Feature selection methods are often used to determine a small set of informative features that guarantee good classification results. Such procedures usually consist of two compon...
Artsiom Harol, Carmen Lai, Elzbieta Pekalska, Robe...
Abstract. Inspired by the early visual system of many mammalians we consider the construction of-and reconstruction from- an orientation score Uf : R2 ×S1 → C as a local orienta...
Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geo...
Anh Phuong Ta, Christian Wolf, Guillaume Lavoue, A...
Abstract. Clustering high dimensional data with sparse features is challenging because pairwise distances between data items are not informative in high dimensional space. To addre...
Given a pair of images represented using bag-of-visual words and a label corresponding to whether the images are “related”(must-link constraint) or “unrelated” (must not li...