Learning principal orientations and residual descriptor for action recognition
作者：
Highlights：
• We exploit the distribution information of principal orientations of dataset by learning the projection matrix with trajectories on both spatial and temporal domains for extracting features informatively.
• We exploit the residual information of projected features in the projection subspace by maximizing the residual value of features from principal orientations.
• We consider the correlation between RGB channel and depth channel for RGB-D based action recognition and jointly learn the projection matrices on corresponding channels.
摘要
•We exploit the distribution information of principal orientations of dataset by learning the projection matrix with trajectories on both spatial and temporal domains for extracting features informatively.•We exploit the residual information of projected features in the projection subspace by maximizing the residual value of features from principal orientations.•We consider the correlation between RGB channel and depth channel for RGB-D based action recognition and jointly learn the projection matrices on corresponding channels.
论文关键词：Action recognition,Unsupervised learning,Trajectories,Principal orientation,Residual value
论文评审过程：Received 13 February 2018, Revised 12 August 2018, Accepted 27 August 2018, Available online 1 September 2018, Version of Record 7 September 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.08.016
