Learning Context Graph for Person Search

Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2158-2167


Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.

Related Material

author = {Yan, Yichao and Zhang, Qiang and Ni, Bingbing and Zhang, Wendong and Xu, Minghao and Yang, Xiaokang},
title = {Learning Context Graph for Person Search},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}