Measuring the intensity of spontaneous facial action units with dynamic Bayesian network

作者：

Highlights：

• This paper aims to measure the intensity of spontaneous facial action unit.

• The proposed framework models the correlation of AU intensities to improve the recognition accuracy.

• Advanced machine learning methods are introduced to learn the parameters of the proposed model.

• Plenty of experiments on DISFA database demonstrate the effectiveness of the proposed method.

摘要

Highlights•This paper aims to measure the intensity of spontaneous facial action unit.•The proposed framework models the correlation of AU intensities to improve the recognition accuracy.•Advanced machine learning methods are introduced to learn the parameters of the proposed model.•Plenty of experiments on DISFA database demonstrate the effectiveness of the proposed method.

论文关键词：Spontaneous facial expression,AU intensity,Dynamic Bayesian Network,FACS,DISFA database

论文评审过程：Received 27 March 2014, Revised 16 March 2015, Accepted 20 April 2015, Available online 29 April 2015, Version of Record 16 July 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.04.022