Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 DetailsÜbersicht
  What helps Where - and Why? Semantic Relatedness for Knowledge Transfer

Rohrbach, M., Stark, M., Szarvas, G., Gurevych, I., & Schiele, B. (2010). What helps Where - and Why? Semantic Relatedness for Knowledge Transfer. In 2010 IEEE Conference on Computer Vision and Pattern Recognition (pp. 910-917). Piscataway, NJ: IEEE. doi:10.1109/CVPR.2010.5540121.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-15DD-4 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-3056-4
Genre: Konferenzbeitrag

Dateien

einblenden: Dateien
ausblenden: Dateien
:
rohrbach10cvpr.pdf (beliebiger Volltext), 2MB
 
Datei-Permalink:
-
Name:
rohrbach10cvpr.pdf
Beschreibung:
-
OA-Status:
Sichtbarkeit:
Privat
MIME-Typ / Prüfsumme:
application/pdf
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
Copyright © 2010, IEEE
Lizenz:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Rohrbach, Marcus1, Autor           
Stark, Michael1, Autor           
Szarvas, György2, Autor
Gurevych, Iryna2, Autor
Schiele, Bernt1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today's recognition methods. Several authors have promoted knowledge transfer between classes as a key ingredient to address this challenge. However, in previous work the decision which knowledge to transfer has required either manual supervision or at least a few training examples limiting the scalability of these approaches. In this work we explicitly address the question of how to automatically decide which information to transfer between classes without the need of any human intervention. For this we tap into linguistic knowledge bases to provide the semantic link between sources (what) and targets (where) of knowledge transfer. We provide a rigorous experimental evaluation of different knowledge bases and state-of-the-art techniques from Natural Language Processing which goes far beyond the limited use of language in related work. We also give insights into the applicability (why) of different knowledge sources and similarity measures for knowledge transfer.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20102010
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eDoc: 536668
DOI: 10.1109/CVPR.2010.5540121
URI: http://dx.doi.org/10.1109/CVPR.2010.5540121
Anderer: Local-ID: C12576EE0048963A-3A1B857E4F1356ACC12577DF005C92B6-rohrbach10cvpr
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 2010 IEEE Conference on Computer Vision and Pattern Recognition
Veranstaltungsort: San Francisco, USA
Start-/Enddatum: 2010-06-15 - 2010-06-17

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 2010 IEEE Conference on Computer Vision and Pattern Recognition
  Kurztitel : CVPR 2010
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 910 - 917 Identifikator: ISBN: 978-1-4244-6984-0