This paper presents a novel approach for tracking humans and objects under severe occlusion. We introduce a new paradigm for multiple hypotheses tracking, observe-and-explain, as ...
We present an online, recursive filtering technique to model linear dynamical systems that operate on the state space of symmetric positive definite matrices (tensors) that lie on...
Given estimates of the motion eld optic ow from an image sequence, it is possible to recover translational direction, ~T, using a variety of techniques. One such technique, known ...
In this paper, we present a procedure for organizing real world scenes along semantic axes. The approach is based on the output energies of linear discriminant filters that take i...
Traditionally, the Universal Background Model (UBM) is viewed as the background model of the entire acoustic feature space. We propose a novel interpretation of the UBM model, and...