Research map / 3D vision / Human pose estimation
Deep High-Resolution Representation Learning 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 |
|---|---|---|---|
| Add intermediate multi-scale exchanges across stages and within stages (ablation) | HRNet-W32 · COCO val2017 | AP: 70.8 -> 73.4 | Helped |
| Add across-stage exchange units (ablation) | HRNet-W32 · COCO val2017 | AP: 70.8 -> 71.9 | Helped |
| Add within-stage exchanges in addition to across-stage exchanges (ablation) | HRNet-W32 · COCO val2017 | AP: 71.9 -> 73.4 | Helped |
| Add high-resolution subnetworks first and introduce lower-resolution subnetworks progressively (ablation) | HRNet-W32 · COCO val2017 | AP: 72.5 -> 73.4 | Helped |
| Predict heatmaps from the highest-resolution representation rather than the lowest-resolution representation (ablation) | HRNet · COCO keypoint detection | AP | Helped |
| Pretrain HRNet-W32 on ImageNet | HRNet-W32 · COCO val2017, input size 256×192 | AP: 73.4 -> 74.4 | Helped |
| Increase width from W32 to W48 | HRNet · COCO val2017, input size 256×192 | AP: 74.4 -> 75.1 | Helped |
| Increase width from W32 to W48 | HRNet · COCO val2017, input size 384×288 | AP: 75.8 -> 76.3 | Helped |
| Increase input size from 256×192 to 384×288 | HRNet-W32 · COCO val2017 | AP: 73.4 -> 75.8 | Helped |
| Add AI Challenger training data | HRNet-W48 · COCO test-dev2017 | AP: 75.5 -> 77.0 | Helped |
| Increase width from W32 to W48 (ablation) | HRNet · MPII test | PCKh@0.5: 92.3 -> 92.3 | No clear effect |
| Use HRNet-W32 instead of SimpleBaseline with ResNet-152 | COCO val2017, input size 256×192 · COCO val2017 | AP: 72.0 -> 73.4 | Helped |
Closest papers by meaning
- SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation (AAAI 2024 · similarity 0.90)
- HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation (CVPR 2020 · similarity 0.89)
- Deep Dual Consecutive Network for Human Pose Estimation (CVPR 2021 · similarity 0.89)
- HRFormer: High-Resolution Vision Transformer for Dense Predict (NeurIPS 2021 · similarity 0.88)
- Distribution-Aware Coordinate Representation for Human Pose Estimation (CVPR 2020 · similarity 0.88)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 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.