The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel...
Florent Perronnin, Yan Liu, Jorge Sanchez, Herve P...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
1 Tags are an important information source in Web 2.0. They can be used to describe users’ topic preferences as well as the content of items to make personalized recommendations....
Abstract. Many sophisticated classification algorithms have been proposed. However, there is no clear methodology of comparing the results among different methods. According to ou...