VIRaL: Visual image retrieval and localization

Kalantidis, Y; Tolias, G; Avrithis, Y; Phinikettos, M; Spyrou, E; Mylonas, P; Kollias, S

dc.contributor.author	Kalantidis, Y	en
dc.contributor.author	Tolias, G	en
dc.contributor.author	Avrithis, Y	en
dc.contributor.author	Phinikettos, M	en
dc.contributor.author	Spyrou, E	en
dc.contributor.author	Mylonas, P	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T01:37:32Z
dc.date.available	2014-03-01T01:37:32Z
dc.date.issued	2011	en
dc.identifier.issn	1380-7501	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/21545
dc.subject	Geotagging	en
dc.subject	Image clustering	en
dc.subject	Image localization	en
dc.subject	Image retrieval	en
dc.subject	Landmark recognition	en
dc.subject	Location recognition	en
dc.subject	Sub-linear indexing	en
dc.subject.classification	Computer Science, Information Systems	en
dc.subject.classification	Computer Science, Software Engineering	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Geotagging	en
dc.subject.other	Image clustering	en
dc.subject.other	Image localization	en
dc.subject.other	Landmark recognition	en
dc.subject.other	Location recognition	en
dc.subject.other	Sub-linear indexing	en
dc.subject.other	Data processing	en
dc.subject.other	Image retrieval	en
dc.subject.other	Metadata	en
dc.subject.other	Mining	en
dc.subject.other	Indexing (of information)	en
dc.title	VIRaL: Visual image retrieval and localization	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/s11042-010-0651-7	en
heal.identifier.secondary	http://dx.doi.org/10.1007/s11042-010-0651-7	en
heal.language	English	en
heal.publicationDate	2011	en
heal.abstract	New applications are emerging every day exploiting the huge data volume in community photo collections. Most focus on popular subsets, e.g., images containing landmarks or associated to Wikipedia articles. In this work we are concerned with the problem of accurately finding the location where a photo is taken without needing any metadata, that is, solely by its visual content. We also recognize landmarks where applicable, automatically linking them to Wikipedia. We show that the time is right for automating the geo-tagging process, and we show how this can work at large scale. In doing so, we do exploit redundancy of content in popular locations-but unlike most existing solutions, we do not restrict to landmarks. In other words, we can compactly represent the visual content of all thousands of images depicting e.g., the Parthenon and still retrieve any single, isolated, non-landmark image like a house or a graffiti on a wall. Starting from an existing, geo-tagged dataset, we cluster images into sets of different views of the same scene. This is a very efficient, scalable, and fully automated mining process. We then align all views in a set to one reference image and construct a 2D scene map. Our indexing scheme operates directly on scene maps. We evaluate our solution on a challenging one million urban image dataset and provide public access to our service through our online application, VIRaL. © 2010 Springer Science+Business Media, LLC.	en
heal.publisher	SPRINGER	en
heal.journalName	Multimedia Tools and Applications	en
dc.identifier.doi	10.1007/s11042-010-0651-7	en
dc.identifier.isi	ISI:000286472300007	en
dc.identifier.volume	51	en
dc.identifier.issue	2	en
dc.identifier.spage	555	en
dc.identifier.epage	592	en