Sciweavers

1474 search results - page 196 / 295
» Computing stable models: worst-case performance estimates
Sort
View
CVBIA
2005
Springer
15 years 9 months ago
Shape Based Segmentation of Anatomical Structures in Magnetic Resonance Images
Standard image based segmentation approaches perform poorly when there is little or no contrast along boundaries of different regions. In such cases, segmentation is largely perfor...
Kilian M. Pohl, John W. Fisher III, Ron Kikinis, W...
ICC
2007
IEEE
117views Communications» more  ICC 2007»
15 years 10 months ago
On The Optimal Amount of Training for Peak-Power-Limited Rayleigh Fading Channels
— We consider the optimal amount of training for single-antenna Rayleigh flat fading channels with peak-powerlimited input. The receiver uses known training symbols to perform m...
Wei Mao, Xin Su, Ming Zhao 0001, Xibin Xu
ICCV
2009
IEEE
2205views Computer Vision» more  ICCV 2009»
16 years 9 months ago
Video stabilization using robust feature trajectories
This paper proposes a new approach for video stabilization. Most existing video stabilization methods adopt a framework of three steps, motion estimation, motion compensation an...
Ken-Yi Lee, Yung-Yu, Chuang Bing-Yu, Chen Ming Ouh...
CVPR
2005
IEEE
16 years 6 months ago
Dense Photometric Stereo Using a Mirror Sphere and Graph Cut
We present a surprisingly simple system that allows for robust normal reconstruction by dense photometric stereo, in the presence of severe shadows, highlight, transparencies, com...
Tai-Pang Wu, Chi-Keung Tang
CVPR
2010
IEEE
16 years 11 days ago
An Object-Dependent Hand Pose Prior from Sparse Training Data
In this paper, we propose a prior for hand pose estimation that integrates the direct relation between a manipulating hand and a 3d object. This is of particular interest for a va...
Henning Hamer, Juergen Gall, Thibaut Weise, Luc Va...