Sciweavers

571 search results - page 7 / 115
» One person labels one million images
Sort
View
ICDAR
2009
IEEE
13 years 5 months ago
Unconstrained Handwritten Document Layout Extraction Using 2D Conditional Random Fields
The paper describes a new approach using a Conditional Random Fields (CRFs) to extract physical and logical layouts in unconstrained handwritten letters such as those sent by indi...
Florent Montreuil, Emmanuele Grosicki, Laurent Heu...
ICPR
2008
IEEE
14 years 1 months ago
Collaborative and content-based image labeling
Many on-line photo sharing systems allow users to tag their images so as to support semantic image search. In this paper, we study how one can take advantages of the already-tagge...
Ning Zhou, W. K. Cheung, Xiangyang Xue, Guoping Qi...
ISBI
2004
IEEE
14 years 8 months ago
A Method for Reconstructing Label Images From a Few Projections, as Motivated by Electron Microscopy
Our aim is to produce a tessellation of space into small voxels and, based on only a few tomographic projections of an object, assign to each voxel a label that indicates one of t...
Hstau Y. Liao, Gabor T. Herman
AAAI
2010
13 years 8 months ago
Facial Age Estimation by Learning from Label Distributions
One of the main difficulties in facial age estimation is the lack of sufficient training data for many ages. Fortunately, the faces at close ages look similar since aging is a slo...
Xin Geng, Kate Smith-Miles, Zhi-Hua Zhou
ICIP
2007
IEEE
14 years 1 months ago
Using a Markov Network to Recognize People in Consumer Images
Markov networks are an effective tool for the difficult but important problem of recognizing people in consumer image collections. Given a small set of labeled faces, we seek to ...
Andrew C. Gallagher, Tsuhan Chen