Sciweavers

748 search results - page 98 / 150
» Learning Feature Distance Measures for Image Correspondences
Sort
View
BMVC
2010
13 years 4 months ago
Saliency Segmentation based on Learning and Graph Cut Refinement
Saliency detection is a well researched problem in computer vision. In previous work, most of the effort is spent on manually devising a saliency measure. Instead we propose a sim...
Paria Mehrani, Olga Veksler

Publication
164views
12 years 8 months ago
A Statistical Overlap Prior for Variational Image Segmentation
This study investigates variational image segmentation with an original data term, referred to as statistical overlap prior, which measures the conformity of overlap between the no...
Ismail Ben Ayed, Shuo Li and Ian Ross
DAGM
2008
Springer
13 years 11 months ago
An Evolutionary Approach for Learning Motion Class Patterns
This article presents a genetic learning algorithm to derive discrete patterns that can be used for classification and retrieval of 3D motion capture data. Based on boolean motion ...
Meinard Müller, Bastian Demuth, Bodo Rosenhah...
ICPR
2006
IEEE
14 years 10 months ago
Dissimilarity-based classification for vectorial representations
General dissimilarity-based learning approaches have been proposed for dissimilarity data sets [11, 10]. They arise in problems in which direct comparisons of objects are made, e....
Elzbieta Pekalska, Robert P. W. Duin
TMM
2010
135views Management» more  TMM 2010»
13 years 4 months ago
Image Classification With Kernelized Spatial-Context
Abstract--The goal of image classification is to classify a collection of unlabeled images into a set of semantic classes. Many methods have been proposed to approach this goal by ...
Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Jinhui Tang,...