Presentation 2015-01-22
Video Summarization Based on Contents Similarity between User Specified-description and Video
Mayu OTANI, Yuta NAKASHIMA, Tomokazu SATO, Naokazu YOKOYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Due to the wide spreading of camera devices, people record videos in everyday life, and such videos are sometimes shared through video blogs. Authoring video blog posts, however, is a time-consuming process which requires users to edit the videos to represent their intention. To facilitate creating videos, we propose a novel video summarization method that utilizes the text written by users. We formulate the problem of video summarization as an optimization problem, in which the objective function involves the content similarity between the summarized video and the text. We conduct a user study with 20 participants. Its result has shown that our proposed method is superior to conventional methods in terms of suitability to video blog posts.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Video summarization / video blog / user study
Paper # PRMU2014-95,MVE2014-57
Date of Issue

Conference Information
Committee PRMU
Conference Date 2015/1/15(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) Video Summarization Based on Contents Similarity between User Specified-description and Video
Sub Title (in English)
Keyword(1) Video summarization
Keyword(2) video blog
Keyword(3) user study
1st Author's Name Mayu OTANI
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Yuta NAKASHIMA
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Tomokazu SATO
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
4th Author's Name Naokazu YOKOYA
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2015-01-22
Paper # PRMU2014-95,MVE2014-57
Volume (vol) vol.114
Number (no) 409
Page pp.pp.-
#Pages 6
Date of Issue