{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:40:22Z","timestamp":1773992422997,"version":"3.50.1"},"reference-count":54,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3068897","type":"journal-article","created":{"date-parts":[[2021,3,24]],"date-time":"2021-03-24T19:45:17Z","timestamp":1616615117000},"page":"50253-50264","source":"Crossref","is-referenced-by-count":60,"title":["Automatic Image Annotation Based on Deep Learning Models: A Systematic Review and Future Challenges"],"prefix":"10.1109","volume":"9","author":[{"given":"Myasar Mundher","family":"Adnan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohd Shafry Mohd","family":"Rahim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3817-2655","authenticated-orcid":false,"given":"Amjad","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4888-2594","authenticated-orcid":false,"given":"Zahid","family":"Mehmood","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3138-3801","authenticated-orcid":false,"given":"Tanzila","family":"Saba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7473-8441","authenticated-orcid":false,"given":"Rizwan Ali","family":"Naqvi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.477"},{"key":"ref33","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/AISP.2017.8324073"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0238956"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5220\/0005216700920099"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09887-2"},{"key":"ref36","article-title":"Fuzzy logic controller for classroom air conditioner","volume":"1484","author":"waheed","year":"2020","journal-title":"J Phys Conf Ser"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2621185"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.14704\/nq.2018.16.6.1612"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2016.7752750"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2016.7761105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.019"},{"key":"ref1","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.03.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"ref23","first-page":"4133","article-title":"Image caption with global-local attention","author":"li","year":"2017","journal-title":"Proc 31sst AAAI Conf Artif Intell (AAAI)"},{"key":"ref26","first-page":"13","article-title":"The iapr TC-12 benchmark: A new evaluation resource for visual information systems","author":"grubinger","year":"2016","journal-title":"Proc LREC Workshop Image Lang Resour"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985733"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15676\/ijeei.2015.7.2.10"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15676\/ijeei.2014.6.1.3"},{"key":"ref54","first-page":"203","article-title":"A survey and analysis on image annotation","author":"adnan","year":"2020","journal-title":"Proc 3rd Int Conf Eng Technol Appl (IICETA)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.09.017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.02.017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4788-5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2960466"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF02478259"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref13","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336896"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2015.7359871"},{"key":"ref18","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IICETA50496.2020.9318815"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6038-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2012.05.003"},{"key":"ref6","first-page":"97","article-title":"Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary","author":"duygulu","year":"2002","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.07.004"},{"key":"ref8","article-title":"On the origin of deep learning","author":"wang","year":"2017","journal-title":"arXiv 1702 07800"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.443"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s13319-014-0024-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref45","first-page":"2924","article-title":"Automatic video description generation via LSTM with joint two-stream encoding","author":"zhang","year":"2016","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15676\/ijeei.2017.9.1.8"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"7627","DOI":"10.36478\/jeasci.2019.7627.7635","article-title":"A survey automatic image annotation based on machine learning models","volume":"14","author":"adnan","year":"2019","journal-title":"J Eng Appl Sci"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MVA.2015.7153244"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref44","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.10.006"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09386110.pdf?arnumber=9386110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T12:29:43Z","timestamp":1643286583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9386110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3068897","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}