Sciweavers

478 search results - page 33 / 96
» Unsupervised Learning of Image Transformations
Sort
View
ICMCS
2009
IEEE
415views Multimedia» more  ICMCS 2009»
13 years 7 months ago
A new localized superpixel Markov random field for image segmentation
In this paper, we present a novel localized Markov random field (MRF) method based on superpixels for region segmentation. Early vision problems could be formulated as pixel label...
Xiaofeng Wang, Xiao-Ping Zhang
GECCO
2003
Springer
120views Optimization» more  GECCO 2003»
14 years 3 months ago
New Usage of SOM for Genetic Algorithms
Abstract. Self-Organizing Map (SOM) is an unsupervised learning neural network and it is used for preserving the structural relationships in the data without prior knowledge. SOM h...
Jung Hwan Kim, Byung Ro Moon
ICIP
2002
IEEE
14 years 11 months ago
Learning similarity space
In this study, we suggest a method to adapt an image retrieval system into a configurable one. Basically, original feature space of a content-based retrieval system is nonlinearly...
Abdurrahman Çarkacioglu, Fatos T. Yarman-Vu...
ADMA
2006
Springer
167views Data Mining» more  ADMA 2006»
14 years 3 months ago
A Correlation Approach for Automatic Image Annotation
The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...
David R. Hardoon, Craig Saunders, Sándor Sz...
CVPR
2004
IEEE
14 years 12 months ago
Is Bottom-Up Attention Useful for Object Recognition?
A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which...
Ueli Rutishauser, Dirk Walther, Christof Koch, Pie...