Sciweavers

CVPR
2005
IEEE
15 years 1 months ago
Geo-Consistency for Wide Multi-Camera Stereo
This paper presents a new model to overcome the occlusion problems coming from wide baseline multiple camera stereo. Rather than explicitly modeling occlusions in the matching cos...
Marc-Antoine Drouin, Martin Trudeau, Sébast...
CVPR
2005
IEEE
15 years 1 months ago
Simultaneous Modeling and Tracking (SMAT) of Feature Sets
A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a poste...
N. D. H. Dowson, Richard Bowden
CVPR
2005
IEEE
15 years 1 months ago
Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior
To increase the range of sizes of video scene text recognizable by optical character recognition (OCR), we developed a Bayesian super-resolution algorithm that uses a text-specifi...
Katherine Donaldson, Gregory K. Myers
CVPR
2005
IEEE
15 years 1 months ago
Modeling Dynamic Scenes with Active Appearance
In this work we propose a model for video scenes that contain temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of ...
Gianfranco Doretto
CVPR
2005
IEEE
15 years 1 months ago
Mixture Trees for Modeling and Fast Conditional Sampling with Applications in Vision and Graphics
We introduce mixture trees, a tree-based data-structure for modeling joint probability densities using a greedy hierarchical density estimation scheme. We show that the mixture tr...
Frank Dellaert, Vivek Kwatra, Sang Min Oh
CVPR
2005
IEEE
15 years 1 months ago
Discriminative Training for Object Recognition Using Image Patches
We present a method for automatically learning discriminative image patches for the recognition of given object classes. The approach applies discriminative training of log-linear...
Thomas Deselaers, Daniel Keysers, Hermann Ney
CVPR
2005
IEEE
15 years 1 months ago
Histograms of Oriented Gradients for Human Detection
We study the question of feature sets for robust visual object recognition, adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient ba...
Navneet Dalal, Bill Triggs
CVPR
2005
IEEE
15 years 1 months ago
Polarization Multiplexing for Bidirectional Imaging
Our goal is to incorporate polarization in appearancebased modeling in an efficient and meaningful way. Polarization has been used in numerous prior studies for separating diffuse...
Oana G. Cula, Kristin J. Dana, Dinesh K. Pai, Dong...
CVPR
2005
IEEE
15 years 1 months ago
Spectral Segmentation with Multiscale Graph Decomposition
We present a multiscale spectral image segmentation algorithm. In contrast to most multiscale image processing, this algorithm works on multiple scales of the image in parallel, w...
Florence Bénézit, Jianbo Shi, Timoth...
CVPR
2005
IEEE
15 years 1 months ago
Spatial Priors for Part-Based Recognition Using Statistical Models
We present a class of statistical models for part-based object recognition that are explicitly parameterized according to the degree of spatial structure they can represent. These...
David J. Crandall, Pedro F. Felzenszwalb, Daniel P...