Show simple item record

dc.contributor.authorMandal, R
dc.contributor.authorBecken, S
dc.contributor.authorConnolly, RM
dc.contributor.authorStantic, B
dc.date.accessioned2021-05-13T23:02:30Z
dc.date.available2021-05-13T23:02:30Z
dc.date.issued2021
dc.identifier.isbn9789811616846
dc.identifier.issn1865-0929
dc.identifier.doi10.1007/978-981-16-1685-3_26
dc.identifier.urihttp://hdl.handle.net/10072/404292
dc.description.abstractPhoto aesthetics assessment is a challenging problem. Deep Convolutional Neural Network (CNN)-based algorithms have achieved promising results for aesthetics assessment in recent times. Lately, few efficient and effective attention-based CNN architectures are proposed that improve learning efficiency by adaptively adjusts the weight of each patch during the training process. In this paper, we investigate how real human attention affects instead of CNN-based synthetic attention network architecture in image aesthetic assessment. A dataset consists of a large number of images along with eye-tracking information has been developed using an eye-tracking device (https://www.tobii.com/group/about/this-is-eye-tracking/ ) power by sensor technology for our research, and it will be the first study of its kind in image aesthetic assessment. We adopted a Residual Attention Network and ResNet architectures which achieve state-of-the-art performance image recognition tasks on benchmark datasets. We report our findings on photo aesthetics assessment with two sets of datasets consist of original images and images with masked attention patches, which demonstrates higher accuracy when compared to the state-of-the-art methods.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherSpringer, Singapore
dc.publisher.placeGermany
dc.relation.ispartofconferencename2021 13th Asian Conference on Intelligent Information and Database Systems (ACIIDS)
dc.relation.ispartofconferencetitleCommunications in Computer and Information Science
dc.relation.ispartofdatefrom2021-04-07
dc.relation.ispartofdateto2021-04-10
dc.relation.ispartoflocationPhuket, Thailand
dc.relation.ispartofpagefrom310
dc.relation.ispartofpageto320
dc.relation.ispartofvolume1371
dc.subject.fieldofresearchBiological psychology
dc.subject.fieldofresearchCognitive and computational psychology
dc.subject.fieldofresearchcode5202
dc.subject.fieldofresearchcode5204
dc.titleResidual Attention Network vs Real Attention on Aesthetic Assessment
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationMandal, R; Becken, S; Connolly, RM; Stantic, B, Residual Attention Network vs Real Attention on Aesthetic Assessment, Recent Challenges in Intelligent Information and Database Systems, 2021, 1371 CCIS, pp. 310-320
dc.date.updated2021-05-11T00:32:40Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© Springer Nature Singapore Pte Ltd. 2021. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher.The original publication is available at www.springerlink.com
gro.hasfulltextFull Text
gro.griffith.authorConnolly, Rod M.
gro.griffith.authorMandal, Ranju
gro.griffith.authorStantic, Bela
gro.griffith.authorBecken, Susanne


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record