Sciweavers

103
Voted
CVPR
2004
IEEE
16 years 2 months ago
Perspective Shape-from-Shading by Fast Marching
Shape-from-Shading (SfS) is a fundamental problem in Computer Vision. At its basis lies the image irradiance equation. Recently, the authors proposed to base the image irradiance ...
Ariel Tankus, Nir A. Sochen, Yehezkel Yeshurun
CVPR
2004
IEEE
16 years 2 months ago
Difference Sphere: An Approach to Near Light Source Estimation
We present a novel approach for estimating light sources from a single image of a scene that is illuminated by major near point light sources, a few directional light sources and ...
Takeshi Takai, Koichiro Niinuma, Atsuto Maki, Taka...
CVPR
2004
IEEE
16 years 2 months ago
Automatic Cascade Training with Perturbation Bias
Face detection methods based on a cascade architecture have demonstrated fast and robust performance. Cascade learning is aided by the modularity of the architecture in which node...
Jie Sun, James M. Rehg, Aaron F. Bobick
CVPR
2004
IEEE
16 years 2 months ago
Thermal Face Recognition in an Operational Scenario
We present results on the latest advances in thermal infrared face recognition, and its use in combination with visible imagery. Previous research has shown high performance under...
Diego A. Socolinsky, Andrea Selinger
121
Voted
CVPR
2004
IEEE
16 years 2 months ago
Reconstructing Open Surfaces from Unorganized Data Points
In this paper a method for fitting open surfaces to an unorganized set of data points is presented using a level set representation of the surface. This is done by tracking a curv...
Jan Erik Solem, Anders Heyden
76
Voted
CVPR
2004
IEEE
16 years 2 months ago
Variational Mixture Smoothing for Non-Linear Dynamical Systems
Cristian Sminchisescu, Allan D. Jepson
CVPR
2004
IEEE
16 years 2 months ago
Integrating and Employing Multiple Levels of Zoom for Activity Recognition
Paul Smith, Mubarak Shah, Niels da Vitoria Lobo
105
Voted
CVPR
2004
IEEE
16 years 2 months ago
Camera Network Calibration from Dynamic Silhouettes
In this paper we present an automatic method for calibrating a network of cameras from only silhouettes. This is particularly useful for shape-from-silhouette or visual-hull syste...
Sudipta N. Sinha, Marc Pollefeys, Leonard McMillan
117
Voted
CVPR
2004
IEEE
16 years 2 months ago
Video Data Mining Using Configurations of Viewpoint Invariant Regions
We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features....
Josef Sivic, Andrew Zisserman
101
Voted
CVPR
2004
IEEE
16 years 2 months ago
Invariant Operators, Small Samples, and the Bias-Variance Dilemma
Invariant features or operators are often used to shield the recognition process from the effect of "nuisance" parameters, such as rotations, foreshortening, or illumina...
Xiaojin Shi, Roberto Manduchi