Conditional convolution neural network enhanced random forest for facial expression recognition

作者：

Highlights：

• A conditional convolution neural network enhanced random forests for facial expression recognition.

• The method achieves fast and accurate results with a limited amount of training data.

• A robust deep salient feature representation based on saliency-guided facial patches using “visual attention” mechanisms.

摘要

•A conditional convolution neural network enhanced random forests for facial expression recognition.•The method achieves fast and accurate results with a limited amount of training data.•A robust deep salient feature representation based on saliency-guided facial patches using “visual attention” mechanisms.

论文关键词：Classification,Feature extraction,Facial expression recognition,Head pose alignment,Conditional CoNERF

论文评审过程：Received 15 December 2017, Revised 24 June 2018, Accepted 10 July 2018, Available online 17 July 2018, Version of Record 24 July 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.07.016