Sciweavers

CVPR
2004
IEEE
14 years 6 months ago
Self-Normalized Linear Tests
Making decisions based on a linear combination L of features is of course very common in pattern recognition. For distinguishing between two hypotheses or classes, the test is of ...
Sachin Gangaputra, Donald Geman
CVPR
2004
IEEE
14 years 6 months ago
Multiple Bernoulli Relevance Models for Image and Video Annotation
Retrieving images in response to textual queries requires some knowledge of the semantics of the picture. Here, we show how we can do both automatic image annotation and retrieval...
Shaolei Feng, Raghavan Manmatha, Victor Lavrenko
CVPR
2004
IEEE
14 years 6 months ago
Efficient Belief Propagation for Early Vision
Markov random field models provide a robust and unified framework for early vision problems such as stereo, optical flow and image restoration. Inference algorithms based on graph...
Pedro F. Felzenszwalb, Daniel P. Huttenlocher
CVPR
2004
IEEE
14 years 6 months ago
Robust Subspace Clustering by Combined Use of kNND Metric and SVD Algorithm
Subspace clustering has many applications in computer vision, such as image/video segmentation and pattern classification. The major issue in subspace clustering is to obtain the ...
Qifa Ke, Takeo Kanade
CVPR
2004
IEEE
14 years 6 months ago
A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues
In this paper we are interested in the joint reconstruction of geometry and photometry of scenes with multiple moving objects from a collection of motion-blurred images. We make s...
Paolo Favaro, Stefano Soatto
CVPR
2004
IEEE
14 years 6 months ago
Inference of Multiple Subspaces from High-Dimensional Data and Application to Multibody Grouping
Multibody grouping is a representative of applying subspace constraints in computer vision tasks. Under linear projection models, feature points of multibody reside in multiple su...
Zhimin Fan, Jie Zhou, Ying Wu
CVPR
2004
IEEE
14 years 6 months ago
3D Models Coding and Morphing for Efficient Video Compression
This paper presents new results in the field of video coding and compression using 3D information. Contrary to prior art in 3D model-based coding where 3D models have to be known,...
Franck Galpin, Koichiro Deguchi, Luce Morin, Rapha...
CVPR
2004
IEEE
14 years 6 months ago
Multibody Motion Segmentation Based on Simulated Annealing
The problem of multibody motion segmentation is an important and challenging issue in computer vision. In this paper, a novel segmentation technique based on simulated annealing (...
Zhimin Fan, Jie Zhou, Ying Wu
CVPR
2004
IEEE
14 years 6 months ago
Separating Style and Content on a Nonlinear Manifold
Ahmed M. Elgammal, Chan-Su Lee