Sciweavers

1585 search results - page 100 / 317
» Using a Non-prior Training Active Feature Model
Sort
View
ICCV
1999
IEEE
15 years 8 months ago
Geodesic Active Regions for Supervised Texture Segmentation
This paper presents a novel variational method for supervised texture segmentation. The textured feature space is generated by filtering the given textured images using isotropic ...
Nikos Paragios, Rachid Deriche
CSL
2007
Springer
15 years 4 months ago
Modeling durations of syllables using neural networks
In this paper, we propose a neural network model for predicting the durations of syllables. A four layer feedforward neural network trained with backpropagation algorithm is used ...
K. Sreenivasa Rao, B. Yegnanarayana
SIBGRAPI
2009
IEEE
15 years 11 months ago
Learning Discriminative Appearance-Based Models Using Partial Least Squares
Appearance information is essential for applications such as tracking and people recognition. One of the main problems of using appearance-based discriminative models is the ambig...
William Robson Schwartz, Larry S. Davis
CVPR
2010
IEEE
15 years 11 months ago
Improving web-image search results using query-relative classifiers
Web image search using text queries has received considerable attention. However, current state-of-the-art approaches require training models for every new query, and are therefore...
Josip Krapac, Moray Allan, Jakob Verbeek, Frédér...
EMNLP
2010
15 years 2 months ago
A Fast Decoder for Joint Word Segmentation and POS-Tagging Using a Single Discriminative Model
We show that the standard beam-search algorithm can be used as an efficient decoder for the global linear model of Zhang and Clark (2008) for joint word segmentation and POS-taggi...
Yue Zhang 0004, Stephen Clark