Multi-scale Deep Learning Architectures for Person Re-identification

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
Proceedings 2017 IEEE International Conference on Computer Vision, 2017
Issue Date:
2017-12-25
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
08237839.pdfPublished version1.36 MB
Adobe PDF
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.
Please use this identifier to cite or link to this item: