Abstract. In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification (re-ID).
Instead of sharing representations in a single joint model, we find that separating
detector and re-ID feature extraction yields better performance. In order to extract
more representative features for each identity, we propose a simple yet effective
re-ID method, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams.
On the standard person search benchmark datasets, we achieve mAP of 83.0%
and 32.6% respectively for CUHK-SYSU and PRW, surpassing the state of the
art by a large margin (more than 5pp).