Mapping the world's photos

By David J. Crandall, Lars Backstrom, Dan Huttenlocher, Jon M. Kleinberg. 2009

890 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

YFCC100M (2015, background): “In the past, geotagged media has been used to address a variety of research endeavors, such as location estimation [9], event detection [15], ﬁnding canonical views of places [4], and visual reconstruction of the world [17].”
Extracting and understanding urban areas of interest using geotagged photos (2015, methodology): “Besides, existing research shows that a major proportion of Flickr photos were taken in urban areas (Crandall et al. 2009, Hollenstein and Purves 2010), and this gives Flickr data one more advantage for studying urban AOI.”
Automatic construction of travel itineraries using social breadcrumbs (2010, methodology): “Note, apart from tags and geo-information, the visual features of photos can also be analyzed to reveal clues about its content [16, 8].”
Worldwide Pose Estimation Using 3D Point Clouds (2012, methodology): “We ﬁrst created a list of geotagged Flickr photos from the world’s top 1,000 landmarks derived via clustering on geotags by Crandall et al. [27].”
Exploring place through user-generated content: Using Flickr tags to describe city cores (2010, background): “Since data sets such as Flickr appear to be, at least at the moment, dominated by images taken in urban regions [5], then the question arises as to how people describe and name regions within cities through tags in everyday use.”
"OMG, from here, I can see the flames!": a use case of mining location based social networks to acquire spatio-temporal data on forest fires (2009, background): “As well as numeric and textual data, georeferenced pictures from the photo-sharing website Flickr have been processed in terms of their density to show where the most famous landmarks are for a given location [4].”
Uncovering social spammers: social honeypots + machine learning (2010, background): “These social systems have attracted a tremendous amount of media and research interest [1, 10, 18].”
Wide-Area Image Geolocalization with Aerial Reference Imagery (2015, background): “Even with hundreds of millions of geo-tagged ground-level images available via photo-sharing websites and social networks, there are still very large geographic regions with few images; most images are captured in cities and around famous landmarks [6].”
Visual landmark recognition from Internet photo collections: A large-scale evaluation (2014, methodology): “To find suitable descriptions for the discovered objects, and thus to enable linking them with information on the web, the usual method is to perform statistical analysis of the tags and titles that users provided for the photos in a cluster [9, 4, 10, 6].”
Geographical topic discovery and comparison (2011, methodology): “In recent years, some studies have been conducted on GPS-associated documents including organizing geo-tagged photos [4] and searching large geographical datasets [7].”
A Latent Variable Model for Geographic Lexical Variation (2010, background): “An active recent literature concerns geotagged information on the web, such as search queries (Back-strom et al., 2008) and tagged images (Crandall et al., 2009).”
Geolocation Prediction in Social Media Data by Finding Location Indicative Words (2012, methodology): “(Lieberman and Lin, 2009) and Flickr image tags (Crandall et al., 2009; Serdyukov et al., 2009; Hauff and Houben, 2012) have been used as the basis for geolocation prediction.”
You are where you tweet: a content-based approach to geo-locating twitter users (2010, background): “…from tweets of nearby Twitter users [21], the targeting of regional advertisements, spreading business information to local customers [3], and novel location-based applications (e.g., Twitter-based earthquake detection, which can be faster than through traditional official channels [18]).”
Spatial, temporal, and socioeconomic patterns in the use of Twitter and Flickr (2013, background): “As demonstrated in Figure 2, tweet locations roughly describe the administrative boundary of the United States and major roads at a very good resolution, which is similar to the representation of Flickr photos in other research (Crandall et al. 2009).”
Travel route recommendation using geotags in photo sharing sites (2010, methodology): “allows users to browse all of the world’s photographs on a single world map [17].”
Image sequence geolocation with human travel priors (2009, background): “[7] identify landmarks based on image data, metadata, and other photos taken within a 15-minute window.”
Web Data Extraction, Applications and Techniques: A Survey (2012, background): “[26] investigated how to organize a large collection of geotagged photos extracted from Flickr.”