Sciweavers

2829 search results - page 483 / 566
» Regularization Methods for Additive Models
Sort
View
TCSV
2010
14 years 11 months ago
Compressed Domain Video Object Segmentation
We propose a compressed domain video object segmentation method for MPEG or MPEG-like encoded videos. Computational superiority is the main advantage of the compressed domain proc...
Fatih Murat Porikli, Faisal I. Bashir, Huifang Sun
SDM
2012
SIAM
216views Data Mining» more  SDM 2012»
13 years 7 months ago
Feature Selection "Tomography" - Illustrating that Optimal Feature Filtering is Hopelessly Ungeneralizable
:  Feature Selection “Tomography” - Illustrating that Optimal Feature Filtering is Hopelessly Ungeneralizable George Forman HP Laboratories HPL-2010-19R1 Feature selection; ...
George Forman
CVPR
2009
IEEE
1131views Computer Vision» more  CVPR 2009»
16 years 12 months ago
Continuous Depth Estimation for Multi-view Stereo
Depth-map merging approaches have become more and more popular in multi-view stereo (MVS) because of their flexibility and superior performance. The quality of depth map used fo...
Yebin Liu (Tsinghua University), Xun Cao (Tsinghu...
CVPR
2003
IEEE
16 years 6 months ago
Stereo Matching with Reflections and Translucency
In this paper, we address the stereo matching problem in the presence of reflections and translucency, where image formation can be modeled as the additive superposition of layers...
Yanghai Tsin, Sing Bing Kang, Richard Szeliski
ICIP
2008
IEEE
16 years 6 months ago
EKF pose estimation: How many filters and cameras to use?
The Extended Kalman Filter (EKF) is suitable for real-time pose estimation due its low computational demand and ability to handle the nonlinear perspective camera model. There are...
Mohammad Ehab Ragab, Kin-hong Wong, Jun Zhou Chen,...