Deep manifold clustering based optimal pseudo pose representation (DMC-OPPR) for unsupervised person re-identification
作者：
Highlights：
• The salient contributions of this paper are as follows.
• Multi-clustering model to handle complex camera angles and poses.
• Cam-pose wise optimal similarity distance threshold determination.
• Cam-pose parameter representation for a incremental self-learning model.
• Evaluation with reduced per pose similar samples to simulate real-world setup.
摘要
The salient contributions of this paper are as follows.•Multi-clustering model to handle complex camera angles and poses.•Cam-pose wise optimal similarity distance threshold determination.•Cam-pose parameter representation for a incremental self-learning model.•Evaluation with reduced per pose similar samples to simulate real-world setup.
论文关键词：Person re-identification,Clustering,Pose estimation,Representation,Computer vision,Deep learning
论文评审过程：Received 13 May 2020, Revised 23 May 2020, Accepted 31 May 2020, Available online 9 June 2020, Version of Record 22 June 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2020.103956
