There is a notable interest in extending probabilistic generative modeling principles to accommodate for more complex structured data types. In this paper we develop a generative ...
This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatic...
We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to p...
Alan L. Yuille, Pierre-Yves Burgi, Norberto M. Grz...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...
This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or articulated objects i...