“…Nowadays, intelligent video surveillance technology has been widely deployed [1,2]. Pedestrian attributes, such as age, clothing style, gender, and accessary, are important soft-biometrics in video surveillance applications, such as person re-identification [3,4,5,6], person search [7,8], human parsing [9], and pedestrian detection [10,11]. Thus, the recognition of them, called Pedestrian Attribute Recognition (PAR), has received great attention in recent years.…”