Person Search via A Mask-Guided Two-Stream CNN Model

Abstract

In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification~(re-ID). Instead of sharing representations in a single joint model, we find that separating detector and re-ID feature extraction yields better performance. In order to extract more representative features for each identity, we segment out the foreground person from the original image patch. We propose a simple yet effective re-ID method, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams. From the experiments on two standard person search benchmarks of CUHK-SYSU and PRW, we achieve mAP of $83.0\%$ and $32.6\%$ respectively, surpassing the state of the art by a large margin (more than 5pp).

arXiv commentaccepted as poster to ECCV 2018

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Residual Learning for Image Recognition
• Harmonious Attention Network for Person Re-Identification
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• How Far are We from Solving Pedestrian Detection?
• CityPersons: A Diverse Dataset for Pedestrian Detection
• Filtered Channel Features for Pedestrian Detection
• Neural Person Search Machines
• IAN: The Individual Aggregation Network for Person Search

Cited by in corpus (7)

• Adaptive Exploration for Unsupervised Person Re-Identification
• Selective Kernel Networks
• Joint Detection and Tracking in Videos with Identification Features
• Dissecting Person Re-identification from the Viewpoint of Viewpoint
• SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
• Multi-Scale Body-Part Mask Guided Attention for Person Re-identification
• Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search