The literature currently provides two ways to establish
point correspondences between images with moving objects.
On one side, there are energy minimization methods
that yield v...
Thomas Brox (University of California, Berkeley), ...
Abstract. We present a technique for learning the parameters of a continuousstate Markov random field (MRF) model of optical flow, by minimizing the training loss for a set of grou...
This paper describes a new model for extracting large-field optical flow patterns to generate distributed representations of neural activation to control complex visual tasks such ...
Current approaches to automated analysis have focused on a small set of prototypic expressions (e.g., joy or anger). Prototypic expressions occur infrequently in everyday life, ho...
Jeffrey F. Cohn, Adena J. Zlochower, James Jenn-Ji...
We explore a polar representation of optical flow in which each element of the brightness motion field is represented by its magnitude and orientation instead of its Cartesian p...