Sciweavers

446 search results - page 61 / 90
» On the design of robust classifiers for computer vision
Sort
View
CVPR
2005
IEEE
14 years 9 months ago
Hierarchical Part-Based Visual Object Categorization
We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linkin...
Guillaume Bouchard, Bill Triggs
ICCV
1999
IEEE
14 years 9 months ago
Euclidean Reconstruction and Reprojection up to Subgroups
The necessary and sufficient conditions for being able to estimate scene structure, motion and camera calibration from a sequence of images are very rarely satisfied in practice. ...
Yi Ma, Stefano Soatto, Jana Kosecka, Shankar Sastr...
CVPR
2008
IEEE
14 years 9 months ago
Viewpoint-independent object class detection using 3D Feature Maps
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
Joerg Liebelt, Cordelia Schmid, Klaus Schertler

Source Code
1511views
15 years 6 months ago
VXL - The Vision-something-Libraries
VXL is a collection of C++ libraries designed for computer vision research and implementation. VXL is written in ANSI/ISO C++ and is designed to be portable over many platforms. Th...
ICCV
2003
IEEE
14 years 9 months ago
3D Tracking = Classification + Interpolation
Hand gestures are examples of fast and complex motions. Computers fail to track these in fast video, but sleight of hand fools humans as well: what happens too quickly we just can...
Carlo Tomasi, Slav Petrov, Arvind Sastry