Sciweavers

456 search results - page 73 / 92
» Segmenting Documents using Multiple Lexical Features
Sort
View
CVPR
2001
IEEE
16 years 1 months ago
Event-Based Analysis of Video
Dynamic events can be regarded as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple st...
Lihi Zelnik-Manor, Michal Irani
ICSE
1999
IEEE-ACM
15 years 4 months ago
Product-Line Architectures in Industry: A Case Study
In this paper, a case study investigating the experiences from using product-line architectures is presented involving two swedish companies, Axis Communications AB and Securitas ...
Jan Bosch
TSD
2007
Springer
15 years 5 months ago
Accurate Unlexicalized Parsing for Modern Hebrew
Many state-of-the-art statistical parsers for English can be viewed as Probabilistic Context-Free Grammars (PCFGs) acquired from treebanks consisting of phrase-structure trees enri...
Reut Tsarfaty, Khalil Sima'an
ICDAR
2011
IEEE
13 years 11 months ago
A New Fourier-Moments Based Video Word and Character Extraction Method for Recognition
— This paper presents a new method based on Fourier and moments features to extract words and characters from a video text line in any direction for recognition. Unlike existing ...
Deepak Rajendran, Palaiahnakote Shivakumara, Bolan...
ICASSP
2011
IEEE
14 years 3 months ago
The SRI NIST 2010 speaker recognition evaluation system
The SRI speaker recognition system for the 2010 NIST speaker recognition evaluation (SRE) incorporates multiple subsystems with a variety of features and modeling techniques. We d...
Nicolas Scheffer, Luciana Ferrer, Martin Graciaren...