{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:08:21Z","timestamp":1774717701528,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3268744","type":"journal-article","created":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T18:23:30Z","timestamp":1682101410000},"page":"40230-40239","source":"Crossref","is-referenced-by-count":20,"title":["Semantic Representations With Attention Networks for Boosting Image Captioning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6514-6426","authenticated-orcid":false,"given":"Deema Abdal","family":"Hafeth","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Lincoln, Lincoln, U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2879-9286","authenticated-orcid":false,"given":"Stefanos","family":"Kollias","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mubeen","family":"Ghafoor","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Lincoln, Lincoln, U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Aligning visual regions and textual concepts for semantic-grounded image representations","volume":"32","author":"liu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref14","first-page":"1","article-title":"Image captioning: Transforming objects into words","volume":"32","author":"herdade","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350943"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref11","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01513"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00036"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154149"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12776-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","first-page":"1","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume":"24","author":"ordonez","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"790","article-title":"Generalizing image captions for image-text parallel corpus","volume":"2","author":"kuznetsova","year":"2013","journal-title":"Proc ACL"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app8050739"},{"key":"ref45","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00856"},{"key":"ref25","first-page":"1","article-title":"Adaptively aligned image captioning via adaptive attention time","volume":"32","author":"huang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","first-page":"249","article-title":"Re-evaluating the role of BLEU in machine translation research","author":"callison-burch","year":"2006","journal-title":"Proc 11th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref20","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":"ref42","first-page":"1","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref44","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref43","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref27","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app9163260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00693-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1803"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPHYS.2019.8780171"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10106753.pdf?arnumber=10106753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T18:44:05Z","timestamp":1684176245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10106753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3268744","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}