Sciweavers

363 search results - page 62 / 73
» Probabilistic Data Generation for Deduplication and Data Lin...
Sort
View
CVPR
2009
IEEE
13 years 10 months ago
Robust unsupervised segmentation of degraded document images with topic models
Segmentation of document images remains a challenging vision problem. Although document images have a structured layout, capturing enough of it for segmentation can be difficult....
Timothy J. Burns, Jason J. Corso
NIPS
2008
13 years 9 months ago
The Recurrent Temporal Restricted Boltzmann Machine
The Temporal Restricted Boltzmann Machine (TRBM) is a probabilistic model for sequences that is able to successfully model (i.e., generate nice-looking samples of) several very hi...
Ilya Sutskever, Geoffrey E. Hinton, Graham W. Tayl...
NIPS
2003
13 years 8 months ago
Human and Ideal Observers for Detecting Image Curves
This paper compares the ability of human observers to detect target image curves with that of an ideal observer. The target curves are sampled from a generative model which speci...
Alan L. Yuille, Fang Fang, Paul R. Schrater, Danie...
CVIU
2008
82views more  CVIU 2008»
13 years 7 months ago
Shape matching and registration by data-driven EM
In this paper, we present an efficient and robust algorithm for shape matching, registration, and detection. The task is to geometrically transform a source shape to fit a target ...
Zhuowen Tu, Songfeng Zheng, Alan L. Yuille
IJCV
2007
196views more  IJCV 2007»
13 years 7 months ago
Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition
We investigate a method for learning object categories in a weakly supervised manner. Given a set of images known to contain the target category from a similar viewpoint, learning...
Robert Fergus, Pietro Perona, Andrew Zisserman