We propose a new method for rapid 3D object indexing that combines feature-based methods with coarse alignment-based matching techniques. Our approach achieves a sublinear complexi...
Bogdan Matei, Ying Shan, Harpreet S. Sawhney, Yi T...
We investigate the problem of learning to rank for document retrieval from the perspective of learning with multiple objective functions. We present solutions to two open problems...
Krysta Marie Svore, Maksims Volkovs, Christopher J...
Databases are often incomplete because of the presence of disjunctive information, due to con icts, partial knowledge and other reasons. Queries against such databases often ask q...
We consider the problem of incrementally rendering a polyhedral scene while the viewpoint is moving. In practical situations the number of geometric primitives to be rendered can ...
Alon Efrat, Leonidas J. Guibas, Olaf A. Hall-Holt,...
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...