Abstract—We introduce a new algorithm for real-time interactive motion control and demonstrate its application to motion captured data, pre-recorded videos and HCI. Firstly, a da...
We present a novel representation and rendering method for free-viewpoint video of human characters based on multiple input video streams. The basic idea is to approximate the art...
Marcel Germann, Alexander Hornung, Richard Keiser,...
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actio...
Computational models of grounded language learning have been based on the premise that words and concepts are learned simultaneously. Given the mounting cognitive evidence for conc...
The emerging MPEG-7 standard embodies a visual descriptor that will be associated with the dominant colors of an image. In this contribution, a threshold adaptation method for reg...