Online unsupervised feature learning for visual tracking

作者：

Highlights：

• An online feature learning based tracking method achieves state-of-the-art performance.

• A dictionary learned from the sequence is capable of capturing appearance changes.

• The feature learning method can be used in the structured learning tracking framework.

摘要

•An online feature learning based tracking method achieves state-of-the-art performance.•A dictionary learned from the sequence is capable of capturing appearance changes.•The feature learning method can be used in the structured learning tracking framework.

论文关键词：Object tracking,Unsupervised feature learning,Dictionary learning

论文评审过程：Received 6 March 2015, Revised 4 February 2016, Accepted 19 April 2016, Available online 3 May 2016, Version of Record 16 May 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.04.008