Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate tire models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning object categories from Google's image search


    Contributors:
    Fergus, R. (author) / Fei-Fei, L. (author) / Perona, P. (author) / Zisserman, A. (author)


    Publication date :

    2005-01-01


    Size :

    1879371 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning Object Categories from Google's Image Search

    Fergus, R. / Fei-Fei, L. / Perona, P. et al. | British Library Conference Proceedings | 2005


    Google's green investments

    British Library Online Contents | 2009


    Google's green investments

    British Library Online Contents | 2009


    Google's Satellite Collection Planning

    Rousmaniere, Louis | AIAA | 2016


    Using Google’s Passive Data and Machine Learning for Origin-Destination Demand Estimation

    Sana, Bhargava / Castiglione, Joe / Cooper, Drew et al. | Transportation Research Record | 2018