Linear latent low dimensional space for online early action recognition and prediction

作者：

Highlights：

• Action recognition and prediction using dimensionality reduction methods.

• Motion data from depth sensors for action analysis in linear latent spaces.

• Online and real time action recognition and prediction using supervised learning.

摘要

•Action recognition and prediction using dimensionality reduction methods.•Motion data from depth sensors for action analysis in linear latent spaces.•Online and real time action recognition and prediction using supervised learning.

论文关键词：Action recognition,Action prediction,Dimensionality reduction

论文评审过程：Received 1 February 2017, Revised 8 June 2017, Accepted 2 July 2017, Available online 4 July 2017, Version of Record 17 August 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.07.003