A spatio-temporal RBM-based model for facial expression recognition

作者：

Highlights：

• Introducing a novel RBM-based model to capture transformations between image pairs.

• Disentangling FER transformations from other transformations using two hidden sets.

• Introducing a Quadripartite Contrastive Divergence algorithm to learn our model.

摘要

Highlights•Introducing a novel RBM-based model to capture transformations between image pairs.•Disentangling FER transformations from other transformations using two hidden sets.•Introducing a Quadripartite Contrastive Divergence algorithm to learn our model.

论文关键词：Face expression recognition,Restricted Boltzmann Machines,Spatio-temporal features,Image transformations

论文评审过程：Received 30 January 2015, Revised 26 May 2015, Accepted 22 July 2015, Available online 31 July 2015, Version of Record 28 September 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.07.006