Multi-scale Deep Learning Architectures for Person Re-identification
arXiv:1709.05165
Abstract
Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks
9 pages, 3 figures, accepted by ICCV 2017
References in corpus (5)
Cited by in corpus (9)
- Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
- Survey on Deep Learning Techniques for Person Re-Identification Task
- Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?
- Person Re-identification with Deep Similarity-Guided Graph Neural Network
- End-to-End Deep Kronecker-Product Matching for Person Re-identification
- Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification
- Omni-directional Feature Learning for Person Re-identification
- Person Re-identification in Videos by Analyzing Spatio-Temporal Tubes
- FTN: Foreground-Guided Texture-Focused Person Re-Identification