Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can...
Robert Fergus, Fei-Fei Li 0002, Pietro Perona, And...
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
One of the central problems in building broad-coverage story understanding systems is generating expectations about event sequences, i.e. predicting what happens next given some a...
Abstract—Contour features play an important role in object recognition. Psychological experiments have shown that maximum-curvature points are most distinctive along a contour [6...
Mobile computing technologies and social software have given new challenges to technology-enhanced learning. Simple e-learning system personalization, adaptation and authoring beco...