Concept Content based Wikipedia Web Image Retrieval Using Clef Vcdt 2008
Authors | Zhong-Qiu Zhao Hervé Glotin |
---|---|
Publication date | 2008 |
Links | Original |
Concept Content based Wikipedia Web Image Retrieval Using Clef Vcdt 2008 - scientific work related to Wikipedia quality published in 2008, written by Zhong-Qiu Zhao and Hervé Glotin.
Overview
One challenge for this Wikipedia task is the training of visual models. Authors propose in this paper to link each topics one or few visual concepts of the Visual Concept Detection (VCDT) CLEFimage08 task, even if three topics do not t VCDT concepts. Authors use the same models and features than in VCDT systems. Authors show that visual IMG NOFB run is the second best model in this campaign for this run type. So it can be concluded that VCDT visual concept partly t this task. Moreover authors show that even a simple boolean text analysis overcomes the best IMG NO FEEDBACK run, which has 0.0037 MAP, against 0.399 for TXT NOFB text run. This emphases the fact that visual retrieval for Wiki task is very dicult.
Embed
Wikipedia Quality
Zhao, Zhong-Qiu; Glotin, Hervé. (2008). "[[Concept Content based Wikipedia Web Image Retrieval Using Clef Vcdt 2008]]".
English Wikipedia
{{cite journal |last1=Zhao |first1=Zhong-Qiu |last2=Glotin |first2=Hervé |title=Concept Content based Wikipedia Web Image Retrieval Using Clef Vcdt 2008 |date=2008 |url=https://wikipediaquality.com/wiki/Concept_Content_based_Wikipedia_Web_Image_Retrieval_Using_Clef_Vcdt_2008}}
HTML
Zhao, Zhong-Qiu; Glotin, Hervé. (2008). "<a href="https://wikipediaquality.com/wiki/Concept_Content_based_Wikipedia_Web_Image_Retrieval_Using_Clef_Vcdt_2008">Concept Content based Wikipedia Web Image Retrieval Using Clef Vcdt 2008</a>".