Please use this identifier to cite or link to this item:
Title: Learning"Verb-object" Concepts for semantic image annotation
Authors: Zhang, X.
Zha, Z.-J.
Xu, C.S. 
Keywords: "verb-object" concept
Semantic image annotation
Issue Date: 2011
Citation: Zhang, X.,Zha, Z.-J.,Xu, C.S. (2011). Learning"Verb-object" Concepts for semantic image annotation. MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops : 1077-1080. ScholarBank@NUS Repository.
Abstract: In real-world image understanding and retrieval applications, there exists a large number of images containing"verb-object" semantic. The most existing image annotation approaches which mainly focus on annotating images with "object" concepts may not well describe the image semantics. In this paper, we propose a novel image annotation approach by learning "verb-object" concepts. The "verb-object" concept learning method is developed based on the assumption that the classifiers of the "verb-object" concepts which contain the same object usually share a common structure. We formulate each "verb-object" concept classifier as a combination of a private part and a common part shared by all the "verb-object" concepts containing the same object. These classifiers are learned simultaneously through a joint optimization process. Experiments on a Web image data set containing 22,812 images with 28 concepts demonstrate that the proposed approach can achieve promising performance compared to the baseline method. Copyright 2011 ACM.
Source Title: MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops
ISBN: 9781450306164
DOI: 10.1145/2072298.2071942
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Nov 29, 2022

Page view(s)

checked on Nov 24, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.