Please use this identifier to cite or link to this item: http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1312
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKokul, T.
dc.contributor.authorFookes, C.
dc.contributor.authorSridharan, S.
dc.contributor.authorRamanan, A.
dc.contributor.authorPinidiyaarachchi, A.
dc.date.accessioned2020-01-08T05:19:34Z
dc.date.accessioned2022-06-27T04:11:18Z-
dc.date.available2020-01-08T05:19:34Z
dc.date.available2022-06-27T04:11:18Z-
dc.date.issued2019-08-16
dc.identifier.issn1556-6021
dc.identifier.urihttp://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1312-
dc.description.abstractDeep similarity trackers are able to track above real-time speed. However, their accuracy is considerably lower than deep classification based trackers since they avoid valuable online cues. To feed the target-specific information for real-time object tracking, we propose a novel Siamese attention network. Different types of attention mechanisms are used to capture different contexts of target information and then learned knowledge is used to feed target cues at different representation levels of similarity tracking. In addition, an online learning mechanism is employed to utilise the available target-specific data. The proposed tracker reduces the impact of noise in the target template and improves the accuracy of similarity tracking by feeding target cues into the similarity search. Extensive evaluation performed on OTB-2013/50/100 and VOT2018 benchmark datasets demonstrate the proposed tracker outperforms state-of-the-art approaches while maintaining real-time tracking speed.en_US
dc.language.isoenen_US
dc.publisherIEEE Transactions on Information Forensics and Securityen_US
dc.subjectVisual object trackingen_US
dc.subjectDeep neural networksen_US
dc.subjectSiamese networken_US
dc.subjectAttention networken_US
dc.titleTarget-Specific Siamese Attention Network for Real-time Object Trackingen_US
dc.typeArticleen_US
Appears in Collections:Physical Science

Files in This Item:
File Description SizeFormat 
Target-Specific Siamese Attention Network for.pdf62.35 kBAdobe PDFThumbnail
View/Open


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