Presentation 2011-02-18
Event Detection by Multiple Keyframes Extraction Based on Scene Length : Nikon Multimedia Event Detection System
Takeshi MATSUO, Shinichi NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We participated in the Multimedia Event Detection (MED) task of TRECVID 2010, where participants try to find video clips that include specific events from a bunch of Internet contents. Our system first divides each video clip into scenes, and then extracts multiple image frames from longer scenes. Despite of its simplicity, it was in the third place among the seven teams of participants. In this paper, we describe our system, and report its performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) TRECVID / multimedia event detection / scene length / multiple keyframes / bag-of-words
Paper # PRMU2010-221
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/2/10(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) Event Detection by Multiple Keyframes Extraction Based on Scene Length : Nikon Multimedia Event Detection System
Sub Title (in English)
Keyword(1) TRECVID
Keyword(2) multimedia event detection
Keyword(3) scene length
Keyword(4) multiple keyframes
Keyword(5) bag-of-words
1st Author's Name Takeshi MATSUO
1st Author's Affiliation Optical Research Laboratory, Nikon Corporation()
2nd Author's Name Shinichi NAKAJIMA
2nd Author's Affiliation Optical Research Laboratory, Nikon Corporation
Date 2011-02-18
Paper # PRMU2010-221
Volume (vol) vol.110
Number (no) 414
Page pp.pp.-
#Pages 5
Date of Issue