Presentation 2011-02-18
Mining Specific Actions from Youtube Video with Spatio-Temporal Features
DO HANG NGA, Keiji YANAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present a new method of automatically extracting from tagged Web videos the video-shots correspond to specific actions with just inputing the action keywords such as walking, eating etc.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spatio-Temporal Feature / Web video / unsupervised learning
Paper # PRMU2010-233
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) Mining Specific Actions from Youtube Video with Spatio-Temporal Features
Sub Title (in English)
Keyword(1) Spatio-Temporal Feature
Keyword(2) Web video
Keyword(3) unsupervised learning
1st Author's Name DO HANG NGA
1st Author's Affiliation The University of Electro-Communication()
2nd Author's Name Keiji YANAI
2nd Author's Affiliation The University of Electro-Communication
Date 2011-02-18
Paper # PRMU2010-233
Volume (vol) vol.110
Number (no) 414
Page pp.pp.-
#Pages 6
Date of Issue