Re-id: Hunting Attributes in the Wild
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.1
Abstract
Person re-identification is a crucial capability underpinning many applications of public-space video surveillance. Recent studies have shown the value of learning semantic attributes as a discriminative representation for re-identification. However, existing attribute representations do not generalise across camera deployments. Thus, this strategy currently requires the prohibitive effort of annotating a vector of person attributes for each individual in a large training set -- for each given deployment/dataset. In this paper we take a different approach and automatically discover a semantic attribute ontology, and learn an effective associated representation by crawling large volumes of internet data. In addition to eliminating the necessity for per-dataset annotation, by training on a much larger and more diverse array of examples this representation is more view-invariant and generalisable than attributes trained at conventional small scales. We show that these automatically discovered attributes provide a valuable representation that significantly improves re-identification performance on a variety of challenging datasets.
Session
Person Detection and Identification
Files
Extended Abstract (PDF, 1 page, 503K)Paper (PDF, 12 pages, 3.9M)
Bibtex File
Presentation
Citation
Ryan Layne, Tim Hospedales, and Shaogang Gong. Re-id: Hunting Attributes in the Wild. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.1
title = {Re-id: Hunting Attributes in the Wild},
author = {Layne, Ryan and Hospedales, Tim and Gong, Shaogang},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.1 }
}