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, Carol Gannon, Mark ...
Traditional supervised visual learning simply asks annotators “what” label an image should have. We propose an approach for image classification problems requiring subjective...
Radiologists disagree with each other over the characteristics and features of what constitutes a normal mammogram and the terminology to use in the associated radiology report. R...
Robert M. Patton, Thomas E. Potok, Barbara G. Beck...
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...