Many researchers have used lexical networks and ontologies to mitigate synonymy and polysemy problems in Question Answering (QA), systems coupled with taggers, query classifiers,...
Adaptive Ridge is a special form of Ridge regression, balancing the quadratic penalization on each parameter of the model. It was shown to be equivalent to Lasso (least absolute s...
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
Dirk Ormoneit, Hedvig Sidenbladh, Michael J. Black...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
Reference Picture Selection (RPS) is a powerful error control technique for video streaming. Previously, two fast block-based motion vector concatenation (MVC) algorithms were pro...