{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:04:28Z","timestamp":1781780668021,"version":"3.54.5"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004055","name":"King Fahd University of Petroleum and Minerals","doi-asserted-by":"publisher","award":["EC241013"],"award-info":[{"award-number":["EC241013"]}],"id":[{"id":"10.13039\/501100004055","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113568","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:18:46Z","timestamp":1774397926000},"page":"113568","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["KRCapVLM: Beam-guided knowledge replay for knowledge-rich image captioning using vision-language model"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3439-1162","authenticated-orcid":false,"given":"Reem","family":"Aljunaid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0237-3025","authenticated-orcid":false,"given":"Qasim","family":"Umer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5786-5118","authenticated-orcid":false,"given":"Sajjad","family":"Mahmood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7318-7644","authenticated-orcid":false,"given":"Mahmood","family":"Niazi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3693-4596","authenticated-orcid":false,"given":"Muzammil","family":"Behzad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113568_bib0001","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10578","article-title":"Meshed-memory transformer for image captioning","author":"Cornia","year":"2020"},{"key":"10.1016\/j.patcog.2026.113568_bib0002","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"2927","article-title":"Visually-aware context modeling for news image captioning","author":"Qu","year":"2024"},{"issue":"1","key":"10.1016\/j.patcog.2026.113568_bib0003","doi-asserted-by":"crossref","first-page":"284","DOI":"10.54097\/m3m0hv16","article-title":"Image captioning in news report scenario","volume":"10","author":"Liu","year":"2024","journal-title":"Acad. J. Sci. Technol."},{"key":"10.1016\/j.patcog.2026.113568_bib0004","doi-asserted-by":"crossref","unstructured":"H. Ahsan, D. Bhatt, K. Shah, N. Bhalla, Multi-Modal image captioning for the visually impaired (2021) 53\u201360. https:\/\/aclanthology.org\/2021.naacl-srw.8\/. 10.18653\/v1\/2021.naacl-srw.8.","DOI":"10.18653\/v1\/2021.naacl-srw.8"},{"issue":"3","key":"10.1016\/j.patcog.2026.113568_bib0005","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.11591\/ijai.v12.i3.pp1104-1117","article-title":"Image captioning to aid blind and visually impaired outdoor navigation","volume":"12","author":"Faurina","year":"2023","journal-title":"IAES Int. J. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113568_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13733","article-title":"Evcap: retrieval-augmented image captioning with external visual-name memory for open-world comprehension","author":"Li","year":"2024"},{"issue":"3","key":"10.1016\/j.patcog.2026.113568_bib0007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3572777","article-title":"Towards retrieval-Augmented architectures for image captioning","volume":"19","author":"Chen","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.patcog.2026.113568_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118669","article-title":"Image captioning for effective use of language models in knowledge-based visual question answering","volume":"212","author":"Salaberria","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113568_bib0009","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"1562","article-title":"Enhancing visual question answering through question-driven image captions as prompts","author":"\u00d6zdemir","year":"2024"},{"key":"10.1016\/j.patcog.2026.113568_bib0010","series-title":"Proceedings of the 28th International Conference on Computational Linguistics (COLING)","first-page":"3143","article-title":"Geo-aware image caption generation","author":"Nikiforova","year":"2020"},{"key":"10.1016\/j.patcog.2026.113568_bib0011","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","first-page":"3992","article-title":"Incorporating background knowledge into video description generation","author":"Whitehead","year":"2018"},{"key":"10.1016\/j.patcog.2026.113568_bib0012","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11336","article-title":"Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training","volume":"34","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113568_bib0013","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113568_bib0014","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume":"162","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113568_bib0015","series-title":"International Conference on Machine Learning","first-page":"23318","article-title":"OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume":"162","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113568_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5579","article-title":"VinVL: revisiting visual representations in vision-language models","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113568_bib0017","first-page":"123","article-title":"Knowledge Hallucination in visual-language pretraining","volume":"58","author":"Cheng","year":"2023","journal-title":"J. AI Res."},{"key":"10.1016\/j.patcog.2026.113568_bib0018","first-page":"200","article-title":"Object-level visual-language pretraining: a unified approach","volume":"111","author":"Dai","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113568_bib0019","first-page":"50","article-title":"Mitigating generic bias in fine-tuning VLP models","volume":"36","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113568_bib0020","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"5038","article-title":"Beyond Generic: enhancing image captioning with real-world knowledge using vision-language pre-training model","author":"Cheng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113568_bib0021","article-title":"A survey on image captioning: models, datasets, and evaluation metrics","volume":"193","author":"Yang","year":"2020","journal-title":"Comput. Vision Image Understand."},{"issue":"3","key":"10.1016\/j.patcog.2026.113568_bib0022","article-title":"A survey on enhancing image captioning with advanced strategies and techniques","volume":"142","author":"Zhang","year":"2023","journal-title":"Comput. Math. Eng. Sci."