Abstract. In this paper we investigate a new method of learning partbased models for visual object recognition, from training data that only provides information about class member...
Abstract. Until now, the great majority of research in low-power systems has assumed a convex power model. However, recently, due to the confluence of emerging technological and ar...
Ani Nahapetian, Foad Dabiri, Miodrag Potkonjak, Ma...
The concept of interoperability of data and model as presented in this paper is viewed as being very useful for implementing variety of future applications related to power system...
Mladen Kezunovic, Santiago Grijalva, Papiya Dutta,...
Understanding the characteristics of the Internet delay space (i.e., the all-pairs set of static round-trip propagation delays among edge networks in the Internet) is important fo...
Bo Zhang, T. S. Eugene Ng, Animesh Nandi, Rudolf H...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...