{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:12:20Z","timestamp":1787163140543,"version":"3.56.0"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019904","name":"Vellore Institute of Technology, Chennai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019904","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3431091","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T13:40:05Z","timestamp":1721396405000},"page":"100991-101003","source":"Crossref","is-referenced-by-count":15,"title":["Enhanced Image Captioning Using Bahdanau Attention Mechanism and Heuristic Beam Search Algorithm"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7957-7934","authenticated-orcid":false,"given":"S.","family":"Abinaya","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mandava","family":"Deepak","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-9940","authenticated-orcid":false,"given":"A.","family":"Sherly Alphonse","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028651"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp48618.2020.00-12"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00486-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00693-9"},{"key":"ref6","first-page":"1","article-title":"Caption generation based on emotions using CSPDenseNet and BiLSTM with self-attention","volume":"2022","author":"Priya","year":"2022","journal-title":"Appl. Comput. Intell. Soft Comput."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13443-5"},{"key":"ref9","first-page":"305","article-title":"Empirical study of image captioning models using various deep learning encoders","volume-title":"Proc. Int. Conf. Mach. Intell. Signal Process.","author":"Mathur"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-31223-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3249462"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDT57929.2023.10151421"},{"key":"ref13","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"arXiv:2202.03052"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRITO48877.2020.9197977"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ELECO47770.2019.8990630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC51019.2021.9418234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref20","article-title":"Show and tell: A neural image caption generator","author":"Vinyals","year":"2014","journal-title":"arXiv:1411.4555"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3312718"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103948"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.37391\/ijeer.100207"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12040836"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10604872.pdf?arnumber=10604872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T13:43:40Z","timestamp":1721915020000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10604872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3431091","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}