Presentation 2008-03-13
Study of Individual Preference Identification to Face Image with Subjective Meta Information
Shinpei MASUDA, Hideyuki TAKAHASHI, Masahito KURIHARA, Koichiro YAMAUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Today, there are various data-searching systems such as used in the google search engine. Almost all of these systems search data according to an explicit meta-information, which specify the class or attribute of the data. The explicit meta-information usually consists of some keywords or feature vectors. However, there are no guarantees that the keywords or feature vectors represent the precise preference of human. To overcome this problem, we proposed an individual preference identification system uses a new subjective meta-information which is constructed from questionnaire data. Experimental results show that the subjective meta-information represents user's preferences well so that it is useful for constructing recommendation systems. Moreover, we investigated what are the important components in the meta-information to identify his/her preferences.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) meta-information / recommendation of image / feeling / preference identification
Paper # NC2007-160
Date of Issue

Conference Information
Committee NC
Conference Date 2008/3/5(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study of Individual Preference Identification to Face Image with Subjective Meta Information
Sub Title (in English)
Keyword(1) meta-information
Keyword(2) recommendation of image
Keyword(3) feeling
Keyword(4) preference identification
1st Author's Name Shinpei MASUDA
1st Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University()
2nd Author's Name Hideyuki TAKAHASHI
2nd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
3rd Author's Name Masahito KURIHARA
3rd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
4th Author's Name Koichiro YAMAUCHI
4th Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
Date 2008-03-13
Paper # NC2007-160
Volume (vol) vol.107
Number (no) 542
Page pp.pp.-
#Pages 6
Date of Issue