English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  A Convnet for Non-maximum Suppression

Hosang, J., Benenson, R., & Schiele, B. (2016). A Convnet for Non-maximum Suppression. In B. Rosenhahn, & B. Andres (Eds.), Pattern Recognition (pp. 192-204). Berlin: Springer. doi:10.1007/978-3-319-45886-1 16.

Item is

Files

show Files

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: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG
 Abstract: Non-maximum suppression (NMS) is used in virtually all state-of-the-art object detection pipelines. While essential object detection ingredients such as features, classifiers, and proposal methods have been extensively researched surprisingly little work has aimed to systematically address NMS. The de-facto standard for NMS is based on greedy clustering with a fixed distance threshold, which forces to trade-off recall versus precision. We propose a convnet designed to perform NMS of a given set of detections. We report experiments on a synthetic setup, and results on crowded pedestrian detection scenes. Our approach overcomes the intrinsic limitations of greedy NMS, obtaining better recall and precision.

Details

show
hide
Language(s): eng - English
 Dates: 2015-11-1920162016
 Publication Status: Issued
 Pages: 14 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Hosang2016Gcpr
DOI: 10.1007/978-3-319-45886-1 16
 Degree: -

Event

show
hide
Title: 38th German Conference on Pattern Recognition
Place of Event: Hannover, Germany
Start-/End Date: 2016-09-12 - 2016-09-15

Legal Case

show

Project information

show

Source 1

show
hide
Title: Pattern Recognition
  Abbreviation : GCPR 2016
  Subtitle : 38th German Conference, GCPR 2016 ; Hannover, Germany, September 12-15, 2016 ; Proceedings
Source Genre: Proceedings
 Creator(s):
Rosenhahn, Bodo1, Editor           
Andres, Björn2, Editor           
Affiliations:
1 External Organizations, ou_persistent22            
2 Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547            
Publ. Info: Berlin : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 192 - 204 Identifier: ISBN: 978-3-319-45885-4

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 9796 Sequence Number: - Start / End Page: - Identifier: -