Presentation	2005-06-16 Training Data Generation Method for Shot Boundary Detection Kazunori MATSUMOTO, Keiichiro HOASHI, Masaru SUGANO, Masaki NAITO,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	To improve the performance of shot boundary detection, more and more features are being treated. This arises that discrimination function of is hard to design. Authors suggest the method to eliminate non-significant negative case from a training data set by an entropy measurement. And also a method to add significant artificial cases based on entropy is discussed. This manuscript describes the detail of experimental result of these methods.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Shot Boundary Detection / Support Vector Machine / Entropy Maximization / Refinement of Training Data
Paper #	DE2005-6,PRMU2005-27
Date of Issue

Conference Information
Committee	PRMU
Conference Date	2005/6/9(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)	Training Data Generation Method for Shot Boundary Detection
Sub Title (in English)
Keyword(1)	Shot Boundary Detection
Keyword(2)	Support Vector Machine
Keyword(3)	Entropy Maximization
Keyword(4)	Refinement of Training Data
1st Author's Name	Kazunori MATSUMOTO
1st Author's Affiliation	KDDI R&D Labs. Inc.()
2nd Author's Name	Keiichiro HOASHI
2nd Author's Affiliation	KDDI R&D Labs. Inc.
3rd Author's Name	Masaru SUGANO
3rd Author's Affiliation	KDDI R&D Labs. Inc.
4th Author's Name	Masaki NAITO
4th Author's Affiliation	KDDI R&D Labs. Inc.
Date	2005-06-16
Paper #	DE2005-6,PRMU2005-27
Volume (vol)	vol.105
Number (no)	118
Page	pp.pp.-
#Pages	6
Date of Issue