Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new r...
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
Abstract. A class of probabilistic-logic models is considered, which increases the expressibility from HMM's and SCFG's regular and contextfree languages to, in principle...
We present a method for identifying connected gene subnetworks significantly enriched for genes that are dysregulated in specimens of a disease. These subnetworks provide a signat...