (NeurIPS 2025 · similarity 0.84)
- TrajCLIP: Pedestrian trajectory prediction method using contrastive learning and idempotent networks (NeurIPS 2024 · 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.
