Sciweavers

715 search results - page 98 / 143
» Layered Object Models for Image Segmentation
Sort
View
CVPR
2003
IEEE
15 years 11 months ago
Object-Specific Figure-Ground Segregation
We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration mode...
Stella X. Yu, Jianbo Shi
HLK
2003
IEEE
15 years 3 months ago
Reconstruction of Objects with Jagged Edges through Rao-Blackwellized Fitting of Piecewise Smooth Subdivision Curves
In some applications objects are known to have nonsmooth or “jagged” edges, which are not well approximated by smooth curves. We use subdivision curves as a simple but flexib...
Michael Kaess, Frank Dellaert
ICCV
2005
IEEE
15 years 3 months ago
Object Categorization by Learned Universal Visual Dictionary
This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class mode...
John M. Winn, Antonio Criminisi, Thomas P. Minka
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
16 years 4 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
MIR
2005
ACM
133views Multimedia» more  MIR 2005»
15 years 3 months ago
Probabilistic web image gathering
We propose a new method for automated large scale gathering of Web images relevant to specified concepts. Our main goal is to build a knowledge base associated with as many conce...
Keiji Yanai, Kobus Barnard