Most face recognition algorithms use a “distancebased” approach: gallery and probe images are projected into a low dimensional feature space and decisions about matching are b...
We consider the problem of approximate range counting over streams of d-dimensional points. In the data stream model, the algorithm makes a single scan of the data, which is prese...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...
Prediction is emerging as an essential ingredient for real-time monitoring, planning and decision support applications such as intrusion detection, e-commerce pricing and automate...
Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structur...