Abstract. We propose a novel probabilistic method, based on latent variable models, for unsupervised topographic visualisation of dynamically evolving, coherent textual information...
Practical experience has shown that in order to obtain the best possible performance, prior knowledge about invariances of a classification problem at hand ought to be incorporated...
—To estimate the convolutional encoder state from received data, one may use the inverse to the encoder G. However, channel errors make this method unreliable. We propose a metho...
—Tracking deforming objects involves estimating the global motion of the object and its local deformations as a function of time. Tracking algorithms using Kalman filters or part...
Yogesh Rathi, Namrata Vaswani, Allen Tannenbaum, A...
Abstract—In this paper a novel system for automatic detection and segmentation of focal liver lesions in CT images is presented. It utilizes a probabilistic boosting tree to clas...
Arne Militzer, Tobias Hager, Florian Jäger, Chris...