We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented wi...
The Bayesian filtering for recursive state estimation and the shape-based matching methods are two of the most commonly used approaches for target tracking. The Multiple Hypothesi...
In this paper we present an efficient and general approach to computing and integrating 3D distance fields directly from multiple range images. We compute normal and confidence va...
Abstract-- The FOCal Underdetermined System Solver (FOCUSS) algorithm has already found many applications in signal processing and data analysis, whereas the regularized MFOCUSS al...
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...