Research map / 3D vision / Human pose estimation
Multi-Context Attention for Human Pose Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 multi-context attention and hourglass residual units | Human pose estimation model · MPII test | PCKh@0.5 mean: 90.9 -> 91.5 | Helped |
| Use multi-context attention and hourglass residual units | Human pose estimation model · LSP test | PCK@0.2 mean: 90.7 -> 92.6 | Helped |
| Add holistic multi-semantics attention at each stack (ablation) | 8-stack hourglass baseline · MPII validation | PCKh@0.5: 1.2% | Helped |
| Replace residual units with hourglass residual units (ablation) | BL+MS · MPII validation | PCKh@0.5: 1% | Helped |
| Add multi-resolution attention (ablation) | BL+MS+HRU · MPII validation | PCKh@0.5: 1% | Helped |
| Replace refined holistic attention with part attention maps in stacks four to eight (ablation) | BL+MS+HRU+MR · MPII validation | PCKh@0.5 mean: 89.4% | Helped |
| Use CRF spatial attention instead of Softmax attention (ablation) | 2-stack hourglass network · MPII validation | PCKh@0.5 | Helped |
Closest papers by meaning
- Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction (CVPR 2020 · similarity 0.89)
- Graph Stacked Hourglass Networks for 3D Human Pose Estimation (CVPR 2021 · similarity 0.88)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.87)
- Deep Dual Consecutive Network for Human Pose Estimation (CVPR 2021 · similarity 0.87)
- Context Modeling in 3D Human Pose Estimation: A Unified Perspective (CVPR 2021 · similarity 0.86)
- Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation (NeurIPS 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.