Research map / 3D vision / Human pose estimation
Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
Yu Chen, Chunhua Shen, Hao Chen, Xiu-Shen Wei, Lingqiao Liu, Jian Jun Yang
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 |
|---|---|---|---|
| add adversarial structure-aware training | stacked hourglass baseline · 300W test | mean error (%): 4.25 -> 3.96 | Improved |
| add adversarial training | baseline · 300W test | AUC: 50.06 -> 53.64 | Improved |
| add adversarial training | baseline · 300W test | failure rate (%): 2.67 -> 2.50 | No clear effect |
| add adversarial training | baseline · AFLW-Full | normalized mean error: 1.81 -> 1.39 | Improved |
| add adversarial training | baseline · MPII validation, invisible wrist | PCKh@0.5: 67.2 -> 70.7 | Improved |
| add adversarial training | baseline · MPII validation, visible joints | PCKh@0.5: 93.6 -> 94.5 | Improved |
| add occlusion-heatmap multi-task output (no discriminators) (ablation) | single-task generator · MPII validation | PCKh@0.5: +0.5% | Improved |
| add discriminators (no occlusion heatmaps) (ablation) | single-task generator · MPII validation | PCKh@0.5: +0.6% | Improved |
| combine multi-task and discriminators (ablation) | single-task generator · MPII validation | PCKh@0.5: 1.5% improvement vs 0.6% and 0.5% separately | Improved |
| add pose discriminator P only (ablation) | baseline · MPII validation | PCKh@0.5: 91.1 -> 91.9 | Improved |
| add confidence discriminator C only (ablation) | baseline · MPII validation | PCKh@0.5: 91.1 -> 91.4 | Improved |
| add adversarial training | 3D baseline (SH) · Human3.6M Protocol 1 | mean error (mm): 67.5 -> 64.9 | Improved |
Closest papers by meaning
- Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation (ICCV 2017 · similarity 0.94)
- A Simple yet Effective Baseline for 3D Human Pose Estimation (ICCV 2017 · similarity 0.90)
- Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment With Limited Resources (ICCV 2017 · similarity 0.89)
- Deep Deformation Network for Object Landmark Localization (ECCV 2016 · similarity 0.89)
- 3D Human Pose Estimation in the Wild by Adversarial Learning (CVPR 2018 · similarity 0.88)
- Multi-Scale Structure-Aware Network for Human Pose Estimation (ECCV 2018 · similarity 0.88)
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.
