Mapping the world's photos
Published 20 April 2009
David Crandall, Lars Bäckström, Daniel P. Huttenlocher, Jon Kleinberg
Citations777
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work uses the spatial distribution of where people take photos to define a relational structure between the photos that are taken at popular places, and finds that visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual features.
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.
Keywords
Computer ScienceEngineering
International Journal of Computer VisionDistinctive Image Features from Scale-Invariant Keypoints
55,266 Citations2004David Lowe
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
IEEE Transactions on Pattern Analysis and Machine IntelligenceNormalized cuts and image segmentation
15,696 Citations2000Jianbo Shi, Jitendra Malik
IEEE Transactions on Pattern Analysis and Machine IntelligenceMean shift: a robust approach toward feature space analysis
11,282 Citations2002Dorin Comaniciu, Peter Meer
It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.
International Journal of Computer VisionModeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
6,410 Citations2001Aude Oliva, Antonio Torralba
The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.
International Conference on Neural Information ProcessingAdvances in kernel methods: support vector learning
5,815 Citations1999Bernhard Schölkopf, Christopher J. C. Burges +1 more
Support vector machines for dynamic reconstruction of a chaotic system, Klaus-Robert Muller et al pairwise classification and support vector machines, Ulrich Kressel.
Technical reportsMaking Large-Scale SVM Learning Practical
4,317 Citations2006Thorsten Joachims
This chapter presents algorithmic and computational results developed for SVM light V 2.0, which make large-scale SVM training more practical and give guidelines for the application of SVMs to large domains.
Visual categorization with bags of keypoints
4,147 Citations2004G. Csurka
Journal of Information ScienceUsage patterns of collaborative tagging systems
1,830 Citations2006Scott A. Golder, Bernardo A. Huberman
A dynamic model of collaborative tagging is presented that predicts regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given URL.
Structure and evolution of online social networks
1,094 Citations2006Ravi Kumar, Jasmine Novak +1 more
A simple model of network growth is presented, characterizing users as either passive members of the network; inviters who encourage offline friends and acquaintances to migrate online; and linkers who fully participate in the social evolution of thenetwork.
Computer NetworksTrawling the Web for emerging cyber-communities
1,010 Citations1999Ravi Kumar, Prabhakar Raghavan +2 more
The subject of this paper is the systematic enumeration of over 100,000 emerging communities from a Web crawl, motivating a graph-theoretic approach to locating such communities, and describing the algorithms and algorithmic engineering necessary to find structures that subscribe to this notion.
IM2GPS: estimating geographic information from a single image
890 Citations2008James Hays, Alexei A. Efros
This paper proposes a simple algorithm for estimating a distribution over geographic locations from a single image using a purely data-driven scene matching approach and shows that geolocation estimates can provide the basis for numerous other image understanding tasks such as population density estimation, land cover estimation or urban/rural classification.
HT06, tagging paper, taxonomy, Flickr, academic article, to read
876 Citations2006Cameron Marlow, Mor Naaman +2 more
A model of tagging systems, specifically in the context of web-based systems, is offered to help illustrate the possible benefits of these tools and a simple taxonomy of incentives and contribution models is provided to inform potential evaluative frameworks.
arXiv (Cornell University)The Structure of Collaborative Tagging Systems
837 Citations2005Scott A. Golder, Bernardo A. Huberman
A dynamical model of collaborative tagging is presented that predicts regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given url.
Microscopic evolution of social networks
733 Citations2008Jure Leskovec, Lars Bäckström +2 more
A complete model of network evolution, where nodes arrive at a prespecified rate and select their lifetimes, and the combination of the gap distribution with the node lifetime leads to a power law out-degree distribution that accurately reflects the true network in all four cases is presented.
Scene completion using millions of photographs
731 Citations2007James Hays, Alexei A. Efros
tagging, communities, vocabulary, evolution
401 Citations2006Shilad Sen, Shyong K. Lam +6 more
A user-centric model of vocabulary evolution in tagging communities based on community influence and personal tendency is presented and evaluated in an emergent tagging system by introducing tagging features into the MovieLens recommender system.
Generating diverse and representative image search results for landmarks
390 Citations2008Lyndon S. Kennedy, Mor Naaman
This work uses a combination of context- and content-based tools to generate representative sets of images for location-driven features and landmarks, a common search task.
Visualizing the Signatures of Social Roles in Online Discussion Groups
358 Citations2007Howard T. Welser, Eric Gleave +2 more
This paper uses visualization methods to reveal structural signatures and regression analysis to confirm the relationship between these signatures and their associated roles in Usenet newsgroups, finding that answer people predominantly contribute one or a few messages to discussions initiated by others.
Scene Summarization for Online Image Collections
348 Citations2007Ian Simon, Noah Snavely +1 more
This work proposes a solution to the problem of scene summarization by examining the distribution of images in the collection to select a set of canonical views to form the scene summary, using clustering techniques on visual features.
NatureThe generic viewpoint assumption in a framework for visual perception
251 Citations1994William T. Freeman
The generic view assumption is used to quantify the likelihood of a view, adding a new term to the probability of a given image interpretation, which better models the visual world and reduces the reliance on other prior assumptions.
World explorer
247 Citations2007Shane Ahern, Mor Naaman +2 more
This work analyzes the tags associated with the geo-referenced Flickr images to generate aggregate knowledge in the form of "representative tags" for arbitrary areas in the world, and uses these tags to create a visualization tool, World Explorer, that can help expose the content of the data, using a map interface to display the derived tags and the original photo items.
Measuring social networks with digital photograph collections
30 Citations2008Scott A. Golder
Results from an analysis of 23 subjects' photo collections demonstrate the feasibility of how digital photo collections can provide useful data for the study of social networks.