Hanjae Kim Sunghun Joung KIM, IG JAE Kwanghoon Sohn 2024-01-12T03:46:08Z 2024-01-12T03:46:08Z 2021-09-29 2021-06 1063-6919 https://pubs.kist.re.kr/handle/201004/77404 Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this imitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-ofthe-art results on two person search benchmarks including CUHK-SYSU and PRW. English IEEE COMPUTER SOC 재식별 사람 추적 Saliency Prototype-Guided Saliency Feature Learning for Person Search Conference 10.1109/CVPR46437.2021.00483 1 CVPR, IEEE conf. on Computer Vision and Pattern Recognition, pp.4863 - 4872 CVPR, IEEE conf. on Computer Vision and Pattern Recognition 4863 4872 US online 2021-06-19 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 000739917305007 2-s2.0-85114189688