Standard image based segmentation approaches perform poorly when there is little or no contrast along boundaries of different regions. In such cases, segmentation is largely perfor...
Kilian M. Pohl, John W. Fisher III, Ron Kikinis, W...
This paper presents Japanese morphological analysis based on conditional random fields (CRFs). Previous work in CRFs assumed that observation sequence (word) boundaries were fixed...
We introduce the notion of restricted Bayes optimal classifiers. These classifiers attempt to combine the flexibility of the generative approach to classification with the high ac...
Many tasks in computer vision involve assigning a label (such as disparity) to every pixel. These tasks can be formulated as energy minimization problems. In this paper, we conside...
Most of previous approaches to automatic prosodic event detection are based on supervised learning, relying on the availability of a corpus that is annotated with the prosodic lab...