Improving tag-based image search by using linked open data

Authors:
M. B. Alves;C. V. Damásio;N. Correia
Affiliations:
ESTG, Instituto Politécnico de, Viana do Castelo;CENTRIA, Universidade Nova de Lisboa, Caparica, Portugal;CITI, Universidade Nova de Lisboa, Caparica, Portugal
Venue:
Proceedings of the 10th Conference on Open Research Areas in Information Retrieval
Year:
2013

Citing 8
Cited 0

WordNet: a lexical database for English

Communications of the ACM
Introduction to Information Retrieval

Introduction to Information Retrieval
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
The MIR flickr retrieval evaluation

MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
DBpedia: a nucleus for a web of open data

ISWC'07/ASWC'07 Proceedings of the 6th international The semantic web and 2nd Asian conference on Asian semantic web conference
A Developers Guide to the Semantic Web

A Developers Guide to the Semantic Web
Semantic hierarchies for image annotation: A survey

Pattern Recognition
All vehicles are cars: subclass preferences in container concepts

Proceedings of the 2nd ACM International Conference on Multimedia Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work, we combine existing linked open data ontologies with image tag-based search in order to allow image retrieval by high-level concepts specified in the Semantic Web. In this way, we move in the direction of obtaining a large-scale ontology of images with a cheap cost comparing with solutions that require human intervention. A novel search method is described and evaluated with respect to simple image tag-based search, with promising results.