Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Abstract. Dimensionality reduction is an essential aspect of visual processing. Traditionally, linear dimensionality reduction techniques such as principle components analysis have...
In this paper we describe the first stage of a new learning system for object detection and recognition. For our system we propose Boosting [5] as the underlying learning technique...
Andreas Opelt, Michael Fussenegger, Axel Pinz, Pet...
Emerging applications in sensor systems and network-wide IP traffic analysis present many technical challenges. They need distributed monitoring and continuous tracking of events....
We consider di usion processes on a class of R trees. The processes are de ned in a manner similar to that of Le Gall's Brownian snake. Each point in the tree has a real value...