— In this paper a neural network based controller for robot positioning and tracking using direct monocular visual feedback is proposed. The visual information is provided using ...
While traditional approaches to code profiling help locate performance bottlenecks, they offer only limited support for removing these bottlenecks. The main reason is the lack of v...
—CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene ...
In this article, we present the algorithms and results of our participation in the medical image annotation and retrieval tasks of ImageCLEFmed 2006. We exploit both global featur...
Jing Liu, Yang Hu, Mingjing Li, Songde Ma, Wei-Yin...
Previous content extraction evaluations have neglected to address problems which complicate the incorporation of extracted information into an existing knowledge base. Previous qu...
Paul McNamee, Hoa Trang Dang, Heather Simpson, Pat...