Skip to main content
Journal cover image

IAN: The Individual Aggregation Network for Person Search

Publication ,  Journal Article
Xiao, J; Xie, Y; Tillo, T; Huang, K; Wei, Y; Feng, J
Published in: Pattern Recognition
March 1, 2019

Person search in real-world scenarios is a new challenging computer version task with many meaningful applications. The challenge of this task mainly comes from: (1) unavailable bounding boxes for pedestrians and the model needs to search for the person over the whole gallery images; (2) huge variance of visual appearance of a particular person owing to varying poses, lighting conditions, and occlusions. To address these two critical issues in modern person search applications, we propose a novel Individual Aggregation Network (IAN) that can accurately localize persons by learning to minimize intra-person feature variations. IAN is built upon the state-of-the-art object detection framework, i.e., faster R-CNN, so that high-quality region proposals for pedestrians can be produced in an online manner. In addition, to relieve the negative effect caused by varying visual appearances of the same individual, IAN introduces a novel center loss that can increase the intra-class compactness of feature representations. The engaged center loss encourages persons with the same identity to have similar feature characteristics. Extensive experimental results on two benchmarks, i.e., CUHK-SYSU and PRW, well demonstrate the superiority of the proposed model. In particular, IAN achieves 77.23% mAP and 80.45% top-1 accuracy on CUHK-SYSU, which outperform the state-of-the-art by 1.7% and 1.85%, respectively.

Duke Scholars

Published In

Pattern Recognition

DOI

ISSN

0031-3203

Publication Date

March 1, 2019

Volume

87

Start / End Page

332 / 340

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4611 Machine learning
  • 4605 Data management and data science
  • 4603 Computer vision and multimedia computation
  • 0906 Electrical and Electronic Engineering
  • 0806 Information Systems
  • 0801 Artificial Intelligence and Image Processing
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Xiao, J., Xie, Y., Tillo, T., Huang, K., Wei, Y., & Feng, J. (2019). IAN: The Individual Aggregation Network for Person Search. Pattern Recognition, 87, 332–340. https://doi.org/10.1016/j.patcog.2018.10.028
Xiao, J., Y. Xie, T. Tillo, K. Huang, Y. Wei, and J. Feng. “IAN: The Individual Aggregation Network for Person Search.” Pattern Recognition 87 (March 1, 2019): 332–40. https://doi.org/10.1016/j.patcog.2018.10.028.
Xiao J, Xie Y, Tillo T, Huang K, Wei Y, Feng J. IAN: The Individual Aggregation Network for Person Search. Pattern Recognition. 2019 Mar 1;87:332–40.
Xiao, J., et al. “IAN: The Individual Aggregation Network for Person Search.” Pattern Recognition, vol. 87, Mar. 2019, pp. 332–40. Scopus, doi:10.1016/j.patcog.2018.10.028.
Xiao J, Xie Y, Tillo T, Huang K, Wei Y, Feng J. IAN: The Individual Aggregation Network for Person Search. Pattern Recognition. 2019 Mar 1;87:332–340.
Journal cover image

Published In

Pattern Recognition

DOI

ISSN

0031-3203

Publication Date

March 1, 2019

Volume

87

Start / End Page

332 / 340

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4611 Machine learning
  • 4605 Data management and data science
  • 4603 Computer vision and multimedia computation
  • 0906 Electrical and Electronic Engineering
  • 0806 Information Systems
  • 0801 Artificial Intelligence and Image Processing