MMIS at ImageCLEF 2008: experiments combining different evidence sources
http://data.open.ac.uk/oro/36073
is a Article , Academic article

Outgoing links

Property Object
Date 2008
Is part of repository
Status Peer reviewed
URI http://data.open.ac.uk/oro/document/113740
Abstract This paper presents the work of the MMIS group at ImageCLEF 2008. The results for three tasks are presented: Visual Concept Detection Task (VCDT), ImageCLEFphoto and ImageCLEFwiki. We combine image annotations, CBIR, textual relevanceand a geographic filter using our generic data fusion method. We also compare methodsfor BRF and clustering.Our top performing method in the VCDT enhances supervised learning by modifying probabilities based on a matrix that shows how terms appear together. Although it occurred in the top quartile of submitted runs, the enhancement did not provide a statistically significant improvement. In the ImageCLEFphoto task we demonstrate that evidence from image retrievalcan provide a contribution to retrieval; however we are yet to find a way of combining text and image evidence in a way to provide an improvement over the baseline. Due to the relative performances of difference evidences in ImageCLEFwiki and our failure to improve over a baseline we conclude that text is the dominant feature in this collection.
Authors authors
Type
Label Overell, Simon; Llorente, Ainhoa ; Liu, Haiming ; Hu, Rui ; Rae, Adam ; Zhu, Jianhan ; Song, Dawei and Rüger, Stefan (2008). MMIS at ImageCLEF 2008: experiments combining different evidence sources. In: CLEF workshop, 17-19 Sep 2008, Aarhus, Denmark.
Title MMIS at ImageCLEF 2008: experiments combining different evidence sources
Creator
Dataset Open Research Online
At CLEF workshop