Multi-view facial landmark detector learned by the Structured Output SVM

作者：

Highlights：

• Real-time multi-view landmark detector independent on initialization

• Detector composed of a mixture of tree based Deformable Part Models

• Landmark detector learned by the Structured Output Support Vector Machines

• Coarse-to-fine strategy to speed up inference based on dynamic programming

摘要

•Real-time multi-view landmark detector independent on initialization•Detector composed of a mixture of tree based Deformable Part Models•Landmark detector learned by the Structured Output Support Vector Machines•Coarse-to-fine strategy to speed up inference based on dynamic programming

论文关键词：Deformable Part Models,Structured output SVM,Facial landmarks detection

论文评审过程：Received 2 March 2015, Revised 29 December 2015, Accepted 18 February 2016, Available online 2 March 2016, Version of Record 17 May 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.02.004