Research map / 3D vision / Human pose estimation
Contact-aware Human Motion Forecasting
Wei Mao, miaomiao Liu, Richard Hartley, Mathieu Salzmann
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 predicted per-joint contact maps (ablation) | Ours · GTA-IM | mean path error (mm): 118.8 -> 108.4 | Improved |
| add predicted per-joint contact maps (ablation) | Ours · GTA-IM | mean pose error (mm): 68.2 -> 61.4 | Improved |
| add predicted per-joint contact maps (ablation) | Ours · PROX | mean path error (mm): 200.1 -> 192.2 | Improved |
| add predicted per-joint contact maps (ablation) | Ours · PROX | mean pose error (mm): 122.4 -> 116.8 | Improved |
| use ground-truth contact maps instead of predicted (ablation) | Ours · GTA-IM | mean path error (mm): 108.4 -> 74.1 | Improved |
| use ground-truth contact maps instead of predicted (ablation) | Ours · GTA-IM | mean pose error (mm): 61.4 -> 58.2 | Improved |
| use ground-truth contact maps instead of predicted (ablation) | Ours · PROX | mean path error (mm): 192.2 -> 88.0 | Improved |
| use ground-truth contact maps instead of predicted (ablation) | Ours · PROX | mean pose error (mm): 116.8 -> 101.1 | Improved |
| use Ours instead of best baseline (SLT*) for path | Ours · GTA-IM | mean path error (mm): 121.8 -> 108.4 | Improved |
| use Ours instead of best baseline (DMGNN) for pose | Ours · GTA-IM | mean pose error (mm): 64.9 -> 61.4 | Improved |
| use Ours instead of LTD for path | Ours · PROX | mean path error (mm): 236.3 -> 192.2 | Improved |
| use Ours instead of DMGNN for pose | Ours · PROX | mean pose error (mm): 129.1 -> 116.8 | Improved |
Closest papers by meaning
- Expressive Forecasting of 3D Whole-Body Human Motions (AAAI 2024 · similarity 0.89)
- MotionMap: Representing Multimodality in Human Pose Forecasting (CVPR 2025 · similarity 0.88)
- Multimodal Sense-Informed Forecasting of 3D Human Motions (CVPR 2024 · similarity 0.88)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.88)
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations (CVPR 2024 · similarity 0.88)
- Pose Priors from Language Models (CVPR 2025 · 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.
