Combining multi-resolution evidence for georeferencing Flickr images

Authors:
Olivier Van Laere;Steven Schockaert;Bart Dhoedt
Affiliations:
Department of Information Technology, Ghent University, IBBT, Belgium;Dept. of Applied Mathematics and Computer Science, Ghent University, Belgium;Department of Information Technology, Ghent University, IBBT, Belgium
Venue:
SUM'10 Proceedings of the 4th international conference on Scalable uncertainty management
Year:
2010

Citing 12
Cited 5

A simple view of the Dempster-Shafer theory of evidence and its implication for the rule of combination

AI Magazine
On the Dempster-Shafer framework and new combination rules

Information Sciences: an International Journal
Combining the results of several neural network classifiers

Neural Networks
Multiple evidence combination in image retrieval: Diogenes searches for people on the Web

SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
A study of smoothing methods for language models applied to information retrieval

ACM Transactions on Information Systems (TOIS)
World explorer: visualizing aggregate data from unstructured text in geo-referenced collections

Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries
Mapping the world's photos

Proceedings of the 18th international conference on World wide web
Placing flickr photos on a map

Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
A new technique for combining multiple classifiers using the dempster-shafer theory of evidence

Journal of Artificial Intelligence Research
Towards ontology learning from folksonomies

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Towards automated georeferencing of Flickr photos

Proceedings of the 6th Workshop on Geographic Information Retrieval
Geotagging: using proximity, sibling, and prominence clues to understand comma groups

Proceedings of the 6th Workshop on Geographic Information Retrieval

Geo-Location estimation of flickr images: social web based enrichment

ECIR'12 Proceedings of the 34th European conference on Advances in Information Retrieval
Placing images on the world map: a microblog-based enrichment approach

SIGIR '12 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval
Georeferencing Flickr photos using language models at different levels of granularity: An evidence based approach

Web Semantics: Science, Services and Agents on the World Wide Web
Georeferencing Flickr resources based on textual meta-data

Information Sciences: an International Journal
A study on the accuracy of Flickr's geotag data

Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

We explore the task of determining the geographic location of photos on Flickr, using combined evidence from Naive Bayes classifiers that are trained at different spatial resolutions. In particular, we estimate the location of Flickr photos, based on their tags, at four different scales, ranging from a city-level granularity to fine-grained intracity areas. Using Dempster-Shafer's evidence theory, we combine the output of the different classifiers into a single mass assignment. We demonstrate experimentally that the induced belief and plausibility measures are useful to determine whether there is sufficient evidence to classify the photo at a given granularity. Thus an adaptive method is obtained, by which photos are georeferenced at the most appropriate resolution.