Research map / 3D vision / Human pose estimation
Learning Discriminative Activated Simplices for Action Recognition
Read the paperCheck 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 |
|---|---|---|---|
| learn dictionaries jointly with block-diagonal penalty (DAS vs independent AS) | Activated Simplices · MSR-Action3D (avg over 252 splits) | accuracy (%): 91.40 -> 95.62 | Helped |
| DAS vs AS on Florence | Activated Simplices · Florence (leave-one-actor-out) | accuracy (%): 94.25 -> 95.30 | Helped |
| DAS vs AS on UTKinect | Activated Simplices · UTKinect (leave-one-sequence-out) | accuracy (%): 96.48 -> 97.99 | Helped |
| add shared (common) basis dictionary (ablation) | DAS · MSR-Action3D (avg over 252 splits) | accuracy (%): 95.00 -> about 96 | Helped |
| increase shared dictionary size beyond 10 (ablation) | DAS · MSR-Action3D (avg over 252 splits) | accuracy (%) | Hurt |
| DAS vs AS across number of bases on composed dataset | Activated Simplices · Composed dataset (39 classes) | accuracy | Helped |
Closest papers by meaning
- Recognizing Actions in 3D Using Action-Snippets and Activated Simplices (AAAI 2016 · similarity 0.91)
- Mining 3D Key-Pose-Motifs for Action Recognition (CVPR 2016 · similarity 0.86)
- Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion (AAAI 2025 · similarity 0.84)
- Recovering Complete Actions for Cross-dataset Skeleton Action Recognition (NeurIPS 2024 · similarity 0.83)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.83)
- MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning (CVPR 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.