Large Scale Tag Recommendation Using Different Image Representations

Authors:
Rabeeh Abbasi;Marcin Grzegorzek;Steffen Staab
Affiliations:
ISWeb - Information Systems and Semantic Web, University of Koblenz-Landau, Koblenz, Germany 56070;ISWeb - Information Systems and Semantic Web, University of Koblenz-Landau, Koblenz, Germany 56070;ISWeb - Information Systems and Semantic Web, University of Koblenz-Landau, Koblenz, Germany 56070
Venue:
SAMT '09 Proceedings of the 4th International Conference on Semantic and Digital Media Technologies: Semantic Multimedia
Year:
2009

Citing 8
Cited 2

Photobook: content-based manipulation of image databases

International Journal of Computer Vision
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
How flickr helps us make sense of the world: context and content in community-contributed media collections

Proceedings of the 15th international conference on Multimedia
Content visualization and management of geo-located image databases

CHI '08 Extended Abstracts on Human Factors in Computing Systems
Generating diverse and representative image search results for landmarks

Proceedings of the 17th international conference on World Wide Web
Image clustering based on a shared nearest neighbors approach for tagged collections

CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Social tag prediction

Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
Tag Recommendations in Folksonomies

PKDD 2007 Proceedings of the 11th European conference on Principles and Practice of Knowledge Discovery in Databases

One person labels one million images

Proceedings of the international conference on Multimedia
Conjunctive ranking function using geographic distance and image distance for geotagged image retrieval

Proceedings of the ACM multimedia 2012 workshop on Geotagging and its applications in multimedia

Quantified Score

Hi-index	0.00

Visualization

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.