Real-time facial action unit intensity prediction with regularized metric learning

作者：

Highlights：

• We present a framework for real-time Action Unit intensity prediction.

• We introduce a Lasso-regularized version of Metric Learning for Kernel Regression.

• We propose a new evaluation metric (r-AUC) designed for regression tasks.

摘要

•We present a framework for real-time Action Unit intensity prediction.•We introduce a Lasso-regularized version of Metric Learning for Kernel Regression.•We propose a new evaluation metric (r-AUC) designed for regression tasks.

论文关键词：Facial expression,Action Units,FACS,Metric Learning for Kernel Regression

论文评审过程：Received 10 December 2014, Revised 19 February 2016, Accepted 4 March 2016, Available online 3 May 2016, Version of Record 20 May 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.03.004