Sciweavers

3320 search results - page 326 / 664
» Accessibility of the Database Literature
Sort
View
FLAIRS
2004
15 years 9 months ago
Automatic Generation of Background Text to Aid Classification
We illustrate that Web searches can often be utilized to generate background text for use with text classification. This is the case because there are frequently many pages on the...
Sarah Zelikovitz, Robert Hafner
ICIS
2004
15 years 9 months ago
Reconciling Attribute Values from Multiple Data Sources
Because of the heterogeneous nature of multiple data sources, data integration is often one of the most challenging tasks of today's information systems. While the existing l...
Zhengrui Jiang, Sumit Sarkar, Prabuddha De, Debabr...
133
Voted
ANLP
1997
81views more  ANLP 1997»
15 years 9 months ago
Name pronunciation in German text-to-speech synthesis
We describe the name analysis and pronunciation component in the German version of the Bell Labs multilingual text-tospeech system. We concentrate on street names because they enc...
Stefanie Jannedy, Bernd Möbius
226
Voted
ICASSP
2010
IEEE
15 years 7 months ago
Removing illumination artifacts from face images using the nuisance attribute projection
Illumination induced appearance changes represent one of the open challenges in automated face recognition systems still significantly influencing their performance. Several tec...
Vitomir Struc, Bostjan Vesnicer, France Mihelic, N...
CORR
2008
Springer
97views Education» more  CORR 2008»
15 years 7 months ago
Fast Density Codes for Image Data
Recently, a new method for encoding data sets in the form of "Density Codes" was proposed in the literature (Courrieu, 2006). This method allows to compare sets of points...
Pierre Courrieu