Facial action unit recognition under incomplete data based on multi-label learning with missing labels

作者：

Highlights：

• This paper formulates facial action unit recognition under incomplete data as a multi-label learning with missing labels problem.

• We discriminate each AU on the most related features.

• Both an exact solution and an approximate solution are provided to optimize the proposed model.

摘要

Highlights•This paper formulates facial action unit recognition under incomplete data as a multi-label learning with missing labels problem.•We discriminate each AU on the most related features.•Both an exact solution and an approximate solution are provided to optimize the proposed model.

论文关键词：Face action unit recognition,Incomplete data,Multi-label learning

论文评审过程：Received 6 April 2016, Revised 10 June 2016, Accepted 4 July 2016, Available online 7 July 2016, Version of Record 26 July 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.07.009