Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Image label completion by pursuing contextual decomposability

Image label completion by pursuing contextual decomposability Image Label Completion by Pursuing Contextual Decomposability XIAOBAI LIU, SCTS & CGCL Huazhong University of Science and Technology SHUICHENG YAN and TAT-SENG CHUA, National University of Singapore HAI JIN, SCTS & CGCL Huazhong University of Science and Technology This article investigates how to automatically complete the missing labels for the partially annotated images, without image segmentation. The label completion procedure is formulated as a nonnegative data factorization problem, to decompose the global image representations that are used for describing the entire images, for instance, various image feature descriptors, into their corresponding label representations, that are used for describing the local semantic regions within images. The solution provided in this work is motivated by following observations. First, label representations of the regions with the same label often share certain commonness, yet may be essentially different due to the large intraclass variations. Thus, each label or concept should be represented by using a subspace spanned by an ensemble of basis, instead of a single one, to characterize the intralabel diversities. Second, the subspaces for different labels are different from each other. Third, while two images are similar with each other, the corresponding label representations should be similar. We formulate this http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) Association for Computing Machinery

Image label completion by pursuing contextual decomposability

Download PDF
20 pages

Loading next page...
 
/lp/association-for-computing-machinery/image-label-completion-by-pursuing-contextual-decomposability-zfhaAK4fxk
Publisher
Association for Computing Machinery
Copyright
Copyright © 2012 by ACM Inc.
ISSN
1551-6857
DOI
10.1145/2168996.2169001
Publisher site
See Article on Publisher Site

Abstract

Image Label Completion by Pursuing Contextual Decomposability XIAOBAI LIU, SCTS & CGCL Huazhong University of Science and Technology SHUICHENG YAN and TAT-SENG CHUA, National University of Singapore HAI JIN, SCTS & CGCL Huazhong University of Science and Technology This article investigates how to automatically complete the missing labels for the partially annotated images, without image segmentation. The label completion procedure is formulated as a nonnegative data factorization problem, to decompose the global image representations that are used for describing the entire images, for instance, various image feature descriptors, into their corresponding label representations, that are used for describing the local semantic regions within images. The solution provided in this work is motivated by following observations. First, label representations of the regions with the same label often share certain commonness, yet may be essentially different due to the large intraclass variations. Thus, each label or concept should be represented by using a subspace spanned by an ensemble of basis, instead of a single one, to characterize the intralabel diversities. Second, the subspaces for different labels are different from each other. Third, while two images are similar with each other, the corresponding label representations should be similar. We formulate this

Journal

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) – Association for Computing Machinery

Published: May 1, 2012

There are no references for this article.