Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/151327
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Dongzheen_US
dc.contributor.authorMao, Kezhien_US
dc.date.accessioned2021-06-22T05:07:58Z-
dc.date.available2021-06-22T05:07:58Z-
dc.date.issued2019-
dc.identifier.citationWang, D. & Mao, K. (2019). Task-generic semantic convolutional neural network for web text-aided image classification. Neurocomputing, 329, 103-115. https://dx.doi.org/10.1016/j.neucom.2018.09.042en_US
dc.identifier.issn0925-2312en_US
dc.identifier.other0000-0002-1467-6023-
dc.identifier.urihttps://hdl.handle.net/10356/151327-
dc.description.abstractIn this work, we explore how to use external and auxiliary web text to improve image classification. The keystone of web text-aided image classification is the representation learning for these two modalities of data. In the recent decade, convolutional neural networks (CNN) as the core representation methods of images have become a commodity in computer vision community. On the other hand, the long reign of word vectors has the same wide-ranging impact on NLP for representation learning. Based on the pre-trained word vectors, we propose a novel semantic CNN (s-CNN) model for high-level text representation learning using task-generic semantic filters. However, the s-CNN model inevitably brings about surplus semantic filters to achieve better applicability and generalization in universal tasks. Moreover, the surplus filters may lead to semantic overlaps and feature redundancy issue. To address this issue, we develop the so-called s-CNN Clustered (s-CNNC) models that uses filter clusters instead of individual filters. Interacting with the image CNN models, the s-CNNC models can further boost image classification under a multi-modal framework (mm-CNN). In addition, we propose to use the external text information selectively in the mm-CNN network to alleviate the noise problem inherent in web text. We validate the effectiveness of the proposed models on six benchmark datasets, and the results show that our approaches achieve remarkable improvements.en_US
dc.language.isoenen_US
dc.relation.ispartofNeurocomputingen_US
dc.rights© 2018 Elsevier B.V. All rights reserved.en_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleTask-generic semantic convolutional neural network for web text-aided image classificationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.identifier.doi10.1016/j.neucom.2018.09.042-
dc.identifier.scopus2-s2.0-85055729191-
dc.identifier.volume329en_US
dc.identifier.spage103en_US
dc.identifier.epage115en_US
dc.subject.keywordsSemantic Convolutional Neural Networken_US
dc.subject.keywordsImage Recognitionen_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:EEE Journal Articles

Page view(s)

56
Updated on Nov 28, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.