de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Konferenzbeitrag

Extracting Structures in Image Collections for Object Recognition

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons44365

Ebert,  Sandra
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44887

Larlus,  Diane
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Ebert, S., Larlus, D., & Schiele, B. (2010). Extracting Structures in Image Collections for Object Recognition. In K. Daniilidis, P. Maragos, & N. Paragios (Eds.), Computer Vision - ECCV 2010 (pp. 720-733). Berlin: Springer.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-000F-15C3-D
Zusammenfassung
Many computer vision methods rely on annotated image databases without taking advantage of the increasing number of unlabeled images available. This paper explores an alternative approach involving unsupervised structure discovery and semi-supervised learning (SSL) in image collections. Focusing on object classes, the first part of the paper contributes with an extensive evaluation of state-of-the-art image representations underlining the decisive influence of the local neighborhood structure, its direct consequences on SSL results, and the importance of developing powerful object representations. In a second part, we propose and explore promising directions to improve results by looking at the local topology between images and feature combination strategies.