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...
This paper introduces an information theoretic approach to verification of modular causal probabilistic models. We assume systems which are gradually extended by adding new functi...
This paper presents a novel approach to skim and describe 3D videos. 3D video is an imaging technology which consists in a stream of 3D models in motion captured by a synchronized ...
Tony Tung (Kyoto University), Takashi Matsuyama (K...
Probabilistic models of the performance of computer systems are useful both for predicting system performance in new conditions, and for diagnosing past performance problems. The ...
Abstract. We show that several previously proposed passage-based document ranking principles, along with some new ones, can be derived from the same probabilistic model. We use lan...