Research map / Architectures and efficiency / Neural architecture search
Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture 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 |
|---|---|---|---|
| replace fixed I3D modules with NAS-rebuilt cells (ablation) | I3D gesture recognition network · IsoGD, RGB | recognition rate: 59.15% -> 61.13% | Helped |
| replace fixed I3D modules with NAS-rebuilt cells (ablation) | I3D gesture recognition network · IsoGD, Depth | recognition rate: 56.64% -> 58.32 % | Helped |
| replace fixed I3D modules with NAS-rebuilt cells (ablation) | I3D gesture recognition network · NvGesture, RGB and Depth; THU-READ, RGB and Depth | recognition rate: 81.67% -> 82.50%; 83.12% -> 85.83%; 65.50% -> 67.92%; 67.50% -> 68.75% | Helped |
| add dynamic attention (DAtt) (ablation) | I3D · NvGesture, RGB | recognition rate: 81.67% -> 83.54% | Helped |
| add dynamic attention (DAtt) (ablation) | I3D · NvGesture, Depth | recognition rate: 83.12% -> 84.58% | Helped |
| add static attention (SAtt) (ablation) | I3D · NvGesture, RGB | recognition rate: 81.67% -> 83.75% | Helped |
| add static attention (SAtt) (ablation) | I3D · NvGesture, Depth | recognition rate: 83.12% -> 85.21% | Helped |
| combine dynamic and static attention as DSA (ablation) | I3D · NvGesture, RGB | recognition rate: 81.67% -> 84.79% | Helped |
| combine dynamic and static attention as DSA (ablation) | I3D · NvGesture, Depth | recognition rate: 83.12% -> 85.83% | Helped |
| add static attention rather than dynamic attention alone (ablation) | I3D attention module · NvGesture, RGB and Depth | recognition rate: 83.54% -> 83.75%; 84.58% -> 85.21% | Helped |
Closest papers by meaning
- Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network (CVPR 2016 · similarity 0.89)
- Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training (CVPR 2019 · similarity 0.87)
- Gesture Recognition: Focus on the Hands (CVPR 2018 · similarity 0.86)
- LD-ConGR: A Large RGB-D Video Dataset for Long-Distance Continuous Gesture Recognition (CVPR 2022 · similarity 0.86)
- Attention in Convolutional LSTM for Gesture Recognition (NeurIPS 2018 · similarity 0.86)
- Skeleton-Based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module (AAAI 2019 · similarity 0.85)
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.