State-of-the-Art Deep Person Re-identification: A Review

Recently, deep learning has achieved great success in person re-identification (ReID). This paper aims to review the state-of-the-art person ReID algorithms based on deep learning. In terms of different application problems in person ReID, the algorithms presented are roughly divided into three categories, i.e., image-based person ReID, video-based person ReID, unsupervised person ReID. For each category, we review the most representative research works in recent years. Our survey aims to address existing problems, challenges and future research directions based on the analyses of the current latest advancements made toward deep learning based person ReID techniques.