Research map / Detection and segmentation / Open-set and few-shot detection
Joint Human Pose Estimation and Instance Segmentation with PosePlusSeg
Niaz Ahmad, Jawad Khan, Jeremy Yuhyun Kim, Youngmoon Lee
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 |
|---|---|---|---|
| Use PosePlusSeg with ResNet-152 instead of the strongest listed baseline | COCO keypoint test · COCO keypoint test | AP: 0.721 -> 0.728 | Improved |
| Use PosePlusSeg with ResNet-152 instead of Pose2Seg | COCO human segmentation minival · COCO human segmentation minival | AP: 0.555 -> 0.563 | Improved |
| Use PosePlusSeg with ResNet-152 instead of multi-scale PersonLab | COCO human segmentation test · COCO human segmentation test | AP: 0.417 -> 0.445 | Improved |
| Add the body heat map to SKHM (ablation) | PosePlusSeg, ResNet-101 · COCO keypoint minival | AP: 0.717 -> 0.729 | Improved |
| Add the body heat map to SKHM (ablation) | PosePlusSeg, ResNet-152 · COCO keypoint minival | AP: 0.744 -> 0.748 | Improved |
| Increase keypoint disk radius from R=8 to R=32 (ablation) | PosePlusSeg · COCO keypoint minival, nose confidence | keypoint confidence score: 0.775 -> 0.830 | Improved |
| Increase keypoint disk radius from R=16 to R=32 (ablation) | PosePlusSeg · COCO keypoint minival, nose confidence | keypoint confidence score: 0.804 -> 0.830 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Pose2Seg — Pose2Seg: Detection Free Human Instance Segmentation (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Pose2Seg: Detection Free Human Instance Segmentation (CVPR 2019 · similarity 0.88)
- Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (AAAI 2020 · similarity 0.88)
- PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model (ECCV 2018 · similarity 0.87)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.87)
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation (CVPR 2016 · similarity 0.87)
- 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.
