We present a generic and robust method for model-based global 3D head pose estimation in monocular and non-calibrated video sequences. The proposed method relies on a 3D/2D matchi...
We present a FrameNet-based semantic role labeling system for Swedish text. As training data for the system, we used an annotated corpus that we produced by transferring FrameNet ...
Laser based people tracking systems have been developed for mobile robotic or intelligent surveillance areas. Existing systems rely on laser point clustering to extract object loc...
For low bitrate video communications, each video frame usually fills the payload of a single network packet. In this situation, the loss of a packet may result in loosing the enti...
In this paper we define a new notion of frame based formulas. We show that the well-known examples of formulas arising from a finite frame, such as the Jankov-de Jongh formulas, s...