We propose a method of clustering images that combines algorithmic and human input. An algorithm provides us with pairwise image similarities. We then actively obtain selected, mo...
We introduce a framework for defining a distance on the (non-Euclidean) space of Linear Dynamical Systems (LDSs). The proposed distance is induced by the action of the group of o...
We introduce a saliency model based on two key ideas. The first one is considering local and global image patch rarities as two complementary processes. The second one is based o...
In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms us...
We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noi...