Research map / Video / Action recognition
A New Representation of Skeleton Sequences for 3D Action Recognition
Check 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 |
|---|---|---|---|
| use the complete clips with MTLN rather than a single frame-level feature (ablation) | Clips + CNN + MTLN · SBU Kinect Interaction | accuracy: 90.88% -> 93.57% | Helped |
| replace MTLN with feature concatenation (ablation) | Clips + CNN + MTLN · NTU RGB+D cross-subject | accuracy: 79.57% -> 77.05% | Hurt |
| replace MTLN with max pooling (ablation) | Clips + CNN + MTLN · NTU RGB+D cross-view | accuracy: 84.83% -> 80.46% | Hurt |
| combine the three cylindrical-coordinate channels into one color clip (ablation) | Clips + CNN + MTLN · CMU | accuracy: 84.67% versus 88.30% | Hurt |
| add six less-stable reference joints to generate more frames (ablation) | Clips + CNN + MTLN · CMU | accuracy: 86.01% versus 88.30% | Hurt |
| use Cartesian instead of cylindrical coordinates (ablation) | Clips + CNN + MTLN · CMU | accuracy: 86.21% versus 88.30% | Hurt |
| use conv4_1 features instead of conv5_1 (ablation) | Clips + CNN + MTLN · CMU | accuracy: 84.59% versus 88.30% | Hurt |
| use fc6 features instead of conv5_1 (ablation) | Clips + CNN + MTLN · CMU | accuracy: 83.52% versus 88.30% | Hurt |
Closest papers by meaning
- Graph CNNs with Motif and Variable Temporal Block for Skeleton-Based Action Recognition (AAAI 2019 · similarity 0.91)
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition (AAAI 2018 · similarity 0.91)
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.91)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.90)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.89)
- Heterogeneous Skeleton-Based Action Representation Learning (CVPR 2025 · similarity 0.89)
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.