A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which part is irrelevant clutter which is not associated to the objects. We investigate empirically to what extent pure bottom-up attention can extract useful information about the location, size and shape of objects from images and demonstrate how this information can be utilized to enable unsupervised learning of objects from unlabeled images. Our experiments demonstrate that the proposed approach to using bottom-up attention is indeed useful for a variety of applications.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Is bottom-up attention useful for object recognition?


    Beteiligte:
    Rutishauser, U. (Autor:in) / Walther, D. (Autor:in) / Koch, C. (Autor:in) / Perona, P. (Autor:in)


    Erscheinungsdatum :

    2004-01-01


    Format / Umfang :

    758087 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Is Bottom-Up Attention Useful for Object Recognition?

    Rutishauser, U. / Walther, D. / Koch, C. et al. | British Library Conference Proceedings | 2004


    Simulating visual attention for object recognition

    Frintrop, S. / Rome, E. | Fraunhofer Publica | 2004

    Freier Zugriff

    Active Object Recognition Integrating Attention and Viewpoint Control

    Dickinson, S. J. / Christensen, H. I. / Tsotsos, J. K. et al. | British Library Online Contents | 1997


    Modulating Shape Features by Color Attention for Object Recognition

    Khan, F. S. / Weijer, J. / Vanrell, M. | British Library Online Contents | 2012