Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/24486
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXia, R-
dc.contributor.authorLi, G-
dc.contributor.authorHuang, Z-
dc.contributor.authorMeng, H-
dc.contributor.authorPang, Y-
dc.date.accessioned2022-04-24T17:35:08Z-
dc.date.available2022-04-24T17:35:08Z-
dc.date.issued2022-04-18-
dc.identifierORCiD:: Ruiyang Xia https://orcid.org/0000-0002-2421-9512-
dc.identifierORCiD: Guoquan Li https://orcid.org/0000-0001-8022-743X-
dc.identifierORCiD: Zhengwen Huang https://orcid.org/0000-0003-2426-242X-
dc.identifierORCiD: Hongying Meng https://orcid.org/0000-0002-8836-1382-
dc.identifierORCiD: Yu Pang https://orcid.org/0000-0002-7507-5387-
dc.identifier.citationXia, R. et al. (2022) 'CBASH: Combined Backbone and Advanced Selection Heads with Object Semantic Proposals for Weakly Supervised Object Detection', IEEE Transactions on Circuits and Systems for Video Technology, 32 (10), pp. 6502 - 6514. doi: 10.1109/tcsvt.2022.3168547.en_US
dc.identifier.issn1051-8215-
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/24486-
dc.description.abstractMost recent object detection methods have achieved growing performance on public datasets. However, enormous efforts are needed for these methods due to the extensive annotations of ground-truth boxes. Weakly Supervised Object Detection (WSOD) methods hence have been proposed to solve this problem as only image-level annotations are required and then output bounding boxes related to the objects. In order to further elevate the weakly supervised detection methods on the extraction of reasonable features, the training of potential positive proposals, and the generation of proposals before training, we propose a new Combined Backbone and Advanced Selection Heads (CBASH) method with the proposals generated from the object semantic information. Specifically, Combined Backbone will make the unobvious object features more noticeable, Advanced Selection Heads promote more potential positive proposals to get training, and the generated object semantic proposals elevate the quality and quantity of positive proposals. The proposed method is evaluated on the challenging PASCAL VOC 2007 and 2012 benchmark datasets. Experimental results show that our proposed method can achieve improved performance on both VOC 2007 and VOC 2012 datasets and outperforms the existing state-of-the-art methods.-
dc.description.sponsorship10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 61971079 and U21A20447); Basic Research and Frontier Exploration Project of Chongqing (Grant Number: cstc2019jcyj- msxmX0666); National Key Research and Development Program of China (Grant Number: 2019YFC1511300); Regional Creative Cooperation Program of Sichuan (Grant Number: 2020YFQ0025); Innovative Group Project of the National Natural Science Foundation of Chongqing (Grant Number: cstc2020jcyj-cxttX0002).en_US
dc.format.extent6502 - 6514-
dc.language.isoen_USen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rightsCopyright © 2022 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/-
dc.rights.urihttps://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/-
dc.subjectweakly supervised object detectionen_US
dc.subjectimage-level annotationsen_US
dc.subjectcombined backboneen_US
dc.subjectadvanced selection headsen_US
dc.subjectobject semantic proposalsen_US
dc.titleCBASH: Combined Backbone and Advanced Selection Heads with Object Semantic Proposals for Weakly Supervised Object Detectionen_US
dc.typeArticleen_US
dc.date.dateAccepted2022-04-02-
dc.identifier.doihttps://doi.org/10.1109/tcsvt.2022.3168547-
dc.relation.isPartOfIEEE Transactions on Circuits and Systems for Video Technology-
pubs.issue10-
pubs.publication-statusPublished-
pubs.volume32-
dc.identifier.eissn1558-2205-
dc.rights.holderInstitute of Electrical and Electronics Engineers (IEEE)-
Appears in Collections:Dept of Electronic and Electrical Engineering Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2022 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/21.23 MBAdobe PDFView/Open


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