Real-time 3D human action recognition based on Hyperpoint sequence

1 code implementation • 16 Nov 2021 • Xing Li, Qian Huang, Zhijian Wang, Zhenjie Hou, Tianjin Yang, Zhuang Miao

Instead of capturing spatio-temporal local structures, SequentialPointNet encodes the temporal evolution of static appearances to recognize human actions.

3D Action Recognition