Research map / Architectures and efficiency / CNN design
A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture 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 |
|---|---|---|---|
| Add connections between neighboring hand joints beyond physical connections (ablation) | ST-TS-HGR-NET · FPHA; DHG (14 gestures); DHG (28 gestures) | accuracy: 91.65 -> 93.22; 93.10 -> 94.29; 88.33 -> 89.40 | Helped |
| Vary t0 from 1 to 2 or 3 (ablation) | ST-TS-HGR-NET · FPHA; DHG (14 gestures); DHG (28 gestures) | accuracy: 93.22 -> 93.04; 94.29 -> 94.17; 89.40 -> 89.04; 93.22 -> 93.04; 94.29 -> 94.29; 89.40 -> 89.40 | No clear effect |
| Vary the number of sub-sequences NS from 15 to 20 or 25 (ablation) | ST-TS-HGR-NET · FPHA; DHG (14 gestures); DHG (28 gestures) | accuracy: 93.33 -> 92.87; 94.29 -> 94.05; 89.40 -> 88.93; 93.33 -> 92.70; 94.29 -> 94.29; 89.40 -> 89.04 | No clear effect |
| Add TS-GA-NET to ST-HGR-NET (ablation) | ST-TS-HGR-NET · FPHA; DHG (14 gestures); DHG (28 gestures) | accuracy: 91.83 -> 93.22; 93.21 -> 94.29; 89.29 -> 89.40 | Helped |
| Add ST-GA-NET to TS-HGR-NET (ablation) | ST-TS-HGR-NET · FPHA; DHG (14 gestures); DHG (28 gestures) | accuracy: 90.96 -> 93.22; 93.33 -> 94.29; 88.21 -> 89.40 | Helped |
Closest papers by meaning
- Skeleton-Based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module (AAAI 2019 · similarity 0.88)
- Decoupled Representation Learning for Skeleton-Based Gesture Recognition (CVPR 2020 · similarity 0.87)
- Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network (CVPR 2016 · similarity 0.85)
- Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition (NeurIPS 2025 · similarity 0.85)
- Spatio-Temporal Difference Descriptor for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.84)
- Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion (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.