Re-id: Hunting Attributes in the Wild

Ryan Layne, Tim Hospedales and Shaogang Gong

In Proceedings British Machine Vision Conference 2014


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.


Person Detection and Identification


Extended Abstract (PDF, 1 page, 503K)
Paper (PDF, 12 pages, 3.9M)
Bibtex File



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.


	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 = { }