Improving facial analysis and performance driven animation through disentangling identity and expression

作者：

Highlights：

• Identity–expression disentanglement can improve performance driven facial animation.

• An identity–expression factorization approach can improve both AAMs and CLMs.

• Identity–expression disentanglement can improve facial expression recognition.

摘要

•Identity–expression disentanglement can improve performance driven facial animation.•An identity–expression factorization approach can improve both AAMs and CLMs.•Identity–expression disentanglement can improve facial expression recognition.

论文关键词：Factorization techniques,Emotion recognition,Graphical models,Performance driven animation,Facial expression analysis

论文评审过程：Received 22 May 2013, Revised 24 March 2016, Accepted 21 April 2016, Available online 31 May 2016, Version of Record 20 June 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.04.017