We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based imag...
Analyzing sequence data has become increasingly important recently in the area of biological sequences, text documents, web access logs, etc. In this paper, we investigate the pro...
We study modular, automatic code generation from hierarchical block diagrams with synchronous semantics. Such diagrams are the fundamental model behind widespread tools in the emb...
Roberto Lublinerman, Christian Szegedy, Stavros Tr...
Motivated by numerous applications in which the data may be modeled by a variable subscripted by three or more indices, we develop a tensor-based extension of the matrix CUR decom...
Michael W. Mahoney, Mauro Maggioni, Petros Drineas
We consider the problem of improving named entity recognition (NER) systems by using external dictionaries--more specifically, the problem of extending state-of-the-art NER system...