Fully automatic person segmentation in unconstrained video using spatio-temporal conditional random fields
作者：
Highlights：
• Propose a method for automatic segmentation of people
• No constraints on camera or person in videos
• Learn model parameters without labeled segmented data
• Contribute labeled segmented video data for future research
• Proposed method performance favorable over other methods
摘要
•Propose a method for automatic segmentation of people•No constraints on camera or person in videos•Learn model parameters without labeled segmented data•Contribute labeled segmented video data for future research•Proposed method performance favorable over other methods
论文关键词：Person segmentation,Video segmentation,Conditional random field,Optical flow,Fully automatic
论文评审过程：Received 30 July 2014, Revised 5 August 2015, Accepted 24 April 2016, Available online 2 May 2016, Version of Record 12 May 2016.
论文官网地址：https://doi.org/10.1016/j.imavis.2016.04.007
