Multi-task Facial Activity Patterns Learning for micro-expression recognition using Joint Temporal Local Cube Binary Pattern

作者：

Highlights：

• We propose a facial activity patterns learning framework and a local descriptor for micro-expression recognition.

• The joint temporal descriptor is proposed to encode the temporal structure of the texture and its intensity variation.

• The proposed framework aims to discover the relationship between MEs and AUs to extract features associated with facial actions.

• The influence of parameters, different components, and the comparison with some competitive state-of-the-art approaches are reported.

摘要

•We propose a facial activity patterns learning framework and a local descriptor for micro-expression recognition.•The joint temporal descriptor is proposed to encode the temporal structure of the texture and its intensity variation.•The proposed framework aims to discover the relationship between MEs and AUs to extract features associated with facial actions.•The influence of parameters, different components, and the comparison with some competitive state-of-the-art approaches are reported.

论文关键词：Micro-expression recognition,Joint temporal local cube binary pattern,Facial action unit,Facial activity patterns learning,Feature selection

论文评审过程：Received 21 February 2021, Revised 19 December 2021, Accepted 21 December 2021, Available online 3 January 2022, Version of Record 25 January 2022.

论文官网地址：https://doi.org/10.1016/j.image.2021.116616