Sciweavers

999 search results - page 14 / 200
» Efficient Learning to Label Images
Sort
View
ICML
2009
IEEE
15 years 10 months ago
Semi-supervised learning using label mean
Semi-Supervised Support Vector Machines (S3VMs) typically directly estimate the label assignments for the unlabeled instances. This is often inefficient even with recent advances ...
Yu-Feng Li, James T. Kwok, Zhi-Hua Zhou
ICML
2009
IEEE
15 years 10 months ago
Learning instance specific distances using metric propagation
In many real-world applications, such as image retrieval, it would be natural to measure the distances from one instance to others using instance specific distance which captures ...
De-Chuan Zhan, Ming Li, Yu-Feng Li, Zhi-Hua Zhou
ICPR
2008
IEEE
15 years 4 months ago
Text detection from scene images using sparse representation
A sparse representation based method is proposed for text detection from scene images. We start with edge information extracted using Canny operator and then group these edge poin...
Wumo Pan, Tien D. Bui, Ching Y. Suen
PAMI
2010
396views more  PAMI 2010»
14 years 8 months ago
Self-Validated Labeling of Markov Random Fields for Image Segmentation
—This paper addresses the problem of self-validated labeling of Markov random fields (MRFs), namely to optimize an MRF with unknown number of labels. We present graduated graph c...
Wei Feng, Jiaya Jia, Zhi-Qiang Liu
ICIP
2008
IEEE
15 years 11 months ago
Supervised image segmentation via ground truth decomposition
This paper proposes a data driven image segmentation algorithm, based on decomposing the target output (ground truth). Classical pixel labeling methods utilize machine learning al...
Ilya Levner, Russell Greiner, Hong Zhang