Nowadays, geographical coordinates (geo-tags), social annotations (tags), and low-level features are available in large image datasets. In our paper, we exploit these three kinds of image descriptions to suggest possible annotations for new images uploaded to a social tagging system. In order to compare the benefits each of these description types brings to a tag recommender system on its own, we investigate them independently of each other. First, the existing data collection is clustered separately for the geographical coordinates, tags, and low-level features. Additionally, random clustering is performed in order to provide a baseline for experimental results. Once a new image has been uploaded to the system, it is assigned to one of the clusters using either its geographical or low-level representation. Finally, the most representative tags for the resulting cluster are suggested to the user for annotation of the new image. Large-scale experiments performed for more than 400,000 images compare the different image representation techniques in terms of precision and recall in tag recommendation.
%0 Conference Paper
%1 Abbasi2009LST
%A Abbasi, Rabeeh
%A Grzegorzek, Marcin
%A Staab, Steffen
%B Semantic Multimedia
%D 2009
%I Springer Berlin / Heidelberg
%K 2009 folksonomies geo lowlevel recommendation samt tag tags
%P 65--76
%R 10.1007/978-3-642-10543-2_8
%T Large Scale Tag Recommendation Using Different Image Representations
%U http://www.springerlink.com/content/k2476uxvq123j101/
%V 5887
%X Nowadays, geographical coordinates (geo-tags), social annotations (tags), and low-level features are available in large image datasets. In our paper, we exploit these three kinds of image descriptions to suggest possible annotations for new images uploaded to a social tagging system. In order to compare the benefits each of these description types brings to a tag recommender system on its own, we investigate them independently of each other. First, the existing data collection is clustered separately for the geographical coordinates, tags, and low-level features. Additionally, random clustering is performed in order to provide a baseline for experimental results. Once a new image has been uploaded to the system, it is assigned to one of the clusters using either its geographical or low-level representation. Finally, the most representative tags for the resulting cluster are suggested to the user for annotation of the new image. Large-scale experiments performed for more than 400,000 images compare the different image representation techniques in terms of precision and recall in tag recommendation.
%@ 978-3-642-10542-5
@inproceedings{Abbasi2009LST,
abstract = {Nowadays, geographical coordinates (geo-tags), social annotations (tags), and low-level features are available in large image datasets. In our paper, we exploit these three kinds of image descriptions to suggest possible annotations for new images uploaded to a social tagging system. In order to compare the benefits each of these description types brings to a tag recommender system on its own, we investigate them independently of each other. First, the existing data collection is clustered separately for the geographical coordinates, tags, and low-level features. Additionally, random clustering is performed in order to provide a baseline for experimental results. Once a new image has been uploaded to the system, it is assigned to one of the clusters using either its geographical or low-level representation. Finally, the most representative tags for the resulting cluster are suggested to the user for annotation of the new image. Large-scale experiments performed for more than 400,000 images compare the different image representation techniques in terms of precision and recall in tag recommendation.},
added-at = {2009-12-09T10:33:04.000+0100},
author = {Abbasi, Rabeeh and Grzegorzek, Marcin and Staab, Steffen},
biburl = {https://www.bibsonomy.org/bibtex/27de70a9af28874ff06d407c0f1d2697c/rabeeh},
booktitle = {Semantic Multimedia},
doi = {10.1007/978-3-642-10543-2_8},
interhash = {e22e59a9d76b06554394ad23fdf3d67e},
intrahash = {7de70a9af28874ff06d407c0f1d2697c},
isbn = {978-3-642-10542-5},
issn = {0302-9743 (Print) 1611-3349 (Online)},
keywords = {2009 folksonomies geo lowlevel recommendation samt tag tags},
pages = {65--76},
publisher = {Springer Berlin / Heidelberg},
series = {Lecture Notes in Computer Science},
subject_collection = {Computer Science},
timestamp = {2009-12-09T10:35:33.000+0100},
title = {Large Scale Tag Recommendation Using Different Image Representations},
url = {http://www.springerlink.com/content/k2476uxvq123j101/},
volume = 5887,
year = 2009
}