A New Framework for Semisupervised and Multitask Learning: with applications to image annotation

Loeff, Nicolas

ISBN 10: 384540907X / ISBN 13: 9783845409078

Published by LAP LAMBERT Academic Publishing, 2011

About this Item

LIKE NEW. SHIPS FROM MULTIPLE LOCATIONS.

Seller Inventory # ERICA758384540907X6

Bibliographic Details

• Title: A New Framework for Semisupervised and Multitask Learning: with applications to image annotation
• Publisher: LAP LAMBERT Academic Publishing
• Publication Date: 2011
• Language: English
• ISBN 10: 384540907X
• ISBN 13: 9783845409078
• Binding: Paperback
• Condition: Like New
• Book Type: book

About this title

Synopsis

Labeling image collections is a tedious and time consuming task, especially when multiple labels have to be chosen for each image. On the other hand, the explosion of Internet content has provided cheap access to almost unlimited amounts of data, albeit with a lower quality of annotations. This dissertation deals with the problem of automatically annotating images, by introducing a new framework that extends state-of-the-art models in word prediction to incorporate information from two sources, unlabeled examples and correlated labels. This is the first semisupervised multitask model used in vision problems of these characteristics.

About the Author

Nicolas Loeff received a Ph.D. in electrical and computer engineering from the University of Illinois at Urbana-Champaign. His research interests include machine learning, computer vision and computational finance.