Sciweavers

516 search results - page 22 / 104
» A Multiresolution Threshold Selection Method Based on Traini...
Sort
View
JMLR
2006
89views more  JMLR 2006»
13 years 8 months ago
Maximum-Gain Working Set Selection for SVMs
Support vector machines are trained by solving constrained quadratic optimization problems. This is usually done with an iterative decomposition algorithm operating on a small wor...
Tobias Glasmachers, Christian Igel
BSN
2009
IEEE
116views Sensor Networks» more  BSN 2009»
14 years 3 months ago
Detecting Walking Gait Impairment with an Ear-worn Sensor
— This paper investigates an ear worn sensor for the development of a gait analysis framework. Instead of explicitly defining gait features that indicate injury or impairment, an...
Louis Atallah, Omer Aziz, Benny P. L. Lo, Guang-Zh...
AAAI
2008
13 years 11 months ago
Concept-Based Feature Generation and Selection for Information Retrieval
Traditional information retrieval systems use query words to identify relevant documents. In difficult retrieval tasks, however, one needs access to a wealth of background knowled...
Ofer Egozi, Evgeniy Gabrilovich, Shaul Markovitch
MVA
2000
203views Computer Vision» more  MVA 2000»
13 years 10 months ago
An Environment to Test Progressive Refinement of Indexing for Content-Based Image Retrieval
Content-based image retrieval is a fairly new discipline. Yet research in this field has highlighted many approaches that show good performance in specific subproblems using singl...
Maria Grazia Albanesi, Marco Ferretti, Alessandro ...
NAACL
2007
13 years 10 months ago
A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation
We compare two pivot strategies for phrase-based statistical machine translation (SMT), namely phrase translation and sentence translation. The phrase translation strategy means t...
Masao Utiyama, Hitoshi Isahara