Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
We present a novel framework for tracking of a long sequence of human activities, including the time instances of change from one activity to the next, using a closed-loop, non-li...
: Contour Estimation, Bayesian Estimation, Random Fields, Dynamic Programming, Multigrid Methods. This paper addresses contour estimation on images modeled as piecewise homogeneous...
—In this paper, we present a novel system which combines depth-from-stereo and visual hull reconstruction for acquiring dynamic real-world scenes at interactive rates. First, we ...
Hartmut Schirmacher, Ming Li, Marcus A. Magnor, Ha...
— Adaptive transceivers play an important role in wireless communications and the design of MIMO systems. Therefore models that enable simulation of dynamic and time varying chan...