Title
Spatial-aware stacked regression network for real-time 3D hand pose estimation
Abstract
•A stacked regression network for fast, robust and accurate 3D hand pose estimation is proposed.•A pose re-parameterization is adopted to utilize the 3D spatial structure of hand.•A spatial attention module is adopted to reduce the influence of irrelevant features.•A cross-stage self-distillation module is adopted to achieve a lightweight network.
Year
DOI
Venue
2021
10.1016/j.neucom.2021.01.045
Neurocomputing
Keywords
DocType
Volume
3D hand pose estimation,Depth image,Knowledge distillation
Journal
437
ISSN
Citations 
PageRank 
0925-2312
1
0.35
References 
Authors
0
8
Name
Order
Citations
PageRank
Pengfei Ren111.70
Haifeng Sun26827.77
Weiting Huang311.03
Jiachang hao411.70
Daixuan Cheng510.35
Qi Qi621056.01
J. Wang747995.23
Jianxin Liao845782.08