—When is optimal estimation linear? It is well-known that, in the case of a Gaussian source contaminated with Gaussian noise, a linear estimator minimizes the mean square estimat...
Fact collections are mostly built using semi-supervised relation extraction techniques and wisdom of the crowds methods, rendering them inherently noisy. In this paper, we propose...
—Optical flow estimation is classically marked by the requirement of dense sampling in time. While coarse-to-fine warping schemes have somehow relaxed this constraint, there is...
—This paper introduces a new sensory system for the 2-D detection, tracking, and prediction of human motions. Using the data acquired through the sensory system, a model of a hum...
We consider the problem of automatically extracting general lists from the web. Existing approaches are mostly dependent upon either the underlying HTML markup or the visual struc...
Fabio Fumarola, Tim Weninger, Rick Barber, Donato ...