This paper presents a hybrid modeling system that fuses LiDAR data, an aerial image and ground view images for rapid creation of accurate building models. Outlines for complex bui...
We present a description of three different algorithms that use background knowledge to improve text classifiers. One uses the background knowledge as an index into the set of tra...
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and e...
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Witnesses and victims of serious crime are often required to construct a facial composite, a visual likeness of a suspect’s face. The traditional method is for them to select in...
Charlie D. Frowd, Vicki Bruce, Melanie Pitchford, ...