Presentation 2014-10-09
Learning Similarities for Rigid and Non-Rigid Object Detection
Asako KANEZAKI, Emanuele RODOLA, Daniel CREMERS, Tatsuya HARADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose an optimization method for estimating parameters in graph-theoretical formulations of the matching problem for object detection. Unlike several methods which optimize parameters for graph matching in a way to promote correct correspondences and to restrict wrong ones, our approach aims at improving performance in the more general task of object detection. In our formulation, similarity functions are adjusted so as to increase the overall similarity among a reference model and the observed target, and at the same time reduce the similarity among reference and "non-target" objects. We evaluate the proposed method in two challenging scenarios, demonstrating substantial improvements in both settings.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) keypoint matching / graph matching / optimization / gradient descent method / 3D shape
Paper # PRMU2014-56
Date of Issue

Conference Information
Committee PRMU
Conference Date 2014/10/2(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) Learning Similarities for Rigid and Non-Rigid Object Detection
Sub Title (in English)
Keyword(1) keypoint matching
Keyword(2) graph matching
Keyword(3) optimization
Keyword(4) gradient descent method
Keyword(5) 3D shape
1st Author's Name Asako KANEZAKI
1st Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo()
2nd Author's Name Emanuele RODOLA
2nd Author's Affiliation Computer Vision Group, TU Munich
3rd Author's Name Daniel CREMERS
3rd Author's Affiliation Computer Vision Group, TU Munich
4th Author's Name Tatsuya HARADA
4th Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
Date 2014-10-09
Paper # PRMU2014-56
Volume (vol) vol.114
Number (no) 230
Page pp.pp.-
#Pages 6
Date of Issue