A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos
作者：
Highlights：
• A systematic approach to jointly solving two related tasks, i.e., face clustering and face tracklet linking in videos.
• Multiple types of prior knowledge extracted from videos.
• A novel and efficient method for constraint propagation, to augment the initial constraints extracted from videos.
• A Coupled Hidden Markov Random Field model to formulate clustering and tracklet linking together, and to incorporate different types of dependencies.
摘要
Highlights•A systematic approach to jointly solving two related tasks, i.e., face clustering and face tracklet linking in videos.•Multiple types of prior knowledge extracted from videos.•A novel and efficient method for constraint propagation, to augment the initial constraints extracted from videos.•A Coupled Hidden Markov Random Field model to formulate clustering and tracklet linking together, and to incorporate different types of dependencies.
论文关键词：Face clustering,Face tracking,Coupled Hidden Markov Random Field
论文评审过程：Received 24 April 2016, Revised 21 September 2016, Accepted 19 October 2016, Available online 26 October 2016, Version of Record 8 December 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2016.10.022
