Sciweavers

324 search results - page 36 / 65
» Attention can improve a simple model for object recognition
Sort
View
CVPR
2009
IEEE
16 years 4 months ago
Convexity and Bayesian Constrained Local Models
The accurate localization of facial features plays a fundamental role in any face recognition pipeline. Constrained local models (CLM) provide an effective approach to localizati...
Ulrich Paquet (Imense Ltd)
UAI
2003
14 years 11 months ago
On the Convergence of Bound Optimization Algorithms
Many practitioners who use EM and related algorithms complain that they are sometimes slow. When does this happen, and what can be done about it? In this paper, we study the gener...
Ruslan Salakhutdinov, Sam T. Roweis, Zoubin Ghahra...
ICPR
2008
IEEE
15 years 11 months ago
A method of feature selection using contribution ratio based on boosting
AdaBoost and support vector machines (SVM) algorithms are commonly used in the field of object recognition. As classifiers, their classification performance is sensitive to affect...
Masamitsu Tsuchiya, Hironobu Fujiyoshi
ICCV
2011
IEEE
13 years 9 months ago
Gradient-based learning of higher-order image features
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
Roland Memisevic
ICPR
2008
IEEE
15 years 4 months ago
Back to the future: Robust foreground extraction with reversed-time background modeling
“Ghosts” arise in traditional background subtraction when an object starts to move, causing the exposed background to be labelled as a ghost foreground. With background model ...
Akhilesh Kumar Sinha, Prithwijit Guha, Amitabha Mu...