We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
— We study a simple game theoretic model for the spread of an innovation in a network. The diffusion of the innovation is modeled as the dynamics of a coordination game in which ...
Abstract. In this paper, we propose a new formulation of the Differential Optical Flow Equation (DOFE) between two consecutive images considering spatial and temporal information ...
Scalable energy-efficient training protocols are proposed for massively-deployed sensor networks, where sensors are initially anonymous and unaware of their location. The protocol...
Ferruccio Barsi, Alan A. Bertossi, Francesco Betti...
We present an algorithm for automatic locating of anthropometric landmarks on 3D human scans. Our method is based on learning landmark characteristics and the spatial relationship...