Research map / 3D vision / Human pose estimation
Motion Prediction Using Trajectory Cues
Zhenguang Liu, Pengxiang Su, Shuang Wu, Xuanjing Shen, Haipeng Chen, Yanbin Hao, Meng Wang
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 |
|---|---|---|---|
| use trajectory representation (velocities plus last position) instead of pose coordinates (ablation) | MPT · H3.6M | MPJPE at 80 ms (mm): 11.3 -> 8.3 | Improved |
| use trajectory representation instead of pose coordinates, long-term (ablation) | MPT · H3.6M | MPJPE at 1,000 ms (mm): 111.7 -> 96.4 | Improved |
| add learnt implicit connection matrix to fixed skeletal and prior connections (ablation) | MPT · H3.6M | MPJPE | Improved |
| add fixed skeletal and prior-knowledge connections to the learnt matrix (ablation) | MPT · H3.6M | MPJPE | Improved |
| model motion in trajectory space with semi-constrained GCN vs best prior method | MPT · H3.6M | average accuracy: 17.5% accuracy improvement | Improved |
| apply MPT to fish pose prediction vs HMR | MPT · Fish | accuracy: 24.1% accuracy improvement | Improved |
| apply MPT to mouse pose prediction vs HMR | MPT · Mouse | accuracy: 13.8% | Improved |
| longer prediction horizon | MPT · H3.6M | advantage of trajectory representation | Hurt |
Closest papers by meaning
- Learning Trajectory Dependencies for Human Motion Prediction (ICCV 2019 · similarity 0.93)
- Learning Dynamic Relationships for 3D Human Motion Prediction (CVPR 2020 · similarity 0.91)
- Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction (TPAMI 2022 · similarity 0.91)
- MotionBERT: A Unified Perspective on Learning Human Motion Representations (ICCV 2023 · similarity 0.89)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.88)
- SimpliHuMoN: Simplifying Human Motion Prediction (NeurIPS 2026 · 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.
