Progressive ShallowNet for large scale dynamic and spontaneous facial behaviour analysis in children

作者：

Highlights：

• Progressive weight ShallowNet for analysis of spontaneous facial emotions.

• Limit the alternative path for the gradient at the earlier stage and increase gradually.

• The network is able to explore more feature space and vulnerable to perturbations.

摘要

Highlights•Progressive weight ShallowNet for analysis of spontaneous facial emotions.•Limit the alternative path for the gradient at the earlier stage and increase gradually.•The network is able to explore more feature space and vulnerable to perturbations.

论文关键词：Psychological health,Human computer interaction,Emotion care,Depressed,Facial behavior recognition,Progressive ShallowNet,Patient monitoring

论文评审过程：Received 18 August 2021, Revised 7 December 2021, Accepted 10 January 2022, Available online 17 January 2022, Version of Record 31 January 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104375