Abstract. In the present paper we describe IntelliDomo's learning model, an ontology-based expert system able to control a home automation system and to learn user's beha...
We present a self-assessing image-based motion compensation method for coronary roadmapping in fluoroscopic images. Extending our previous work on respiratory motion compensation...
Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, u...
Motion segmentation based on point trajectories can integrate information of a whole video shot to detect and separate moving objects. Commonly, similarities are defined between ...
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...