We present a method for detecting and parsing buildings from unorganized 3D point clouds into a compact, hierarchical representation that is useful for high-level tasks. The input...
Matching near-infrared (NIR) face images to visible light (VIS) face images offers a robust approach to face recognition with unconstrained illumination. In this paper we propose ...
Scene text images feature an abundance of font style variety but a dearth of data in any given query. Recognition methods must be robust to this variety or adapt to the query data...
This workshop will explore the use of low-cost materials and tools to build textile-based interfaces. We will introduce a range methods for handcrafting textile sensors and circui...
—This paper describes a new logic-based approach for representing and reasoning about metabolic networks. First it shows how biological pathways can be elegantly represented in a...