Ultra-lightweight face activation for dynamic vision sensor with convolutional filter-level fusion using facial landmarks

作者：

Highlights：

• Design hand-craft filters for facial feature extraction from landmark data.

• Develop an ultra-lightweight face activation network using landmark filters.

• Achieve feasible performance and computational cost in a mobile environment.

• Construct dataset for face activation obtained from a dynamic vision sensor.

摘要

•Design hand-craft filters for facial feature extraction from landmark data.•Develop an ultra-lightweight face activation network using landmark filters.•Achieve feasible performance and computational cost in a mobile environment.•Construct dataset for face activation obtained from a dynamic vision sensor.

论文关键词：Ultra-lightweight face activation,Dynamic vision sensor,Filter fusion,Efficient convolutional neural network,Facial landmark,Knowledge distillation

论文评审过程：Received 26 April 2021, Revised 8 April 2022, Accepted 5 June 2022, Available online 8 June 2022, Version of Record 14 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117792