In this paper, we present a tracking framework for capturing articulated human motions in real-time, without the need for attaching markers onto the subject's body. This is a...
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous se...
We introduce a new probability distribution over a potentially infinite number of binary Markov chains which we call the Markov Indian buffet process. This process extends the IBP...
We investigate a new, convex relaxation of an expectation-maximization (EM) variant that approximates a standard objective while eliminating local minima. First, a cautionary resu...
The FISH server is highly accurate in identifying the family membership of domains in a query protein sequence, even in the case of very low sequence identities to known homologue...