Many optimisation problems contain substructures involving constraints on sequences of decision variables. Such constraints can be very complex to express with mixed integer progra...
The l-bfgs limited-memory quasi-Newton method is the algorithm of choice for optimizing the parameters of large-scale log-linear models with L2 regularization, but it cannot be us...
In this paper, we present a robust face alignment system that is capable of dealing with exaggerating expressions, large occlusions, and a wide variety of image noises. The robustn...
Sparsity-promoting L1-regularization has recently been succesfully used to learn the structure of undirected graphical models. In this paper, we apply this technique to learn the ...
Mark W. Schmidt, Alexandru Niculescu-Mizil, Kevin ...
The goal of automatic image annotation is to automatically generate annotations for images to describe their content. In the past, statistical machine translation models have been...