Research map / 3D vision / Face and shape
Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks
Cong Yang, Bipin Indurkhya, John See, Bo Gao, Yan Ke, Zeyd Boukhers, Zhenyu Yang, Marcin Grzegorzek
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 |
|---|---|---|---|
| train and test with SkeView GT instead of original GT | DeepFlux · SK1491 | F1: 0.732 -> 0.752 | Improved |
| train and test with SkeView GT instead of original GT | Ada-LSN · SK1491 | F1: 0.786 -> 0.798 | Improved |
| train and test with SkeView GT instead of original GT | Hi-Fi · SK1491 | F1: 0.724 -> 0.727 | Improved |
| train and test with SkeView GT instead of original GT | HED · SK1491 | F1: 0.497 -> 0.494 | No clear effect |
| train and test with SkeView GT instead of original GT | SRN · SK1491 | F1: 0.678 -> 0.677 | No clear effect |
| add MG context re-ranking | Path Similarity · MPEG7 | Bulls-eye score (%): 62.96 -> 75.46 | Improved |
| add CT context re-ranking | Path Similarity · MPEG7 | Bulls-eye score (%): 62.96 -> 80.98 | Improved |
| add CT context re-ranking | High-order matching · MPEG7 | Bulls-eye score (%): 78.74 -> 87.28 | Improved |
| add MG context re-ranking | Skeleton Context · MPEG7 | Bulls-eye score (%): 13.67 -> 9.40 | Hurt |
| add CT context re-ranking | Skeleton Context · Animal2000 | Bulls-eye score (%): 8.88 -> 8.32 | Hurt |
| use High-order matching instead of Path Similarity | skeleton matching · Animal2000 | Bulls-eye score (%): 24.26 -> 34.14 | Improved |
| compare SkeView GT to automatic skeletons | reconstruction error · SK1491 | RE: 0.90 -> 0.88 | Improved |
Closest papers by meaning
- Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (CVPR 2016 · similarity 0.88)
- SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces From RGB Images (TPAMI 2021 · similarity 0.87)
- DeepFlux for Skeletons in the Wild (CVPR 2019 · similarity 0.87)
- SkeletonGait: Gait Recognition Using Skeleton Maps (AAAI 2024 · similarity 0.85)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.84)
- Motif Guided Graph Transformers with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification (AAAI 2025 · similarity 0.83)
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.
