The Open UniversitySkip to content
 

Contextual image annotation via projection and quantum theory inspired measurement for integration of text and visual features

Kaliciak, Leszek; Wang, Lei; Song, Dawei; Zhang, Peng and Hou, Yuexian (2011). Contextual image annotation via projection and quantum theory inspired measurement for integration of text and visual features. In: 5th International Symposium on Quantum Interactions (QI2011), 26-29 June 2011, Aberdeen, UK.

Full text available as:
Full text not publicly available
Due to copyright restrictions, this file is not available for public download
Click here to request a copy from the OU Author.
URL: http://cs.tju.edu.cn/faculty/dsong/papers/fulltext...
Google Scholar: Look up in Google Scholar

Abstract

Multimedia information retrieval suffers from the semantic gap, a difference between human perception and machine representation of images. In order to reduce the gap, a quantum theory inspired theoretical framework for integration of text and visual features has been proposed. This article is a followup work on this model. Previously, two relatively straight forward statistical approaches for making associations between dimensions of both feature spaces were employed, but with unsatisfactory results. In this paper, we propose to alleviate the problem regarding unannotated images by projecting them onto subspaces representing visual context and by incorporating a quantum-like measurement. The proposed principled approach extends the traditional vector space model (VSM) and seamlessly integrates with the tensor-based framework. Here,we experimentally test the novel association methods in a small-scale experiment.

Item Type: Conference Item
Copyright Holders: 2011 Springer-Verlag
ISSN: 0302-9743
Extra Information: Quantum Interaction
5th International Symposium, QI 2011, Aberdeen, UK, June 26-29, 2011, Revised Selected Papers
Editors:Dawei Song, Massimo Melucci, Ingo Frommholz, Peng Zhang, Lei Wang, Sachi Arafat
Lecture Notes in Computer Science, Volume 7052 2011
ISBN: 978-3-642-24970-9 (Print)
ISBN: 978-3-642-24971-6 (Online)
pp.217-222
Keywords: multimedia retrieval; quantum theory; image annotation; tensor product
Academic Unit/Department: Mathematics, Computing and Technology
Mathematics, Computing and Technology > Computing & Communications
Related URLs:
Item ID: 34940
Depositing User: Mary Mcmahon
Date Deposited: 26 Oct 2012 09:17
Last Modified: 26 Oct 2012 21:06
URI: http://oro.open.ac.uk/id/eprint/34940
Share this page:

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk