Connectedness of random walk segmentation is examined, and novel properties are discovered, by considering electrical circuits equivalent to random walks. A theoretical analysis s...
—A novel framework is proposed for the design of cost-sensitive boosting algorithms. The framework is based on the identification of two necessary conditions for optimal cost-sen...
—The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single frame object recogn...
— Kernel mapping is one of the most used approaches to intrinsically derive nonlinear classifiers. The idea is to use a kernel function which maps the original nonlinearly separ...
— This paper proposes a novel method for recognizing faces degraded by blur using deblurring of facial images. The main issue is how to infer a Point Spread Function (PSF) repres...
— This paper addresses recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such meas...
Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patri...
—In this paper, we describe the explicit application of articulation constraints for estimating the motion of a system of articulated planes. We relate articulations to the relat...
—Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learni...
—Human faces are remarkably similar in global properties, including size, aspect ratio, and location of main features, but can vary considerably in details across individuals, ge...