The bag-of-words (BoW) model treats images as an unordered set of local regions and represents them by visual word histograms. Implicitly, regions are assumed to be identically an...
Ramazan Gokberk Cinbis, Jakob J. Verbeek, Cordelia...
Local experts have been used to great effect for fitting deformable
models to images. Typically, the best location in
an image for the deformable model’s landmarks are found
t...
—We propose a statistical framework for high-level feature extraction that uses SIFT Gaussian mixture models (GMMs) and audio models. SIFT features were extracted from all the im...
Scale-space representation of an image is a significant way to generate features for classification. However, for a specific classification task, the entire scale-space may not be...
In this paper we evaluate the effectiveness of two likelihood normalization techniques, the Background Model Set (BMS) and the Universal Background Model (UBM), for improving perf...