Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...
Those motion parameters that cannot be recovered from image measurements are unobservable in the visual dynamic system. This paper studies this important issue of singularity in th...
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
In this demo, we present a method called LocalRank to rank web pages. Our method integrates the web and a local user database with semantic links including geographical ones. We fi...
In this paper we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object a...
Ahmed M. Elgammal, Ramani Duraiswami, Larry S. Dav...