Attributes driven tracklet-to-tracklet person re-identification using latent prototypes space mapping
作者：
Highlights：
• Different from most of current person re-identification works, our work focus on tracklet-to- tracklet identification under multi-camera setting.
• We learn and consider the contextual relations among human attributes, and validate that such cues help person re-identification tasks.
• Our learning framework establishes a discriminative feature representation by leveraging the relations between attributes and low-level features within a latent space.
摘要
Highlights•Different from most of current person re-identification works, our work focus on tracklet-to- tracklet identification under multi-camera setting.•We learn and consider the contextual relations among human attributes, and validate that such cues help person re-identification tasks.•Our learning framework establishes a discriminative feature representation by leveraging the relations between attributes and low-level features within a latent space.
论文关键词：Tracklet-to-tracklet,Person re-identification,Attributes,Latent prototypes space,Attribute correlations
论文评审过程：Received 20 July 2016, Revised 2 January 2017, Accepted 4 January 2017, Available online 5 January 2017, Version of Record 12 March 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.01.006
