Research map / 3D vision / Human pose estimation
SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
Read the paperCheck 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 point learning-based human detection instead of regression-based detection (ablation) | SIMPLE-W32 · COCO2017 val | AP: 64.5 -> 67.1 | Helped |
| Add regression-based human detection instead of no human detection (ablation) | SIMPLE-W32 · COCO2017 val | AP: 63.4 -> 64.5 | Helped |
| Add ground-truth heatmap mimicking (ablation) | SIMPLE-W32 · COCO2017 val | AP: 67.1 -> 67.9 | Helped |
| Replace soft feature-map mimicking with soft heatmap mimicking (ablation) | SIMPLE-W32 · COCO2017 val | AP: 66.8 -> 70.2 | Helped |
| Add soft feature-map mimicking (ablation) | SIMPLE-W32 · COCO2017 val | AP: 67.1 -> 66.8 | Hurt |
| Add soft heatmap mimicking (ablation) | SIMPLE-W32 · COCO2017 val | AP: 67.1 -> 70.2 | Helped |
| Combine ground-truth and soft-heatmap mimicking (ablation) | SIMPLE-W32 · COCO2017 val | AP: 67.1 -> 70.8 | Helped |
| Add network mimicking (ablation) | SIMPLE-W18 · COCO2017 test-dev | AP Total: 66.1 -> 68.1 | Helped |
| Add network mimicking (ablation) | SIMPLE-W32 · COCO2017 test-dev | AP Total: 69.6 -> 71.1 | Helped |
Closest papers by meaning
- Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (AAAI 2020 · similarity 0.91)
- Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks (CVPR 2021 · similarity 0.89)
- Combining Detection and Tracking for Human Pose Estimation in Videos (CVPR 2020 · similarity 0.89)
- HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation (CVPR 2020 · similarity 0.88)
- End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer (AAAI 2026 · similarity 0.87)
- AdaptivePose: Human Parts as Adaptive Points (AAAI 2022 · similarity 0.87)
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.