{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T14:03:03Z","timestamp":1778335383936,"version":"3.51.4"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100016929","name":"Yayasan UTP Prestigious Scholarship (YUTP) under Universiti Teknologi PETRONAS (UTP) with Cost Center","doi-asserted-by":"publisher","award":["015LC0-281"],"award-info":[{"award-number":["015LC0-281"]}],"id":[{"id":"10.13039\/100016929","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3132453","type":"journal-article","created":{"date-parts":[[2021,12,3]],"date-time":"2021-12-03T20:27:37Z","timestamp":1638563257000},"page":"161959-161977","source":"Crossref","is-referenced-by-count":24,"title":["A Reinforcement Learning Based Adaptive ROI Generation for Video Object Segmentation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0341-8288","authenticated-orcid":false,"given":"Usman Ahmad","family":"Usmani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzo","family":"Watada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8850-6203","authenticated-orcid":false,"given":"Jafreezal","family":"Jaafar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2654-4463","authenticated-orcid":false,"given":"Izzatdin Abdul","family":"Aziz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3523-1960","authenticated-orcid":false,"given":"Arunava","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2019.8806244"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100892"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.23919\/TST.2017.8195348"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.185"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2654543"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref75","first-page":"1680","article-title":"Lucid data dreaming for object tracking","volume":"1","author":"khoreva","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis (ICCV)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-019-00845-9"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103032"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.638"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299035"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00898"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00342"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref61","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.148"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref64","first-page":"1","article-title":"Learning structured representation for text classification via reinforcement learning","author":"zhang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.87"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-019-0027-x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_46"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_23"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818105"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.21"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-020-01785-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11052-2"},{"key":"ref24","first-page":"1202","article-title":"Evaluation of super-voxel methods for early video processing","author":"xu","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67832-6_37"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.267"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00312"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref94","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","author":"baldi","year":"2012","journal-title":"Proc ICML Workshop Unsupervised Transf Learn"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2845918"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3026658"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref54","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2905607"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115626"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943365"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3076849"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09683-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09857-8"},{"key":"ref82","first-page":"565","article-title":"PReMVOS: Proposal-generation, refinement and merging for video object segmentation","author":"luiten","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref81","first-page":"433","article-title":"C-EFIC: Color and edge based foreground background segmentation with interior classification","author":"allebosch","year":"2015","journal-title":"Proc Int Joint Conf Comput Vis Imag Comput Graph"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0512-5"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107465"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.126"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25903-1_12"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.784"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126418"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_13"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.374"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1122-2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.336"},{"key":"ref48","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00626"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.369"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2819173"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09634037.pdf?arnumber=9634037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T21:46:11Z","timestamp":1647294371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9634037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3132453","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}