Learning Context Graph for Person Search
arXiv:1904.01830
Abstract
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.
To appear in CVPR 2019
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- A Discriminatively Learned CNN Embedding for Person Re-identification
- Video Salient Object Detection via Fully Convolutional Networks
- Few-Shot Learning with Graph Neural Networks
- GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
- Pose Invariant Embedding for Deep Person Re-identification
- Learning Correspondence Structures for Person Re-identification