Manifold learning algorithms have been proven to be capable of discovering some nonlinear structures. However, it is hard for them to extend to test set directly. In this paper, a ...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Abstract. During development, processor architectures can be tuned and configured by many different parameters. For benchmarking, automatic design space explorations (DSEs) with h...
Ralf Jahr, Horia Calborean, Lucian Vintan, Theo Un...
We present a method for learning appearance models that can be used to recognise and track both 3D head pose and identities of novel subjects with continuous head movement across ...
In this paper a system was developed for robot behavior acquisition using kinesthetic demonstrations. It enables a humanoid robot to imitate constrained reaching gestures directed...