Abstract. In order to evaluate the quality of segmentations of an image and assess intra- and inter-expert variability in segmentation performance, an Expectation Maximization (EM)...
We present a class of richly structured, undirected hidden variable models suitable for simultaneously modeling text along with other attributes encoded in different modalities. O...
Clustering is a fundamental task in many vision applications. To date, most clustering algorithms work in a batch setting and training examples must be gathered in a large group b...
We present a new data set encoding localized semantics for 1014 images and a methodology for using this kind of data for recognition evaluation. This methodology establishes protoc...
The problem of maintaining geometric structures for points in motion has been well studied over the years. Much theoretical work to date has been based on the assumption that point...