Abstract Several state-of-the-art Generic Visual Categorization (GVC) systems are built around a vocabulary of visual terms and characterize images with one histogram of visual word counts. We propose a novel and practical approach to GVC based on a universal vocabulary, which describes the content of all the considered classes of images, and class vocabularies obtained through the adaptation of the universal vocabulary using class-specific data. An image is characterized by a set of histograms – one per class – where each histogram describes whether the image content is best modeled by the universal vocabulary or the corresponding class vocabulary. It is shown experimentally on three very different databases that this novel representation outperforms those approaches which characterize an image with a single histogram.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Adapted Vocabularies for Generic Visual Categorization


    Beteiligte:


    Erscheinungsdatum :

    2006-01-01


    Format / Umfang :

    12 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Adapted Vocabularies for Generic Visual Categorization

    Perronnin, F. / Dance, C. / Csurka, G. et al. | British Library Conference Proceedings | 2006


    Latent mixture vocabularies for object categorization and segmentation

    Larlus, D. / Jurie, F. | British Library Online Contents | 2009


    Big Data and Controlled Vocabularies

    Mathieu, Camille | NTRS | 2019


    Hybrid Generative-Discriminative Visual Categorization

    Holub, A. D. / Welling, M. / Perona, P. | British Library Online Contents | 2008


    Learning Vocabularies over a Fine Quantization

    Mikulik, A. / Perdoch, M. / Chum, O. e. et al. | British Library Online Contents | 2013