Research map / 3D vision / Human pose estimation
Distribution-Aware Coordinate Representation 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 |
|---|---|---|---|
| Replace standard shifting with Taylor-based distribution-aware decoding | HRNet-W32 · COCO val2017, 128×96 | AP: 66.9 -> 68.4 | Helped |
| Add the standard 0.25-pixel shift instead of using the maximum activation directly (ablation) | HRNet-W32 · COCO val2017, 128×96 | AP: 61.2 -> 66.9 | Helped |
| Add Gaussian distribution modulation before DARK decoding (ablation) | DARK decoder on HRNet-W32 · COCO val2017, 128×96 | AP: 68.1 -> 68.4 | Helped |
| Use sub-pixel ground-truth heatmap centers instead of quantized centers (ablation) | HRNet-W32 with standard decoding · COCO val2017, 128×96 | AP: 66.9 -> 68.0 | Helped |
| Use sub-pixel ground-truth heatmap centers instead of quantized centers (ablation) | HRNet-W32 with DARK decoding · COCO val2017, 128×96 | AP: 68.4 -> 70.7 | Helped |
| Add DARK representation to HRNet-W48 | HRNet-W48 · COCO test-dev2017 | AP: 75.5 -> 76.2 | Helped |
| Add DARK representation to HRNet-W32 | HRNet-W32 · MPII validation | PCKh@0.1 Mean: 37.7 -> 42.0 | Helped |
| Add DARK representation to HRNet-W32 at reduced input resolution | HRNet-W32 · COCO val2017, 128×96 | AP: 66.9 -> 70.7 | Helped |
Closest papers by meaning
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.89)
- Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation (NeurIPS 2024 · similarity 0.87)
- SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation (AAAI 2024 · similarity 0.86)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.86)
- Video-Based Human Pose Regression via Decoupled Space-Time Aggregation (CVPR 2024 · similarity 0.86)
- PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization (CVPR 2024 · 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.