We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up,...
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
In many AI domains such as product configuration, a user should interactively specify a solution that must satisfy a set of constraints. In such scenarios, offline compilation of ...
Henrik Reif Andersen, Tarik Hadzic, David Pisinger
Record linkage identifies multiple records referring to the same entity even if they are not bit-wise identical. It is thus an essential technology for data integration and data c...
—We propose a novel approach for the reconstruction of urban structures from 3D point clouds with an assumption of Manhattan World (MW) building geometry; i.e., the predominance ...
Carlos A. Vanegas, Daniel G. Aliaga, Bedrich Benes