no code implementations • 9 Oct 2022 • Hongxin Lin, Yunwei Chiu, PeiYuan Wu
The graph convolutional networks (GCNs) have been applied to model the physically connected and non-local relations among human joints for 3D human pose estimation (HPE).
no code implementations • 20 Oct 2019 • Zelin Xiao, Hongxin Lin, Renjie Li, Hongyang Chao, Shengyong Ding
Interestingly, the principal component analysis exactly provides an effective way to define such a frame, i. e. setting the principal components as the frame axes.
no code implementations • 14 Aug 2019 • Hongxin Lin, Zelin Xiao, Yang Tan, Hongyang Chao, Shengyong Ding
Deep models are capable of fitting complex high dimensional functions while usually yielding large computation load.
no code implementations • 23 Oct 2018 • Yang Tan, Hongxin Lin, Zelin Xiao, Shengyong Ding, Hongyang Chao
However, such devices only provide sparse(limited speckles in structured light system) and noisy 3D data which can not support face recognition directly.