In this work, we develop a secret sharing based compiler solution to achieve confidentiality, integrity and availability (intrusion tolerance) of critical data together, rather th...
Information networks are widely used to characterize the relationships between data items such as text documents. Many important retrieval and mining tasks rely on ranking the dat...
We present a novel clustering method using HMM parameter space and eigenvector decomposition. Unlike the existing methods, our algorithm can cluster both constant and variable leng...
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...
A major challenge for face recognition algorithms lies in the variance faces undergo while changing pose. This problem is typically addressed by building view dependent models bas...