no code implementations • IEEE Access ( Volume: 8 ) 2020 • Hongye Yang, Yuzhang Gu, Jianchao Zhu, Keli Hu, Xiaolin Zhang
In addition, such a fixed adjacency matrix used in all layers leads to the network failing to extract multi-level semantic features.
Ranked #58 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • 27 Sep 2016 • Kangru Wang, Lei Qu, Lili Chen, Yuzhang Gu, DongChen zhu, Xiaolin Zhang
The main contribution of this paper is a newly proposed descriptor which is implemented in the disparity image to obtain a disparity texture image.