Latent Mixture Vocabularies for Object Categorization

The visual vocabulary is an intermediate level representation which has been proven to be very powerful for addressing object categorization problems. It is generally built by vector quantizing a set of local image descriptors, independently of the object model used for categorizing images. We propose here to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination. We experimentally show that the proposed model outperforms approaches not learning such an adapted visual vocabulary.