An online spatio-temporal tensor learning model for visual tracking and its applications to facial expression recognition

作者：

Highlights：

• Visual tracking in videos is an essential component in human computer interaction.

• An online tensor based learning strategy is proposed for visual tracking.

• The tracking method show superior tracking performance in challenging conditions.

• The proposed tracker delivers the scale and orientation information of the target.

• Real time facial expression recognition system is presented using proposed tracker.

摘要

•Visual tracking in videos is an essential component in human computer interaction.•An online tensor based learning strategy is proposed for visual tracking.•The tracking method show superior tracking performance in challenging conditions.•The proposed tracker delivers the scale and orientation information of the target.•Real time facial expression recognition system is presented using proposed tracker.

论文关键词：Object tracking,Appearance model,Incremental N-mode SVD,Facial expression recognition

论文评审过程：Received 12 May 2017, Revised 3 August 2017, Accepted 21 August 2017, Available online 23 August 2017, Version of Record 31 August 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.08.039