Sciweavers

322 search results - page 15 / 65
» A data driven method for feature transformation
Sort
View
ICCV
2007
IEEE
14 years 1 months ago
Fast Automatic Heart Chamber Segmentation from 3D CT Data Using Marginal Space Learning and Steerable Features
Multi-chamber heart segmentation is a prerequisite for global quantification of the cardiac function. The complexity of cardiac anatomy, poor contrast, noise or motion artifacts ...
Yefeng Zheng, Adrian Barbu, Bogdan Georgescu, Mich...
NIPS
2007
13 years 9 months ago
Random Features for Large-Scale Kernel Machines
To accelerate the training of kernel machines, we propose to map the input data to a randomized low-dimensional feature space and then apply existing fast linear methods. The feat...
Ali Rahimi, Benjamin Recht
ICDE
2008
IEEE
158views Database» more  ICDE 2008»
14 years 9 months ago
CARE: Finding Local Linear Correlations in High Dimensional Data
Finding latent patterns in high dimensional data is an important research problem with numerous applications. Existing approaches can be summarized into 3 categories: feature selec...
Xiang Zhang, Feng Pan, Wei Wang
TMI
2008
149views more  TMI 2008»
13 years 7 months ago
Shape-Driven Three-Dimensional Watersnake Segmentation of Biological Membranes in Electron Tomography
Abstract--Due to the significant complexity of membrane morphology and the generally poor image quality in electron tomographic volumes, current automatic methods for segmentation ...
Hieu Tat Nguyen, Qiang Ji
IROS
2006
IEEE
128views Robotics» more  IROS 2006»
14 years 1 months ago
Improving Data Association in Vision-based SLAM
— This paper presents an approach to vision-based simultaneous localization and mapping (SLAM). Our approach uses the scale invariant feature transform (SIFT) as features and app...
Arturo Gil, Óscar Reinoso, Óscar Mar...