In this paper, we propose the use of the Maximum Entropy approach for the task of automatic image annotation. Given labeled training data, Maximum Entropy is a statistical techniqu...
Abstract— Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to simultaneously learn the names and appearances o...
Michael Jamieson, Afsaneh Fazly, Suzanne Stevenson...
Creating more fine-grained annotated data than previously relevent document sets is important for evaluating individual components in automatic question answering systems. In this...
Users’ search needs are often represented by words and images are retrieved according to such textual queries. Annotation words assigned to the stored images are most useful to ...
Abstract. In many supervised learning tasks it can be costly or infeasible to obtain objective, reliable labels. We may, however, be able to obtain a large number of subjective, po...