English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Learning to Localize Objects with Structured Output Regression

Blaschko, M., & Lampert, C. (2008). Learning to Localize Objects with Structured Output Regression. In A. Forsyth, P. Torr, & A. Zisserman (Eds.), Computer Vision – ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008 (pp. 2-15). Berlin, Germany: Springer.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C6C3-1 Version Permalink: https://hdl.handle.net/21.11116/0000-0003-37E2-0
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://link.springer.com/content/pdf/10.1007%2F978-3-540-88682-2_2.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Blaschko, MB1, 2, 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: Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization task. First a binary classifier is trained using a sample of positive and negative examples, and this classifier is subsequently applied to multiple regions within test images. We propose instead to treat object localization in a principled way by posing it as a problem of predicting structured data: we model the problem not as binary classification, but as the prediction of the bounding box of objects located in images. The use of a joint-kernel framework allows us to formulate the training procedure as a generalization of an SVM, which can be solved efficiently. We further improve computational efficiency by using a branch-and-bound strategy for localization during both training and testing. Experimental evaluation on the PASCAL VOC and TU Darmstadt datasets show that the structured training procedure improves pe
rformance over binary training as well as the best previously published scores.

Details

show
hide
Language(s):
 Dates: 2008-10
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-540-88682-2_2
BibTex Citekey: 5247
 Degree: -

Event

show
hide
Title: 10th European Conference on Computer Vision (ECCV 2008)
Place of Event: Marseille, France
Start-/End Date: 2008-10-12 - 2008-10-18

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computer Vision – ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008
Source Genre: Proceedings
 Creator(s):
Forsyth, AD, Editor
Torr, PHS, Editor
Zisserman, A, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 2 - 15 Identifier: ISBN: 978-3-540-88681-5

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 5304 Sequence Number: - Start / End Page: - Identifier: -