MMIS at ImageCLEF 2008: experiments combining different evidence sources

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.

URL: http://www.academia.edu/634939/MMIS_at_ImageCLEF_2...

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.

Viewing alternatives

Item Actions

Export

You can export this page using these formats