Abstract. This paper presents an online learning algorithm for appearancebased gaze estimation that allows free head movement in a casual desktop environment. Our method avoids the...
Model compensation schemes are a powerful approach to handling mismatches between training and testing conditions. Normally these schemes are run in a batch adaptation mode, re-re...
— Several multi-objective evolutionary algorithms compare the hypervolumes of different sets of points during their operation, usually for selection or archiving purposes. The ba...
Integrity checking is an essential means for the preservation of the intended semantics of a deductive database. Incrementality is the only feasible approach to checking and can be...
An open issue in data-driven dependency parsing is how to handle non-projective dependencies, which seem to be required by linguistically adequate representations, but which pose ...