English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Beyond Sliding Windows: Object Localization by Efficient Subwindow Search

Lampert, C., Blaschko, M., & Hofmann, T. (2008). Beyond Sliding Windows: Object Localization by Efficient Subwindow Search. In 2008 IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-8). Piscataway, NJ, USA: IEEE.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C8F5-C Version Permalink: http://hdl.handle.net/21.11116/0000-0003-4311-E
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Lampert, CH1, 2, Author              
Blaschko, MB1, 2, Author              
Hofmann, T, 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: Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branchand- bound scheme that allows efficient maximization of a large class of classifier functions over all possible subimages. It converges to a globally optimal solution typically in sublinear time. We show how our method is applicable to different object detection and retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest neighbor classifiers based on the 2-distance. We demonstrate state-of-the-art performance of the resulting systems on the UIUC Cars dataset, the PASCAL VOC 2006 dataset and in the PASCAL VOC 2007 competition.

Details

show
hide
Language(s):
 Dates: 2008-06
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/CVPR.2008.4587586
BibTex Citekey: 5070
 Degree: -

Event

show
hide
Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008)
Place of Event: Anchorage, AK, USA
Start-/End Date: 2008-06-23 - 2008-06-28

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2008 IEEE Conference on Computer Vision and Pattern Recognition
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1 - 8 Identifier: ISBN: 978-1-4244-2243-2