English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 DetailsSummary
  How Good are Detection Proposals, really?

Hosang, J., Benenson, R., & Schiele, B. (2014). How Good are Detection Proposals, really? In M. Valstar, A. French, & T. Pridmore (Eds.), Proceedings of the British Machine Vision Conference (pp. 1-12). Durham: BMVA Press.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-3C2E-2 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-CA0B-9
Genre: Conference Paper

Files

show Files
hide Files
:
paper082.pdf (Any fulltext), 2MB
View   Save
File Permalink:
https://hdl.handle.net/11858/00-001M-0000-0024-3C30-9
Name:
paper082.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms
License:
-
:
abstract082.pdf (Abstract), 537KB
View   Save
File Permalink:
https://hdl.handle.net/11858/00-001M-0000-0024-3C31-7
Name:
abstract082.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
-
:
sup082.zip (Supplementary material), 3MB
View   Save
File Permalink:
https://hdl.handle.net/11858/00-001M-0000-0024-3C32-5
Name:
sup082.zip
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/zip / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Hosang, Jan1, Author           
Benenson, Rodrigo1, Author           
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: -
 Abstract: Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. Despite the popularity of detection proposals, it is unclear which trade‐offs are made when using them during object detection. We provide an in depth analysis of ten object proposal methods along with four baselines regarding ground truth annotation recall (on Pascal VOC 2007 and ImageNet 2013), repeatability, and impact on DPM detector performance. Our findings show common weaknesses of existing methods, and provide insights to choose the most adequate method for different settings.

Details

show
hide
Language(s): eng - English
 Dates: 2014
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Hosang2013Bmvc
 Degree: -

Event

show
hide
Title: 25th British Machine Vision Conference
Place of Event: Nottingham, UK
Start-/End Date: 2014-09-01 - 2014-09-05

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the British Machine Vision Conference
  Abbreviation : BMVC 2014
Source Genre: Proceedings
 Creator(s):
Valstar, Michel1, Editor
French, Andrew1, Editor
Pridmore, Tony1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Durham : BMVA Press
Pages: - Volume / Issue: - Sequence Number: 82 Start / End Page: 1 - 12 Identifier: -