Sciweavers

611 search results - page 64 / 123
» Do background images improve
Sort
View
CVPR
2012
IEEE
11 years 10 months ago
The Shape Boltzmann Machine: A strong model of object shape
A good model of object shape is essential in applications such as segmentation, object detection, inpainting and graphics. For example, when performing segmentation, local constra...
S. M. Ali Eslami, Nicolas Heess, John M. Winn
ICIP
2003
IEEE
14 years 9 months ago
An adaptive multigrid algorithm for region of interest diffuse optical tomography
Dueto diffuse nature of lightphotons, Diffuse Optical Tomography (DOT) image reconstruction is a challenging 3D problem with a relatively large number of unknowns and limited meas...
Murat Guven, Birsen Yazici, Xavier Intes, Britton ...
AAAI
2008
13 years 10 months ago
Concept-Based Feature Generation and Selection for Information Retrieval
Traditional information retrieval systems use query words to identify relevant documents. In difficult retrieval tasks, however, one needs access to a wealth of background knowled...
Ofer Egozi, Evgeniy Gabrilovich, Shaul Markovitch
ICIP
2007
IEEE
14 years 9 months ago
Rate-Distortion Optimal Depth Maps in the Wavelet Domain for Free-Viewpoint Rendering
We consider the problem of estimating and encoding depth maps from multiple views in the context of 3D-TV with free-viewpoint rendering. We propose a novel codec based on the Rate...
Matthieu Maitre, Yoshihisa Shinagawa, Minh N. Do
CVPR
2006
IEEE
14 years 9 months ago
Image Matching Using Photometric Information
Image matching is an essential task in many computer vision applications. It is obvious that thorough utilization of all available information is critical for the success of match...
Michael Kolomenkin, Ilan Shimshoni