CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
We propose a global optimization framework for 3D shape reconstruction from sparse noisy 3D measurements frequently encountered in range scanning, sparse featurebased stereo, and ...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
In this paper we extend the class of energy functions for which the optimal -expansion and -swap moves can be computed in polynomial time. Specifically, we introduce a class of hi...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
Although camera self-calibration and metric reconstruction have been extensively studied during the past decades, automatic metric reconstruction from long video sequences with va...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
We propose statistical data association techniques for visual tracking of enormously large numbers of objects. We do not assume any prior knowledge about the numbers involved, and...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
Kernel machines have recently been considered as a promising solution for implicit surface modelling. A key challenge of machine learning solutions is how to fit implicit shape mo...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
Pattern variation is a major factor that affects the performance of recognition systems. In this paper, a novel manifold tangent modeling method called Discriminant Additive Tange...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
This paper presents a novel framework to localize in a photograph prominent irregularities in facial skin, in particular nevi (moles, birthmarks). Their characteristic configurati...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
Reliable tracking of multiple moving objects in video is an interesting challenge, made difficult in real-world video by various sources of noise and uncertainty. We propose a Bay...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
In this note, we propose a method to perform segmentation on the tensor manifold, that is, the space of positive definite matrices of given dimension. In this work, we explicitly ...
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
Linear Discriminant Analysis (LDA) is a popular statistical approach for dimensionality reduction. LDA captures the global geometric structure of the data by simultaneously maximi...