Linear parameterized models of optical flow, particularly affine models, have become widespread in image motion analysis. The linear model coefficients are straightforward to estim...
David J. Fleet, Michael J. Black, Yaser Yacoob, Al...
The general problem of defining and determining the sample distribution in the case of continuousparameter random fields, is addressed. Defining a distribution in the case of d...
—Characterizing the performance of ad hoc networks is one of the most intricate open challenges; conventional ideas based on information-theoretic techniques and inequalities hav...
This paper proposes a unified framework for spatiotemporal segmentation of video sequences. A Bayesian network is presented to model the interactions among the motion vector field...
A new probabilistic image segmentation model based on hypothesis testing and Gibbs Random Fields is introduced. First, a probabilistic difference measure derived from a set of hyp...