Research map / 3D vision / Human pose estimation
Multi-Person Pose Forecasting with Individual Interaction Perceptron and Prior Learning
Peng Xiao, Yi Xie, Xuemiao Xu, Weihong Chen, Huaidong Zhang
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 Interaction Perceptron Module (IPM) to backbone (ablation) | IAFormer backbone · CMU-Mocap (UMPM) | JPE avg (mm): 111.3 -> 99.2 | Improved |
| add Interaction Prior Learning Module (IPLM) to backbone (ablation) | IAFormer backbone · CMU-Mocap (UMPM) | JPE avg (mm): 111.3 -> 99.2 | Improved |
| add IPLM on top of IPM (ablation) | IAFormer · CMU-Mocap (UMPM) | JPE avg (mm): 99.2 -> 95.9 | Improved |
| add Interaction Trajectory Weight alongside amplitude weight and IPLM (ablation) | IAFormer · CMU-Mocap (UMPM) | JPE avg (mm): 98.7 -> 95.9 | Improved |
| add Interaction Amplitude Weight alongside trajectory weight and IPLM (ablation) | IAFormer · CMU-Mocap (UMPM) | JPE avg (mm): 97.8 -> 95.9 | Improved |
| IAFormer vs JRFormer on 6-person Mix1 | IAFormer · Mix1, 6 persons | JPE avg (mm): 108 -> 114 | Hurt |
| IAFormer vs AuxFormer for long-term forecasting on single-person Human3.6M | IAFormer · Human3.6M, 1000ms | JPE (mm): 107.0 -> 130.4 | Hurt |
| IAFormer vs AuxFormer for short-term forecasting on Human3.6M | IAFormer · Human3.6M, 320ms | JPE (mm): 43.4 -> 39.8 | Improved |
| IAFormer vs TBIFormer on two-person CHI3D | IAFormer · CHI3D | JPE avg (mm): 142 -> 129 | Improved |
Closest papers by meaning
- Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning (CVPR 2024 · similarity 0.88)
- Multimodal Sense-Informed Forecasting of 3D Human Motions (CVPR 2024 · similarity 0.87)
- Expressive Forecasting of 3D Whole-Body Human Motions (AAAI 2024 · similarity 0.87)
- Capturing Closely Interacted Two-Person Motions with Reaction Priors (CVPR 2024 · similarity 0.85)
- MotionMap: Representing Multimodality in Human Pose Forecasting (CVPR 2025 · similarity 0.85)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (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.
