Presentation 2003/7/11
Extraction of image similarity by clustering of word vectors made from attached text and its evaluation
Keigo HIRAI, Ryuichi OKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a method to determine a similarity measure between images by using texts which are attached to images. A text is transformed a word vector. A clustering algorithm is applied to both a set of word vector and a set of vectors made from images independently. Then each pair data of image and text makes a linkage between clusters of two kinds. The proposed similarity is defined in a circle across clusters of two kinds by through of partition of image. Entry of a single image or text into the circle realizes an image retrieval.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) imaga retrieval / similarity measure / media integration / text clustering
Paper # PRMU2003-62,IE2003-32,MVE2003-44
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/7/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Extraction of image similarity by clustering of word vectors made from attached text and its evaluation
Sub Title (in English)
Keyword(1) imaga retrieval
Keyword(2) similarity measure
Keyword(3) media integration
Keyword(4) text clustering
1st Author's Name Keigo HIRAI
1st Author's Affiliation The University of Aizu Graduate School()
2nd Author's Name Ryuichi OKA
2nd Author's Affiliation The University of Aizu
Date 2003/7/11
Paper # PRMU2003-62,IE2003-32,MVE2003-44
Volume (vol) vol.103
Number (no) 208
Page pp.pp.-
#Pages 6
Date of Issue