},{"key":"10.1016\/j.patcog.2026.113568_bib0023","first-page":"14311","article-title":"Image captioning: a survey of models, evaluation metrics, and challenges","volume":"9","author":"Li","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113568_bib0024","first-page":"2703","article-title":"A survey on image captioning: datasets, models, evaluation metrics, and challenges","volume":"24","author":"Chao","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113568_bib0025","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3156","article-title":"Show and tell: a neural image caption generator","author":"Vinyals","year":"2015"},{"key":"10.1016\/j.patcog.2026.113568_bib0026","series-title":"International Conference on Machine Learning","first-page":"2048","article-title":"Show, attend and tell: neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"10.1016\/j.patcog.2026.113568_bib0027","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018"},{"key":"10.1016\/j.patcog.2026.113568_bib0028","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4634","article-title":"Attention on attention for image captioning","author":"Huang","year":"2019"},{"issue":"11","key":"10.1016\/j.patcog.2026.113568_bib0029","doi-asserted-by":"crossref","first-page":"2942","DOI":"10.1109\/TMM.2019.2915033","article-title":"Deep hierarchical encoder\u2013decoder network for image captioning","volume":"21","author":"Xiao","year":"2019","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113568_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2025.105155","article-title":"ARAFNet: An attribute refinement attention fusion network for advanced visual captioning","volume":"162","author":"Hossen","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.patcog.2026.113568_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109134","article-title":"Attribute-driven filtering: a new attributes predicting approach for fine-grained image captioning","volume":"137","author":"Hossen","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113568_bib0032","series-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","first-page":"2407","article-title":"Guiding the long-short term memory model for image caption generation","author":"Jia","year":"2015"},{"key":"10.1016\/j.patcog.2026.113568_bib0033","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.patcog.2026.113568_bib0034","series-title":"Proceedings of the 25th ACM International Conference on Multimedia","first-page":"46","article-title":"Structcap: structured semantic embedding for image captioning","author":"Chen","year":"2017"},{"key":"10.1016\/j.patcog.2026.113568_bib0035","series-title":"Groupcap: group-based image captioning with structured relevance and diversity constraints","author":"Chen","year":"2017"},{"key":"10.1016\/j.patcog.2026.113568_bib0036","unstructured":"R. Mokady, A. Hertz, A.H. Bermano, ClipCap: CLIP prefix for image captioning, arXiv preprint arXiv: 2111.09734(2021)."},{"key":"10.1016\/j.patcog.2026.113568_bib0037","series-title":"European Conference on Computer Vision","first-page":"121","article-title":"Oscar: object-semantics aligned pre-training for vision-language tasks","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113568_bib0038","unstructured":"J. Wang, Z. Yang, X. Hu, L. Li, K. Lin, Z. Gan, Z. Liu, C. Liu, L. Wang, GIT: A generative image-to-text transformer for vision and language, arXiv preprint arXiv: 2205.14100(2022)."},{"key":"10.1016\/j.patcog.2026.113568_bib0039","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","first-page":"4013","article-title":"Entity-aware image caption generation","author":"Lu","year":"2018"},{"key":"10.1016\/j.patcog.2026.113568_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12466","article-title":"Good news, everyone! context driven entity-aware captioning for news images","author":"Biten","year":"2019"},{"key":"10.1016\/j.patcog.2026.113568_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13035","article-title":"Transform and tell: entity-aware news image captioning","author":"Tran","year":"2020"},{"key":"10.1016\/j.patcog.2026.113568_bib0042","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"49","article-title":"Rich image captioning in the wild","author":"Tran","year":"2016"},{"key":"10.1016\/j.patcog.2026.113568_bib0043","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"6485","article-title":"Informative image captioning with external sources of information","author":"Zhao","year":"2019"},{"key":"10.1016\/j.patcog.2026.113568_bib0044","unstructured":"OFA-Sys, OFA-Large Model, 2022, (https:\/\/huggingface.co\/OFA-Sys\/ofa-large). Accessed 19 May 2025."},{"key":"10.1016\/j.patcog.2026.113568_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3558","article-title":"Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts","author":"Changpinyo","year":"2021"},{"issue":"1","key":"10.1016\/j.patcog.2026.113568_bib0046","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.patcog.2026.113568_bib0047","unstructured":"X. Chen, H. Fang, T.-Y. Lin, R. Vedantam, S. Gupta, P. Doll\u00e1r, C.L. Zitnick, Microsoft COCO captions: data collection and evaluation server, abs\/1504.00325(2015). https:\/\/api.semanticscholar.org\/CorpusID:2210455."},{"key":"10.1016\/j.patcog.2026.113568_bib0048","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL)","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.patcog.2026.113568_bib0049","series-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and\/or Summarization","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.patcog.2026.113568_bib0050","series-title":"Text Summarization Branches Out: Proceedings of the ACL-04 Workshop","first-page":"74","article-title":"ROUGE: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.patcog.2026.113568_bib0051","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4566","article-title":"Cider: consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"issue":"13","key":"10.1016\/j.patcog.2026.113568_bib0052","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.patcog.2026.113568_bib0053","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"7870","article-title":"Recall and learn: fine-tuning deep pretrained language models with less forgetting","author":"Chen","year":"2020"},{"key":"10.1016\/j.patcog.2026.113568_bib0054","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"9514","article-title":"Raise a child in large language model: towards effective and generalizable fine-tuning","author":"Xu","year":"2021"},{"issue":"2","key":"10.1016\/j.patcog.2026.113568_bib0055","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"CLIP-Adapter: vetter vision-Language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"Int. J. Comput. Vis."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005340?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005340?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:10:46Z","timestamp":1780492246000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326005340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"alternative-id":["S0031320326005340"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113568","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"KRCapVLM: Beam-guided knowledge replay for knowledge-rich image captioning using vision-language model","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113568","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113568"}}