Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 DetailsÜbersicht
  A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection

Lampert, C., & Blaschko, M. (2008). A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection. Pattern Recognition: Proceedings of the 30th DAGM Symposium, 31-40.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C8EB-4 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C8EC-2
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Lampert, C1, 2, Autor           
Blaschko, MB1, Autor           
Rigoll, G., Herausgeber
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Dept. Empirical Inference, Max Planck Institute for Intelligent System, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: 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. In 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.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2008-06
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://www.dagm2008.org/
DOI: 10.1007/978-3-540-69321-5_4
BibTex Citekey: 5259
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 30th Annual Symposium of the German Association for Pattern Recognition
Veranstaltungsort: München, Germany
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Pattern Recognition: Proceedings of the 30th DAGM Symposium
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Berlin, Germany : Springer
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 31 - 40 Identifikator: -