Multimodal Information Approaches for the Wikipedia Collection at Imageclef 2011

From Wikipedia Quality
Revision as of 13:34, 22 December 2019 by Isabella (talk | contribs) (Multimodal Information Approaches for the Wikipedia Collection at Imageclef 2011 -- new article)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Multimodal Information Approaches for the Wikipedia Collection at Imageclef 2011 - scientific work related to Wikipedia quality published in 2011, written by Ruben Granados, Joan Benavent, Xaro Benavent, Esther de Ves and Ana García-Serrano.

Overview

The main goal of this paper it is to present experiments in ImageCLEF 2011 Campaign (Wikipedia retrieval task). This edition authors focused on applying different strategies of merging multimodal information, textual and visual, following both early and late fusion approaches. Authors best runs are in the top ten of the global list, at positions 8, 9 and 10 with MAP 0.3405, 0.3367 and 0.323, being the second best group of the contest. Moreover, 18 of the 20 runs submitted are above the average MAP of its own modality (textual or mixed). In system, the TBIR module works firstly and acts as a filter, and the CBIR system works only with the filtered sub-collection. The two ranked lists are fused using its own probability in a final ranked list. The best run of the TBIR system is in position 14 with a MAP of 0.3044, and uses subsystems IDRA and Lucene, fusing monolingual experiments carried out with IDRA preprocessing and Lucene search engine, taking into account extra information from Wikipedia articles. The best result at the CBIR system is obtained by using a logistic regression relevance feedback algorithm and CEDD