Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
arXiv:1710.06555
Abstract
Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a fundamental problem in ReID and is still an open problem today. In this paper, we design a Multi-Scale Context-Aware Network (MSCAN) to learn powerful features over full body and body parts, which can well capture the local context knowledge by stacking multi-scale convolutions in each layer. Moreover, instead of using predefined rigid parts, we propose to learn and localize deformable pedestrian parts using Spatial Transformer Networks (STN) with novel spatial constraints. The learned body parts can release some difficulties, eg pose variations and background clutters, in part-based representation. Finally, we integrate the representation learning processes of full body and body parts into a unified framework for person ReID through multi-class person identification tasks. Extensive evaluations on current challenging large-scale person ReID datasets, including the image-based Market1501, CUHK03 and sequence-based MARS datasets, show that the proposed method achieves the state-of-the-art results.
arXiv commentAccepted by CVPR 2017
References in corpus (9)
- Deep Residual Learning for Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Multi-Scale Context Aggregation by Dilated Convolutions
- Person Re-identification: Past, Present and Future
- PersonNet: Person Re-identification with Deep Convolutional Neural Networks
- A Richly Annotated Dataset for Pedestrian Attribute Recognition
- Person Re-identification in the Wild
- Crafting GBD-Net for Object Detection
- DARI: Distance metric And Representation Integration for Person Verification
Cited by in corpus (7)
- STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification
- A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
- CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
- Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
- Support Neighbor Loss for Person Re-Identification
- Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology
- Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification