Research map / Detection and segmentation / CNN features
Joint Multi-Person Pose Estimation and Semantic Part Segmentation
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 part segment consistency features to pose assembly (ablation) | Our Model · PASCAL-Person-Part | mAP: 38.7 -> 39.2 | Helped |
| add part segment consistency features to pose assembly (ablation) | Our Model · PASCAL-Person-Part | ADK (%): 41.9 -> 40.7 | Helped |
| add estimated pose features to part segmentation (ablation) | Our model (ResNet-101) · PASCAL-Person-Part | mIOU (%): 62.66 -> 64.39 | Helped |
| add estimated pose features to part segmentation (ablation) | Our model (VGG-16) · PASCAL-Person-Part | mIOU (%): 56.50 -> 58.06 | Helped |
| add estimated pose features to part segmentation (ablation) | Our model (ResNet-101) · PASCAL-Person-Part, Size XS | mIOU (%): 40.4 -> 53.4 | Helped |
| use ResNet-101 instead of VGG-16 for Part FCN (ablation) | Our model with pose features · PASCAL-Person-Part | mIOU (%): 58.06 -> 64.39 | Helped |
| use one pose configuration per detection box instead of multiple (ablation) | FCRF pose inference · PASCAL-Person-Part | pose estimation results | No clear effect |
| perform refinement once rather than iteratively (ablation) | Joint pose estimation and part segmentation framework · PASCAL-Person-Part | overall performance | No clear effect |
Closest papers by meaning
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation (CVPR 2016 · similarity 0.90)
- End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation (CVPR 2016 · similarity 0.89)
- Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer (CVPR 2018 · similarity 0.89)
- Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (AAAI 2020 · similarity 0.88)
- Deep Dual Consecutive Network for Human Pose Estimation (CVPR 2021 · similarity 0.88)
- FCPose: Fully Convolutional Multi-Person Pose Estimation With Dynamic Instance-Aware Convolutions (CVPR 2021 · 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.