Presentation 2014-01-24
Efficient modeling with selecting learning samples in human pose estimaiton
Yoichi MATSUYAMA, Norimichi UKITA, Norihiro HAGITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The more learning samples the better the modeling general. However the computational cost in modeling rises rapidlly the samples increase in number. The computational cost can be expensive if modeling is required only once. But in the stage of exporing good models and their parameters, modeling is repeated many times. So the computational cost in modeling should be smaller. In this paper, we propose efficient modeling while maintaining the accuracy of the model by appropiately selecting the learning samples. Experimental results show the efficiency of the proposed modeling in human pose estimaiton.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Efficient model learning / Selecting learning samples / Humanpose estimation / Deformable part model Latent SVM
Paper # PRMU2013-115,MVE2013-56
Date of Issue

Conference Information
Committee MVE
Conference Date 2014/1/16(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Efficient modeling with selecting learning samples in human pose estimaiton
Sub Title (in English)
Keyword(1) Efficient model learning
Keyword(2) Selecting learning samples
Keyword(3) Humanpose estimation
Keyword(4) Deformable part model Latent SVM
1st Author's Name Yoichi MATSUYAMA
1st Author's Affiliation Nara Institute of Sciense and Technology()
2nd Author's Name Norimichi UKITA
2nd Author's Affiliation Nara Institute of Sciense and Technology
3rd Author's Name Norihiro HAGITA
3rd Author's Affiliation Nara Institute of Sciense and Technology
Date 2014-01-24
Paper # PRMU2013-115,MVE2013-56
Volume (vol) vol.113
Number (no) 403
Page pp.pp.-
#Pages 6
Date of Issue