论文信息 - SINAI at VideoCLEF 2008

SINAI at VideoCLEF 2008

This paper describes the flrst participation of the SINAI research group in the VideoCLEF 2008 track. We have only submitted runs for the classiflcation task on Dutch and English languages. Our approach has consisted in the use of a particular Information Retrieval system as classiflcation architecture, using the speech transcriptions as textual queries and generating textual corpus for each topic class. In order to generate this textual corpus we have used the Google 1 search engine. The experiments show that an IR system can perform well as classifler of multilingual videos, using their speech transcriptions and obtaining good results.

Luis Alfonso Ureña López | José Manuel Perea Ortega | Manuel Carlos Díaz-Galiano | María Teresa Martín-Valdivia | Arturo Montejo Ráez

[1] Martin F. Porter,et al. An algorithm for suffix stripping , 1997, Program.

[2] Luis Alfonso Ureña López,et al. SINAI at TRECVID 2007 , 2007, TRECVID.

[3] Michael McGill,et al. Introduction to Modern Information Retrieval , 1983 .

[4] Carol Peters. Cross-Language Evaluation Forum - CLEF 2006 , 2006 .

[5] Miguel Ángel García Cumbreras,et al. SINAI at ImageCLEF 2005 , 2005, CLEF.

[6] L. A. Ureña-López,et al. SINAI at ImageCLEF 2007 , 2007 .

[7] Miguel Ángel García Cumbreras,et al. SINAI at ImageCLEF 2006 , 2006, CLEF.

[8] Miguel A. García-Cumbreras,et al. SINAI at CLEF Ad-Hoc Robust Track 2007: Applying Google Search Engine for Robust Cross-Lingual Retrieval , 2008 .