We consider a semi-supervised setting for domain adaptation where only unlabeled data is available for the target domain. One way to tackle this problem is to train a generative m...
Abstract. Similarity computation is a difficult issue in music information retrieval, because it tries to emulate the special ability that humans show for pattern recognition in ge...
In this paper we present a fast and accurate procedure called clustered low rank matrix approximation for massive graphs. The procedure involves a fast clustering of the graph and...
This paper addresses the problem of tracking objects which undergo rapid and significant appearance changes. We propose a novel coupled-layer visual model that combines the targe...
Abstract. Automated verification of multi-threaded programs is difficult. Direct treatment of all possible thread interleavings by reasoning about the program globally is a prohib...