Modulated Graph Convolutional Network for 3D Human Pose Estimation
                      Zhiming Zou and Wei Tang*
                      University of Illinois at Chicago
                        {zzou6, tangw}@uic.edu

               Abstract
  The graph convolutional network (GCN) has recently
achieved promising performance of 3D human pose esti-
mation (HPE) by modeling the relationship among body
parts. However, most prior GCN approaches suffer from
two main drawbacks. First, they share a fea ...