Currently 3D animation rendering and video compression are completely independent processes even if rendered frames are streamed on-the-fly within a client-server platform. In suc...
Robert Herzog, Shin-ichi Kinuwaki, Karol Myszkowsk...
The processing, description and recognition of dynamic (time-varying) textures are new exciting areas of texture analysis. Many real-world textures are dynamic textures whose retri...
A new hand gesture recognition method based on Input– Output Hidden Markov Models is presented. This method deals with the dynamic aspects of gestures. Gestures are extracted fr...
We describe how to build a VIDEOPLACE-like vision-driven user interface using "optical-flow" measurements. The optical-flow denotes the estimated movement of an image pat...
In this paper we address the problem of human body pose estimation from still images. A multi-view set of images of a person sitting at a table is acquired and the pose estimated....