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.
Product Identifiers
Publisher
Lap Lambert Academic Publishing
ISBN-13
9783845409078
eBay Product ID (ePID)
190468453
Product Key Features
Author
Nicolas Loeff
Publication Name
A New Framework for Semisupervised and Multitask Learning
Format
Paperback
Language
English
Subject
Engineering & Technology
Publication Year
2011
Type
Textbook
Number of Pages
92 Pages
Dimensions
Item Height
229mm
Item Width
152mm
Item Weight
145g
Additional Product Features
Title_Author
Nicolas Loeff
Country/Region of Manufacture
Germany
Best Selling in Adult Learning & University
Current slide {CURRENT_SLIDE} of {TOTAL_SLIDES}- Best Selling in Adult Learning & University