{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T23:35:17Z","timestamp":1784158517513,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1109\/access.2025.3642465","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:33:44Z","timestamp":1765391624000},"page":"211352-211369","source":"Crossref","is-referenced-by-count":1,"title":["Knowledge-Driven Image Captioning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0188-2653","authenticated-orcid":false,"given":"Anwar Ul","family":"Haque","sequence":"first","affiliation":[{"name":"SMCS, Institute of Business Administration (IBA), Karachi, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-2789","authenticated-orcid":false,"given":"Sayeed","family":"Ghani","sequence":"additional","affiliation":[{"name":"SMCS, Institute of Business Administration (IBA), Karachi, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6818-7858","authenticated-orcid":false,"given":"Muhammad","family":"Saeed","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Karachi, Karachi, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2019.09.014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-020-03579-2"},{"key":"ref3","article-title":"Dynamic routing between capsules","author":"Sabour","year":"2017","journal-title":"arXiv:1710.09829"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.54254\/2755-2721\/2025.AST24685"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112205"},{"key":"ref6","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arxiv.2205.14100"},{"key":"ref7","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"arXiv:1908.02265"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581807.3581879"},{"key":"ref9","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"arXiv:2201.12086"},{"key":"ref10","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref11","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"arXiv:1711.00937"},{"key":"ref12","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref13","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref14","article-title":"ResT v2: Simpler, faster and stronger","author":"Zhang","year":"2022","journal-title":"arXiv:2204.07366"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/e26100876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2023.0140912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117273"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-024-11527-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2025.04.458"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2021.102069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01073-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98355-0_9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icicml63543.2024.10957937"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icip51287.2024.10647426"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3336371"},{"issue":"4","key":"ref26","first-page":"58","article-title":"A review paper on understanding capsule networks","volume":"6","author":"Shah","year":"2018","journal-title":"Int. J. Eng. Dev. Res."},{"key":"ref27","first-page":"3859","article-title":"Dynamic routing between capsules","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Sabour"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3131343"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e26177"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3447772"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-017-0055-z"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3330430.3333636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/itnec.2017.8284938"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/dmo.2011.5976510"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/skg.2015.55"},{"key":"ref37","first-page":"1","article-title":"Extractive text summarization using sentence ranking","volume-title":"Proc. Int. Conf. Data Sci. Commun. (IconDSC)","author":"Madhuri"},{"key":"ref38","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013","journal-title":"arXiv:1310.4546"},{"key":"ref39","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref40","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref41","article-title":"Meshed-memory transformer for image captioning","author":"Cornia","year":"2019","journal-title":"arXiv:1912.08226"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11296791.pdf?arnumber=11296791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:00:22Z","timestamp":1766127622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11296791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3642465","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}