Results 221 to 230 of about 9,001,538 (255)
Some of the next articles are maybe not open access.
A soft-labeled self-training approach
2016 23rd International Conference on Pattern Recognition (ICPR), 2016Semi-supervised classification methods try to improve a supervised learned classifier with the help of unlabeled data. In many cases one assumes a certain structure on the data, as for example the manifold assumption, the smoothness assumption or the cluster assumption.
Alexander Mey, Marco Loog
openaire +2 more sources
An Improved Self-Training for Face Recognition
2013 Seventh International Conference on Image and Graphics, 2013Face recognition has attracted considerable concerns in recent years. In practical applications, there are generally a small amount of labeled face images and a lot of unlabeled ones can be available. In this paper, we introduce a semi-supervised face recognition method where semi-supervised LDA (SDA) and Affinity Propagation (AP) are integrated into ...
Haitao Gan +4 more
openaire +1 more source
Yoga Posture Recognition for Self-training
2014Self-training plays an important role in sports exercise, but improper training postures can cause serious harm to muscles and ligaments of the body. Hence, more and more researchers are devoted into the development of computer-assisted self-training systems for sports exercise.
Hua-Tsung Chen +5 more
openaire +2 more sources
Self-training with adaptive regularization for S3VM
2017 International Joint Conference on Neural Networks (IJCNN), 2017The Semi-Supervised Support Vector Machine (S3VM) solves a non-convex, Mixed-Integer Program (MIP). Due to difficulty in solving the problem, convex approximations have typically been used. However, existing approaches suffer from poor scalability and struggle on certain datasets, compared to graph based counterparts.
Edward Cheung, Yuying Li 0001
openaire +1 more source
Self-training for Cell Segmentation and Counting
2019Learning semantic segmentation and object counting often need a large amount of training data while manual labeling is expensive. The goal of this paper is to train such networks on a small set of annotations. We propose an Expectation Maximization(EM)-like self-training method that first trains a model on a small amount of labeled data and adds ...
Junliang Luo +4 more
openaire +1 more source
An incremental self-trained ensemble algorithm
2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), 2018Incremental learning has boosted the speed of Data Mining algorithms without sacrificing much, or sometimes none, predictive accuracy. Instead, by saving computational resources, combination of such kind of algorithms with iterative procedures that improve the learned hypothesis utilizing vast amounts of available unlabeled data could be achieved ...
Stamatis Karlos +4 more
openaire +1 more source
2010
You have to make the five elementary pictures of the program and paste them in the book on the places reserved for that purpose. Take part in the play and you will be pleasantly surprised at the result.
openaire +1 more source
You have to make the five elementary pictures of the program and paste them in the book on the places reserved for that purpose. Take part in the play and you will be pleasantly surprised at the result.
openaire +1 more source
A Lazy Learning Approach for Self-training
2013This research is partially funded by the Spanish MICINN projects COGNITIO (TIN-2012-38450-C03-03) and EdeTRI (TIN2012-39348-C02-01), and the grant 2009-SGR-1434 from the Generalitat de Catalunya.
openaire +3 more sources
International Journal of Educational Technology in Higher Education, 2021
Cristina Valls-Bautista +2 more
exaly
Cristina Valls-Bautista +2 more
exaly

