Segmentation of foreground and background has been an important research problem arising out of many applications including video surveillance. A method commonly used for segmenta...
Pradeep K. Atrey, Vinay Kumar, Anurag Kumar, Mohan...
In this paper, we propose a new method, Parametric Embedding (PE), for visualizing the posteriors estimated over a mixture model. PE simultaneously embeds both objects and their c...
Tomoharu Iwata, Kazumi Saito, Naonori Ueda, Sean S...
In this paper we present a novel approach for estimating featurespace maximum likelihood linear regression (fMLLR) transforms for full-covariance Gaussian models by directly maxim...
Arnab Ghoshal, Daniel Povey, Mohit Agarwal, Pinar ...
Language model (LM) adaptation is often achieved by combining a generic LM with a topic-specific model that is more relevant to the target document. Unlike previous work on unsup...
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...