Exploring the semantics behind a collection to improve automated image annotation
http://data.open.ac.uk/oro/23432
is a Article , Academic article

Outgoing links

Property Object
Creator
Dataset Open Research Online
Publisher Springer
At 10th Workshop of the Cross-Language Evaluation Forum (CLEF 2009)
Date 2009-10
Is part of repository
Status Peer reviewed
URI
  • http://data.open.ac.uk/oro/document/11046
  • http://data.open.ac.uk/oro/document/13296
  • http://data.open.ac.uk/oro/document/24968
  • http://data.open.ac.uk/oro/document/6045
Abstract The goal of this research is to explore several semantic relatedness measures that help to refine annotations generated by a baseline non-parametric density estimation algorithm. Thus, we analyse the benefits of performing a statistical correlation using the training set or using the World Wide Web versus approaches based on a thesaurus like WordNet or Wikipedia (considered as a hyperlink structure). Experiments are carried out using the dataset provided by the 2009 edition of the ImageCLEF competition, a subset of the MIR-Flickr 25k collection. Best results correspond to approaches based on statistical correlation as they do not depend on a prior disambiguation phase like WordNet and Wikipedia. Further work needs to be done to assess whether proper disambiguation schemas might improve their performance.
Authors authors
Type
Label Llorente, Ainhoa ; Motta, Enrico and Rüger, Stefan (2009). Exploring the semantics behind a collection to improve automated image annotation. In: Multilingual Information Access Evaluation II. Multimedia Experiments, Springer.
Title Exploring the semantics behind a collection to improve automated image annotation