We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
In this article, we investigate efficient transmission of Object-based MPEG-4 video over IP networks with QoS management capabilities. MPEG-4 Audio Visual Objects (AVOs) are class...
Abstract. This paper proposes a novel method to deal with the representation issue in texture classification. A learning framework of image descriptor is designed based on the Fish...
Computer-based geometry systems have been widely used for teaching and learning, but largely based on mouse-andkeyboard interaction, these systems usually require users to draw fi...
In this paper, we present a novel solution to the image annotation problem which annotates images using search and data mining technologies. An accurate keyword is required to ini...