TY - GEN
T1 - Unsupervised graph association for person re-identification
AU - Wu, Jinlin
AU - Liu, Hao
AU - Yang, Yang
AU - Lei, Zhen
AU - Liao, Shengcai
AU - Li, Stan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - In this paper, we propose an unsupervised graph association (UGA) framework to learn the underlying viewinvariant representations from the video pedestrian tracklets. The core points of UGA are mining the underlying cross-view associations and reducing the damage of noise associations. To this end, UGA is adopts a two-stage training strategy: (1) intra-camera learning stage and (2) intercamera learning stage. The former learns the intra-camera representation for each camera. While the latter builds a cross-view graph (CVG) to associate different cameras. By doing this, we can learn view-invariant representation for all person. Extensive experiments and ablation studies on seven re-id datasets demonstrate the superiority of the proposed UGA over most state-of-the-art unsupervised and domain adaptation re-id methods.
AB - In this paper, we propose an unsupervised graph association (UGA) framework to learn the underlying viewinvariant representations from the video pedestrian tracklets. The core points of UGA are mining the underlying cross-view associations and reducing the damage of noise associations. To this end, UGA is adopts a two-stage training strategy: (1) intra-camera learning stage and (2) intercamera learning stage. The former learns the intra-camera representation for each camera. While the latter builds a cross-view graph (CVG) to associate different cameras. By doing this, we can learn view-invariant representation for all person. Extensive experiments and ablation studies on seven re-id datasets demonstrate the superiority of the proposed UGA over most state-of-the-art unsupervised and domain adaptation re-id methods.
UR - http://www.scopus.com/inward/record.url?scp=85081937462&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081937462&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2019.00841
DO - 10.1109/ICCV.2019.00841
M3 - Conference contribution
AN - SCOPUS:85081937462
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 8320
EP - 8329
BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Y2 - 27 October 2019 through 2 November 2019
ER -