Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Anchorage, AL, June 2008 Learning Subcategory Relevances for Category Recognition
 

Summary: in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Anchorage, AL, June 2008
Learning Subcategory Relevances for Category Recognition
Sinisa Todorovic and Narendra Ahuja
Beckman Institute, University of Illinois at Urbana-Champaign
{sintod, n-ahuja}@uiuc.edu
Abstract
A real-world object category can be viewed as a charac-
teristic configuration of its parts, that are themselves sim-
pler, smaller (sub)categories. Recognition of a category
can therefore be made easier by detecting its constituent
subcategories and combing these detection results. Given
a set of training images, each labeled by an object cate-
gory contained in it, we present an approach to learning:
(1) Taxonomy defined by recursive sharing of subcategories
by multiple image categories; (2) Subcategory relevance as
the degree of evidence a subcategory offers for the pres-
ence of its parent; (3) Likelihood that the image contains a
subcategory; and (4) Prior that a subcategory occurs. The
images are represented as points in a feature space spanned
by confidences in the occurrences of the subcategories. The

  

Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign
Todorovic, Sinisa - School of Electrical Engineering and Computer Science, Oregon State University

 

Collections: Computer Technologies and Information Sciences; Engineering