English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Object Localization with Global and Local Context Kernels

Blaschko, M., & Lampert, C. (2009). Object Localization with Global and Local Context Kernels. In British Machine Vision Conference 2009 (BMVC 2009) (pp. 1-11). Durham, UK: BMVA Press. doi:10.5244/C.23.63.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C313-5 Version Permalink: http://hdl.handle.net/21.11116/0000-0002-E588-2
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Blaschko, M, Author              
Lampert, CH1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Recent research has shown that the use of contextual cues significantly improves performance in sliding window type localization systems. In this work, we propose a method that incorporates both global and local context information through appropriately defined kernel functions. In particular, we make use of a weighted combination of kernels defined over local spatial regions, as well as a global context kernel. The relative importance of the context contributions is learned automatically, and the resulting discriminant function is of a form such that localization at test time can be solved efficiently using a branch and bound optimization scheme. By specifying context directly with a kernel learning approach, we achieve high localization accuracy with a simple and efficient representation. This is in contrast to other systems that incorporate context for which expensive inference needs to be done at test time. We show experimentally on the PASCAL VOC datasets that the inclusion of context can significantly improve localization performance, provided the relative contributions of context cues are learned appropriately.

Details

show
hide
Language(s):
 Dates: 2009-09
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.5244/C.23.63
BibTex Citekey: 5956
 Degree: -

Event

show
hide
Title: British Machine Vision Conference 2009 (BMVC 2009)
Place of Event: London, UK
Start-/End Date: 2009-09-07 - 2009-09-10

Legal Case

show

Project information

show

Source 1

show
hide
Title: British Machine Vision Conference 2009 (BMVC 2009)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Durham, UK : BMVA Press
Pages: - Volume / Issue: - Sequence Number: 63 Start / End Page: 1 - 11 Identifier: ISBN: 1-901725-39-1