Task-dependent multi-task multiple kernel learning for facial action unit detection

作者：

Highlights：

• AU co-occurrence relations are modeled as multi-task multiple kernel learning.

• TD-MTMKL fuses different facial feature representations with multiple kernels.

• TD-MTMKL captures commonalities and adapts to variations among co-occurred AUs.

摘要

Highlights•AU co-occurrence relations are modeled as multi-task multiple kernel learning.•TD-MTMKL fuses different facial feature representations with multiple kernels.•TD-MTMKL captures commonalities and adapts to variations among co-occurred AUs.

论文关键词：Facial action unit detection,Multi-task multiple kernel learning,Support vector machines

论文评审过程：Received 27 January 2015, Revised 26 August 2015, Accepted 29 August 2015, Available online 25 September 2015, Version of Record 27 November 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.08.026