Research map / 3D vision / Human pose estimation
A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation
Wentao Liu, Jie Chen, Cheng Li, Chen Qian, Xiao Chu, Xiaolin Hu
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 IOI block instead of residual blocks (ablation) | pose network · MPII val | mean PCKh@0.5: 87.3 -> 88.8 | Improved |
| use IOI block instead of inception-residual blocks (ablation) | pose network · MPII val | mean PCKh@0.5: 88.4 -> 88.8 | Improved |
| add scale attention (AIOI) to IOI (ablation) | pose network · MPII val | mean PCKh@0.5: 88.8 -> 89.1 | Improved |
| use sigmoid instead of softmax in attention (ablation) | pose network · MPII val | mean PCKh@0.5: 87.9 -> 88.4 | Improved |
| add attention to IOI under limb occlusion (ablation) | pose network · MPII val occluded | mean PCKh@0.5: 86.5 -> 87.2 | Improved |
| add cascaded joint prediction feed-forward (CJN vs MS-AIOI) (ablation) | pose network · MPII val | mean PCKh@0.5: 89.1 -> 89.6 | Improved |
| order joint groups easy to hard instead of random (ablation) | pose network · MPII val | mean PCKh@0.5: 88.8 -> 89.6 | Improved |
| predict groups sequentially instead of all joints per branch (ablation) | pose network · MPII val | mean PCKh@0.5: 89.4 -> 89.6 | Improved |
| random joint grouping vs no message passing (ablation) | pose network · MPII val | mean PCKh@0.5: 89.1 -> 88.8 | No clear effect |
| use full model (AIOI+CJN) vs best prior | pose network · LSP test | mean PCK@0.2: 92.6 -> 93.6 | Improved |
| use full model (AIOI+CJN) vs best prior | pose network · MPII test | mean PCKh@0.5: 91.5 -> 91.6 | Improved |
Closest papers by meaning
- Cascaded Pyramid Network for Multi-Person Pose Estimation (CVPR 2018 · similarity 0.86)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.85)
- Multi-Context Attention for Human Pose Estimation (CVPR 2017 · similarity 0.85)
- TransPose: Keypoint Localization via Transformer (ICCV 2021 · similarity 0.84)
- A Simple yet Effective Baseline for 3D Human Pose Estimation (ICCV 2017 · similarity 0.84)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · 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.
