Presentation 2015-03-20
Video Level Violence Rating
Jien KATO, Yu WANG, Guanwen ZHANG,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Given a video as input, we propose an approach to estimate a rate which describes the extent of "how violent it is". Such an estimation is highly desirable for many practical applications such as preventing children from videos of excessive visual violence. However, existing methods on human action recognition and violent scenes detection can not be directly utilized for this objective due to the unique property of the rating task. Our proposed approach includes (1) a novel video descriptor called Violent Attribute Activation (VAA), and (2) a rank-prediction-based rating approach that enforces the order constrains during the rating process. The performance of the approach has been confirmed on a novel dataset that are specially prepared for the violence rating problem.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) violence rating / Visual violence / human action recognition / violent scene detection / learning to ranking
Paper # BioX2014-78,PRMU2014-198
Date of Issue

Conference Information
Committee PRMU
Conference Date 2015/3/12(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 Level Violence Rating
Sub Title (in English)
Keyword(1) violence rating
Keyword(2) Visual violence
Keyword(3) human action recognition
Keyword(4) violent scene detection
Keyword(5) learning to ranking
1st Author's Name Jien KATO
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Yu WANG
2nd Author's Affiliation Graduate School of Information Science, Nagoya University
3rd Author's Name Guanwen ZHANG
3rd Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2015-03-20
Paper # BioX2014-78,PRMU2014-198
Volume (vol) vol.114
Number (no) 521
Page pp.pp.-
#Pages 4
Date of Issue