In this paper we investigate random forest based language model adaptation. Large amounts of out-of-domain data are used to grow the decision trees while very small amounts of in-...
For p 1, we prove that every forest with p trees whose sizes are a1, . . . , ap can be embedded in any graph containing at least p i=1(ai + 1) vertices and having minimum degree ...
This paper proposes an alternative approach to the standard notion of rational (or regular) expression for tree languages. The main difference is that in the new notion we have on...
In this paper we propose an approach for action recognition based on a vocabulary forest of local motionappearance features. Large numbers of features with associated motion vecto...
We consider the number of nodes in the levels of unlabelled rooted random trees and show that the stochastic process given by the properly scaled level sizes weakly converges to th...