In this paper we present a method for performing discriminative human pose estimation using a mixture of Gaussian Processes appearance model to map directly from the image features to the multi-model pose distribution. In order to obtain a pose estimate for a sequence of frames, we introduce a dynamic programming algorithm for inferring a smooth pose sequence from the multi-model distribution g...

In many engineering problems, unknown parameters of a model are inferred in order to make predictions, to design controllers, or to optimize the model. When parameters are distributed (continuous) or very high-dimensional (discrete) and quantities of interest are low-dimensional, parameters need not be fully resolved to make accurate estimates of quantities of interest. In this work, we extend ...

Article history: Received 21 November 2012 Received in revised form 21 November 2013 Accepted 24 May 2014 Available online 6 June 2014

We study an initial-boundary value problem (IBVP) for a coupled Cahn-Hilliard-Hele-Shaw system that models tumor growth. For large initial data with finite energy, we prove global (local resp.) existence, uniqueness, higher order spatial regularity and Gevrey spatial regularity of strong solutions to the IBVP in 2D (3D resp.). Asymptotically in time, we show that the solution converges to a con...

Our goal is to provide a multilingual speech based Human Machine Interface for in-car infotainment and navigation systems. The multilinguality is for example needed for music player control via speech as artist and song names in the globalized music market come from many languages. Another frequent use case is the input of foreign navigation destinations via speech. In this paper we propose app...