We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...
Abstract. This paper presents a novel technique for learning the underlying structure that links visual observations with semantics. The technique, inspired by a text-retrieval tec...
Jonathon S. Hare, Paul H. Lewis, Peter G. B. Enser...
We present a new approach to estimating mixture models based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from ...
In this paper, we present a structural learning model for joint sentiment classification and aspect analysis of text at various levels of granularity. Our model aims to identify ...
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. T...
Andrea Fossati (EPFL), Mathieu Salzmann (Universit...