Once the battery becomes fully discharged, a battery-powered portable electronic system goes off-line. Therefore, it is important to take the battery behavior into account. A syst...
We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
Poor convergence to concave shapes is a main limitation of snakes as a standard segmentation and shape modelling technique. The gradient of the external energy of the snake represe...
This paper describes the research of parametric and procedural modeling techniques associated with digital fabrication and form-finding within architectural design. The outcome of...