Uncooperative gait recognition by learning to rank
作者：
Highlights：
• We formulate transfer learning based on a bipartite ranking model for gait recognition.
• Invariant features to covariate conditions are transferred across different people.
• Under-sampled training data is handled by leveraging samples of different people.
• A single model can deal with any covariate condition and combinations of them.
• Outperforming other methods especially under challenging uncooperative settings.
摘要
Highlights•We formulate transfer learning based on a bipartite ranking model for gait recognition.•Invariant features to covariate conditions are transferred across different people.•Under-sampled training data is handled by leveraging samples of different people.•A single model can deal with any covariate condition and combinations of them.•Outperforming other methods especially under challenging uncooperative settings.
论文关键词：Gait recognition,Covariate conditions,Learning to rank,Transfer learning,Distance learning
论文评审过程：Received 16 October 2013, Revised 6 April 2014, Accepted 12 June 2014, Available online 27 June 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2014.06.010
