Nonnegative Tensor-Based Linear Dynamical Systems for Recognizing Human Action from 3D Skeletons
Recently, skeleton-based action recognition has become a very important topic in the field of computer vision. It is a challenging task to accurately build a human action model and precisely distinguish similar human actions. In this paper, an action (skeleton sequence) is represented as a third-ord...
Main Authors: | Guang Li, Kai Liu, Wenwen Ding, Fei Cheng, Chongyang Ding |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2019-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2019/8940807 |
Similar Items
-
Skeleton-Based Square Grid for Human Action Recognition With 3D Convolutional Neural Network
by: Wenwen Ding, et al.
Published: (2021-01-01) -
Key-Skeleton-Pattern Mining on 3D Skeletons Represented by Lie Group for Action Recognition
by: Guang Li, et al.
Published: (2018-01-01) -
Advances in Nonnegative Matrix and Tensor Factorization
by: R. Zdunek, et al.
Published: (2008-01-01) -
Some bounds for the Z-eigenpair of nonnegative tensors
by: Xiaoyu Ma, et al.
Published: (2019-10-01) -
Bounds for the Z-eigenpair of general nonnegative tensors
by: Liu Qilong, et al.
Published: (2016-01-01)