Sciweavers

CVPR
2008
IEEE
15 years 1 months ago
Learning patch correspondences for improved viewpoint invariant face recognition
Variation due to viewpoint is one of the key challenges that stand in the way of a complete solution to the face recognition problem. It is easy to note that local regions of the ...
Ahmed Bilal Ashraf, Simon Lucey, Tsuhan Chen
CVPR
2008
IEEE
15 years 1 months ago
Incremental learning of nonparametric Bayesian mixture models
Clustering is a fundamental task in many vision applications. To date, most clustering algorithms work in a batch setting and training examples must be gathered in a large group b...
Ryan Gomes, Max Welling, Pietro Perona
CVPR
2008
IEEE
15 years 1 months ago
Privacy preserving crowd monitoring: Counting people without people models or tracking
Antoni B. Chan, Zhang-Sheng John Liang, Nuno Vasco...
CVPR
2008
IEEE
15 years 1 months ago
A bi-illuminant dichromatic reflection model for understanding images
This paper presents a new model for understanding the appearance of objects that exhibit both body and surface reflection under realistic illumination. Specifically, the model rep...
Bruce A. Maxwell, Richard M. Friedhoff, Casey A. S...
CVPR
2008
IEEE
15 years 1 months ago
A mixed generative-discriminative framework for pedestrian classification
This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classificat...
Markus Enzweiler, Dariu M. Gavrila
CVPR
2008
IEEE
15 years 1 months ago
Unsupervised learning of visual taxonomies
Evgeniy Bart, Ian Porteous, Pietro Perona, Max Wel...
CVPR
2008
IEEE
15 years 1 months ago
Recognising faces in unseen modes: A tensor based approach
This paper addresses the limitation of current multilinear techniques (multilinear PCA, multilinear ICA) when applied to face recognition for handling faces in unseen illumination...
Santu Rana, Wanquan Liu, Mihai M. Lazarescu, Sveth...
CVPR
2008
IEEE
15 years 1 months ago
Latent topic random fields: Learning using a taxonomy of labels
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
Xuming He, Richard S. Zemel
CVPR
2008
IEEE
15 years 1 months ago
Discriminative modeling by Boosting on Multilevel Aggregates
This paper presents a new approach to discriminative modeling for classi cation and labeling. Our method, called Boosting on Multilevel Aggregates (BMA), adds a new class of hiera...
Jason J. Corso