Abstract. We propose a generative approach to the problem of labeling images containing configurations of objects from multiple classes. The main building blocks are dense statisti...
This paper addresses real-time automatic visual tracking,
labeling and classification of a variable number of
objects such as pedestrians or/and vehicles, under timevarying
illu...
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing...
We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given a training set of images and corresponding label maps. The resulting inferen...
Mert R. Sabuncu, B. T. Thomas Yeo, Koenraad Van Le...
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...