creators_name: Crandall, David
creators_name: Backstrom, Lars
creators_name: Huttenlocher, Daniel
creators_name: Kleinberg, Jon
type: conference_item
datestamp: 2009-04-06 19:10:49
lastmod: 2009-04-07 14:02:34
metadata_visibility: show
title: Mapping the World's Photos
ispublished: pub
full_text_status: public
pres_type: paper
abstract: We investigate how to organize a large collection of geotagged photos, working with a dataset of about 35 million images collected from Flickr. Our approach combines content analysis based on text tags and image data with structural analysis based on geospatial data. We use the spatial distribution of where people take photos to define a relational structure between the photos that are taken at popular places. We then study the interplay between this structure and the content, using classification methods for predicting such locations from visual, textual and temporal features of the photos. We find that visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual features. We illustrate using these techniques to organize a large photo collection, while also revealing various interesting properties about popular cities and landmarks at a global scale.
date: 2009-04
pagerange: 761-761
event_title: 18th International World Wide Web Conference
event_location: Madrid, Spain
event_dates: April 20th-24th, 2009
event_type: conference
refereed: TRUE
citation: Crandall, David <http://www2009.eprints.org/view/author/Crandall=3ADavid=3A=3A.html> and Backstrom, Lars <http://www2009.eprints.org/view/author/Backstrom=3ALars=3A=3A.html> and Huttenlocher, Daniel <http://www2009.eprints.org/view/author/Huttenlocher=3ADaniel=3A=3A.html> and Kleinberg, Jon <http://www2009.eprints.org/view/author/Kleinberg=3AJon=3A=3A.html> (2009) Mapping the World's Photos. In: 18th International World Wide Web Conference, April 20th-24th, 2009, Madrid, Spain.
document_url: http://www2009.eprints.org/77/1/p761.pdf