Research map / Label-efficient and robust learning / Domain adaptation and generalization
Consistency and Diversity Induced Human Motion Segmentation
Tao Zhou, Huazhu Fu, Chen Gong, Ling Shao, Fatih Porikli, Haibin Ling, Jianbing Shen
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 CDMS (consistency plus diversity) instead of MCSTL | CDMS · MAD target, Keck source (HOG) | ACC: 0.6125 -> 0.6536 | Improved |
| use CDMS instead of MCSTL | CDMS · UT target, MAD source (HOG) | ACC: 0.6433 -> 0.6643 | Improved |
| use CDMS instead of MCSTL | CDMS · Weiz target, UT source (HOG) | ACC: 0.6371 -> 0.6266 | Hurt |
| use CDMS instead of MCSTL | CDMS · Keck target, MAD source (HOG) | NMI: 0.8270 -> 0.7891 | Hurt |
| add Keck as a second source to Weiz (ablation) | CDMS · MAD target (HOG) | ACC: 0.6392 -> 0.6345 | No clear effect |
| add Weiz as a second source to UT (ablation) | CDMS · MAD target (HOG) | ACC: 0.6371 -> 0.6440 | Improved |
| add Weiz as a second source to UT (ablation) | CDMS · MAD target (HOG) | NMI: 0.8238 -> 0.8289 | No clear effect |
| fuse multi-level representations instead of first or last layer only (ablation) | CDMS · Weiz | NMI | Improved |
| add temporal correlation preservation term (ablation) | CDMS · Weiz | NMI | Improved |
| add diversity constraint (HSIC) across levels (ablation) | CDMS · Weiz | NMI | Improved |
| add multi-mutual consistency learning (ablation) | CDMS · Weiz | NMI | Improved |
| increase number of source actions (ablation) | CDMS · MAD target, Keck source | NMI/ACC | Improved |
Closest papers by meaning
- Multi-Mutual Consistency Induced Transfer Subspace Learning for Human Motion Segmentation (CVPR 2020 · similarity 0.94)
- Graph Constrained Data Representation Learning for Human Motion Segmentation (ICCV 2021 · similarity 0.91)
- Learning Transferable Subspace for Human Motion Segmentation (AAAI 2018 · similarity 0.90)
- Temporal Rate Reduction Clustering for Human Motion Segmentation (ICCV 2025 · similarity 0.86)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.83)
- Learned Trajectory Embedding for Subspace Clustering (CVPR 2024 · 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.
