We propose a novel patch-based image representation that is useful because it (1) inherently detects regions with repetitive structure at multiple scales and (2) yields a paramete...
Lena Gorelick, Andrew Delong, Olga Veksler, Yuri B...
In this paper, we investigate the low coverage problem of efficient broadcast protocols in wireless ad hoc networks with realistic physical layer models. To minimize energy consum...
This paper describes an accurate, extensible method for automatically classifying unknown foreign words that requires minimal monolingual resources and no bilingual training data ...
The explosion in the amount of free text materials on the Internet, and the use of this information by people from all walks of life, has made the issue of generalized information...
In this paper we describe a method for Minimum Bayes Risk decoding for speech recognition. This is a technique similar to Consensus a.k.a. Confusion Network Decoding, in which we ...