This paper proposes a new technique for generating three-dimensional speech animation. The proposed technique takes advantage of both data-driven and machine learning approaches. ...
We study how to best use crowdsourced relevance judgments learning to rank [1, 7]. We integrate two lines of prior work: unreliable crowd-based binary annotation for binary classi...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
In this paper we consider the competition on the Internet between information providers to maximise their exposure to a relevant audience. Spammers and Search engine gamers adopt a...
Abstract. This paper addresses a task of variable selection which consists in choosing a subset of variables that is sufficient to predict the target label well. Here instead of tr...