In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably wi...
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
This paper provides a technique for measuring camera translation relatively w.r.t. the scene from two images. We demonstrate that the amount of the translation can be reliably mea...
Akihiko Torii, Bastian Leibe, Michal Havlena, Tom&...
Many linear discriminant analysis (LDA) and kernel Fisher discriminant analysis (KFD) methods are based on the restrictive assumption that the data are homoscedastic. In this paper...
One of the main challenges in image segmentation is to adapt prior knowledge about the objects/regions that are likely to be present in an image, in order to obtain more precise d...