---
_id: '3716'
abstract:
- lang: eng
  text: "Most current methods for multi-class object classification and localization
    work as independent 1-vs-rest classifiers. They decide whether and where an object
    is visible in an image purely on a per-class basis. Joint learning of more than
    one object class would generally be preferable, since this would allow the use
    of contextual information such as co-occurrence between classes. However, this
    approach is usually not employed because of its computational cost.\r\n\r\nIn
    this paper we propose a method to combine the efficiency of single class localization
    with a subsequent decision process that works jointly for all given object classes.
    By following a multiple kernel learning (MKL) approach, we automatically obtain
    a sparse dependency graph of relevant object classes on which to base the decision.
    Experiments on the PASCAL VOC 2006 and 2007 datasets show that the subsequent
    joint decision step clearly improves the accuracy compared to single class detection.\r\n"
alternative_title:
- LNCS
article_processing_charge: No
author:
- first_name: Christoph
  full_name: Lampert, Christoph
  id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
  last_name: Lampert
  orcid: 0000-0001-8622-7887
- first_name: Matthew
  full_name: Blaschko, Matthew
  last_name: Blaschko
citation:
  ama: 'Lampert C, Blaschko M. A multiple kernel learning approach to joint multi-class
    object detection. In: <i>30th DAGM Symposium</i>. Vol 5096. Springer; 2008:31-40.
    doi:<a href="https://doi.org/10.1007/978-3-540-69321-5_4">10.1007/978-3-540-69321-5_4</a>'
  apa: 'Lampert, C., &#38; Blaschko, M. (2008). A multiple kernel learning approach
    to joint multi-class object detection. In <i>30th DAGM Symposium</i> (Vol. 5096,
    pp. 31–40). Munich, Germany: Springer. <a href="https://doi.org/10.1007/978-3-540-69321-5_4">https://doi.org/10.1007/978-3-540-69321-5_4</a>'
  chicago: Lampert, Christoph, and Matthew Blaschko. “A Multiple Kernel Learning Approach
    to Joint Multi-Class Object Detection.” In <i>30th DAGM Symposium</i>, 5096:31–40.
    Springer, 2008. <a href="https://doi.org/10.1007/978-3-540-69321-5_4">https://doi.org/10.1007/978-3-540-69321-5_4</a>.
  ieee: C. Lampert and M. Blaschko, “A multiple kernel learning approach to joint
    multi-class object detection,” in <i>30th DAGM Symposium</i>, Munich, Germany,
    2008, vol. 5096, pp. 31–40.
  ista: 'Lampert C, Blaschko M. 2008. A multiple kernel learning approach to joint
    multi-class object detection. 30th DAGM Symposium. DAGM: German Association For
    Pattern Recognition, LNCS, vol. 5096, 31–40.'
  mla: Lampert, Christoph, and Matthew Blaschko. “A Multiple Kernel Learning Approach
    to Joint Multi-Class Object Detection.” <i>30th DAGM Symposium</i>, vol. 5096,
    Springer, 2008, pp. 31–40, doi:<a href="https://doi.org/10.1007/978-3-540-69321-5_4">10.1007/978-3-540-69321-5_4</a>.
  short: C. Lampert, M. Blaschko, in:, 30th DAGM Symposium, Springer, 2008, pp. 31–40.
conference:
  end_date: 2008-06-13
  location: Munich, Germany
  name: 'DAGM: German Association For Pattern Recognition'
  start_date: 2008-06-10
date_created: 2018-12-11T12:04:46Z
date_published: 2008-07-07T00:00:00Z
date_updated: 2026-06-12T11:23:57Z
day: '07'
doi: 10.1007/978-3-540-69321-5_4
extern: '1'
fulldoi: https://doi.org/10.1007/978-3-540-69321-5_4
intvolume: '      5096'
language:
- iso: eng
main_file_link:
- url: http://www.kyb.mpg.de/fileadmin/user_upload/files/publications/attachments/DAGM2008-Lampert-Blaschko_5072%5b0%5d.pdf
month: '07'
oa_version: None
page: 31 - 40
publication: 30th DAGM Symposium
publication_identifier:
  isbn:
  - '9783540693208'
  issn:
  - 0302-9743
publication_status: published
publisher: Springer
publist_id: '2641'
status: public
title: A multiple kernel learning approach to joint multi-class object detection
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 5096
year: '2008'
...