We present two methods for learning the structure of personal names from unlabeled data. The first simply uses a few implicit constraints governing this structure to gain a toehol...
In this work, we introduce an information-theoreticbased correction term to the likelihood ratio classification method for multiple classes. Under certain conditions, the term is ...
This paper proposes a unique map learning method for mobile robots based on the co-visibility infor mation of objects i.e., the information on whether two objects are visible at...
Abstract: Designing and implementing multimodal applications that take advantage of several recognitionbased interaction techniques (e.g. speech and gesture recognition) is a diffi...
: The paper presents a new concept of computer user interface dedicated for the disabled people. The concept is based on the recognition of ultrasound image of the selected region ...