Sciweavers

4343 search results - page 697 / 869
» Segmentation from a Box
Sort
View
BMVC
2002
14 years 20 days ago
Low Density Feature Point Matching for Articulated Pose Identification
We describe a general algorithm for identifying an arbitrary pose of an articulated subject with low density feature points. The algorithm aims to establish a one-to-one correspon...
Horst Holstein, Baihua Li
CIKM
2008
Springer
14 years 7 days ago
Identification of class specific discourse patterns
In this paper we address the problem of extracting important (and unimportant) discourse patterns from call center conversations. Call centers provide dialog based calling-in supp...
Anup Chalamalla, Sumit Negi, L. Venkata Subramania...
LREC
2010
224views Education» more  LREC 2010»
13 years 11 months ago
Construction of Chunk-Aligned Bilingual Lecture Corpus for Simultaneous Machine Translation
With the development of speech and language processing, speech translation systems have been developed. These studies target spoken dialogues, and employ consecutive interpretatio...
Masaki Murata, Tomohiro Ohno, Shigeki Matsubara, Y...
LREC
2010
172views Education» more  LREC 2010»
13 years 11 months ago
Evaluating Utility of Data Sources in a Large Parallel Czech-English Corpus CzEng 0.9
CzEng 0.9 is the third release of a large parallel corpus of Czech and English. For the current release, CzEng was extended by significant amount of texts from various types of so...
Ondrej Bojar, Adam Liska, Zdenek Zabokrtský
LREC
2010
193views Education» more  LREC 2010»
13 years 11 months ago
DiSCo - A German Evaluation Corpus for Challenging Problems in the Broadcast Domain
Typical broadcast material contains not only studio-recorded texts read by trained speakers, but also spontaneous and dialect speech, debates with cross-talk, voice-overs, and on-...
Doris Baum, Daniel Schneider, Rolf Bardeli, Jochen...