In this paper, we propose a new domain adaptation technique for neural machine translation called cost weighting, which is appropriate for adaptation scenarios in which a small in-domain data set and a large general-domain data set are available. Cost weighting incorporates a domain classifier into the neural machine translation training algorithm, using features derived from the encoder repres...

In this paper, we introduce a new concept in set-valued mappings which we have called condition $(UHS)$. Then, adding this condition to a new type of contractive set-valued mappings, recently has been introduced by Amini-Harandi [Fixed and coupled fixed points of a new type contractive set-valued mapping in complete metric spaces, Fixed point theory and applications, 215 (2012)], we prove that ...

Point set surfaces (PSS) are a smooth manifold surface approximation from a set of sample points. The surface definition is based on a projection operation that constructs local polynomial approximations and respects a minimum feature size. We present techniques for ray tracing PSSs. For the computation of ray-surface intersection the properties of the projection operation are exploited: The su...

We present an efficient scalable streaming technique for mapping highly detailed color information on extremely dense point clouds. Our method does not require meshing or extensive processing of the input model, works on a coarsely spatially-reordered point stream and can adaptively refine point cloud geometry on the basis of image content. Seamless multi-band image blending is obtained by usin...