Current publish / subscribe systems offer a range of expressive subscription languages for constraints. However, classical systems restrict the publish operation to be a single p...
A spoken language generation system has been developed that learns to describe objects in computer-generated visual scenes. The system is trained by a `show-and-tell' procedu...
This proposal presents a new error robust strategy for encoding redundant pictures for the H.264/AVC standard. The method is based on providing motion vectors as redundant data, i...
Maheshi B. Dissanayake, Chaminda T. E. R. Hewage, ...
In this paper, we present an AUC (i.e., the Area Under the Curve of Receiver Operating Characteristics (ROC)) maximization based learning algorithm to design the classifier for ma...
This paper presents an Adaptive Genetic Algorithm (AGA) where selection pressure, crossover and mutation probabilities are adapted according to population diversity statistics. Th...