PixGeo: Geographically Grounding Touristic Personal Photographs

Authors:
Rodrigo F. Carvalho;Fabio Ciravegna
Affiliations:
Dept. of Computer Science, Organisations, Information and Knowledge group (OAK), The University of Sheffield, Sheffield, UK S1 4DP;Dept. of Computer Science, Organisations, Information and Knowledge group (OAK), The University of Sheffield, Sheffield, UK S1 4DP
Venue:
SAMT '09 Proceedings of the 4th International Conference on Semantic and Digital Media Technologies: Semantic Multimedia
Year:
2009

Citing 10
Cited 0

Requirements for photoware

CSCW '02 Proceedings of the 2002 ACM conference on Computer supported cooperative work
Advances in Instance Selection for Instance-Based Learning Algorithms

Data Mining and Knowledge Discovery
Understanding photowork

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Give and take: a study of consumer photo-sharing culture and practice

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Spirittagger: a geo-aware tag suggestion tool mined from flickr

MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Attributing semantics to personal photographs

Multimedia Tools and Applications
Mapping the world's photos

Proceedings of the 18th international conference on World wide web
Understanding context before using it

CONTEXT'05 Proceedings of the 5th international conference on Modeling and Using Context
Automatic person annotation of family photo album

CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
Color and texture descriptors

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.01

Visualization

Abstract

Realizing the potential of digital media in the home relies on the existence of detailed, semantically unambiguous metadata. However, in the domain of personal photography, the generation of such metadata remains an unsolved issue. This paper introduces PixGeo, a solution to geographically grounding touristic personal photographs based on exploiting the existence of strong contextual connections among photographs in a user's collection. We experiment with building temporal clusters within test collections and leverage an 8 million image dataset from Flickr to perform scene matching using k -NN. In the evaluation we find that the approach performs 30% better than chance for grounding photos.