—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the backgr...
We introduce a new class of probabilistic latent variable model called the Implicit Mixture of Conditional Restricted Boltzmann Machines (imCRBM) for use in human pose tracking. K...
Graham Taylor, Leonid Sigal, David Fleet, Geoffrey...
This paper presents an extensive evaluation, on artificial datasets, of EDY, an unsupervised algorithm for automatically synthesizing a Structured Hidden Markov Model (S-HMM) from ...
Many classes of images have the characteristics of sparse structuring of statistical dependency and the presence of conditional independencies among various groups of variables. S...
Humans demonstrate a remarkable ability to parse complicated motion sequences into their constituent structures and motions. We investigate this problem, attempting to learn the st...