Learning Context Graph for Person Search
This work addresses person search for surveillance and security applications, offering an incremental improvement by integrating context into existing frameworks.
The paper tackles the problem of person search in difficult conditions like varying illumination, pose, and occlusion by employing context information through a contextual instance expansion module and a graph learning framework, achieving state-of-the-art performance on two widely used datasets.
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.