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

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Konferenzbeitrag

How Good are Detection Proposals, really?

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons86681

Hosang,  Jan
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons79212

Benenson,  Rodrigo
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)

paper082.pdf
(beliebiger Volltext), 2MB

Ergänzendes Material (frei zugänglich)

sup082.zip
(Ergänzendes Material), 3MB

Zitation

Hosang, J., Benenson, R., & Schiele, B. (2014). How Good are Detection Proposals, really? In M. Valstar, A. French, & T. Pridmore (Eds.), Proceedings of the British Machine Vision Conference (pp. 1-12). Durham: BMVA Press.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-0024-3C2E-2
Zusammenfassung
Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. Despite the popularity of detection proposals, it is unclear which trade‐offs are made when using them during object detection. We provide an in depth analysis of ten object proposal methods along with four baselines regarding ground truth annotation recall (on Pascal VOC 2007 and ImageNet 2013), repeatability, and impact on DPM detector performance. Our findings show common weaknesses of existing methods, and provide insights to choose the most adequate method for different settings.