Research map / 3D vision / Human pose estimation
Progressive Bi-C3D Pose Grammar for Human Pose Estimation
Lu Zhou, Yingying Chen, Jinqiao Wang, Hanqing Lu
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 single-scale Bi-C3D pose grammar (ablation) | two-stack hourglass · MPII validation | PCKh@0.5: 87.42 -> 88.15 | Improved |
| go from single-scale to two-scale grammar (ablation) | Bi-C3D grammar · MPII validation | PCKh@0.5: 88.15 -> 88.25 | Improved |
| go from two-scale to three-scale grammar (ablation) | Bi-C3D grammar · MPII validation | PCKh@0.5: 88.25 -> 88.37 | Improved |
| add global sequential grammar (ablation) | two-stack hourglass · MPII validation | PCKh@0.5: 87.42 -> 88.16 | Improved |
| combine multi-scale and sequential grammars (progressive) (ablation) | three-scale grammar · MPII validation | PCKh@0.5: 88.37 -> 88.48 | Improved |
| replace Bi-C3D with Bi-LSTM grammar (ablation) | single-scale grammar · MPII validation | PCKh@0.5: 88.15 -> 88.03 | Hurt |
| replace dilated C3D with 7x7 large kernel C3D (ablation) | single-scale grammar · MPII validation | PCKh@0.5: 88.15 -> 88.16 | No clear effect |
| replace dilated C3D with 7x7 large kernel C3D (ablation) | single-scale grammar · MPII validation | parameters (M): 6.77 -> 8.82 | Hurt |
| replace dilated C3D with plain C3D (no dilation) (ablation) | single-scale grammar · MPII validation | PCKh@0.5: 88.15 -> 87.83 | Hurt |
| replace Bi-C3D with Bi-LSTM grammar (ablation) | single-scale grammar · MPII validation | parameters (M): 6.77 -> 7.13 | Hurt |
| full model vs baseline on challenging joints | hourglass baseline · MPII | PCKh@0.5: +2.2% ankle, +2.8% wrist | Improved |
Closest papers by meaning
- Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation (AAAI 2018 · similarity 0.91)
- Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation (TPAMI 2021 · similarity 0.89)
- Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts (ICCV 2019 · similarity 0.88)
- Recurrent 3D Pose Sequence Machines (CVPR 2017 · similarity 0.87)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.86)
- HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units (AAAI 2025 · similarity 0.86)
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.
