Research map / Detection and segmentation / CNN features
Linear Span Network for Object Skeleton Detection
Chang Liu, Wei Ke, Fei Qin, Qixiang Ye
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 subspace linear span (3 subspaces) on top of feature linear span (ablation) | LSN · SK-LARGE | F-measure (%): 49.53 -> 66.15 | Improved |
| span 3 subspaces instead of 2 (SRN) (ablation) | LSN · SK-LARGE | F-measure (%): 65.88 -> 66.15 | Improved |
| span 4 subspaces instead of 3 (ablation) | LSN · SK-LARGE | F-measure (%): 66.15 -> 65.89 | Hurt |
| add iterative training with resolution alignment (iter1) (ablation) | LSN_3 · SK-LARGE | F-measure (%): 66.15 -> 66.82 | Improved |
| train end-to-end instead of iterative strategy (ablation) | LSN_3 · SK-LARGE | F-measure (%): 66.82 -> 66.63 | Hurt |
| use more training iterations (iter2, iter3) (ablation) | LSN_3 · SK-LARGE | F-measure (%): 66.82 -> 66.74 -> 66.68 | No clear effect |
| use LSN instead of SRN | skeleton detector · SK-LARGE | F-measure: 0.655 -> 0.668 | Improved |
| use LSN instead of SRN | skeleton detector · WH-SYMMAX | F-measure: 0.780 -> 0.797 | Improved |
| use LSN instead of SRN | skeleton detector · SK-SMALL | F-measure: 0.632 -> 0.633 | No clear effect |
| use LSN instead of SRN | skeleton detector · SYMMAX | F-measure: 0.446 -> 0.480 | Improved |
| use LSN instead of SRN | skeleton detector · Sym-PASCAL | F-measure: 0.443 -> 0.425 | Hurt |
| use LSN instead of HED | edge detector · BSDS500 | ODS: 0.780 -> 0.790 | Improved |
Closest papers by meaning
- Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (CVPR 2016 · similarity 0.85)
- Multi-Scale Bidirectional FCN for Object Skeleton Extraction (AAAI 2018 · similarity 0.84)
- Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition (ICCV 2023 · similarity 0.84)
- DeepFlux for Skeletons in the Wild (CVPR 2019 · similarity 0.84)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.82)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.82)
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.
