{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:09:04Z","timestamp":1790323744753,"version":"4.1.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133362","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:48:28Z","timestamp":1781884108000},"page":"133362","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Context-guided deep interaction networks for image captioning"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2711-8198","authenticated-orcid":false,"given":"Fuyun","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6594-3271","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0503-6208","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133362_bib0001","series-title":"Proceedings of the 14th european conference on computer vision","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"Anderson","year":"2016"},{"key":"10.1016\/j.eswa.2026.133362_bib0002","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.eswa.2026.133362_bib0003","series-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation 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"},{"issue":"5","key":"10.1016\/j.eswa.2026.133362_bib0004","doi-asserted-by":"crossref","first-page":"4019","DOI":"10.1007\/s10462-022-10270-w","article-title":"Automatic captioning for medical imaging (MIC): A rapid review of literature","volume":"56","author":"Beddiar","year":"2023","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.133362_bib0005","series-title":"Proceedings of the 28th pacific-asia conference on knowledge discovery and data mining","first-page":"15","article-title":"Geometrically-aware dual transformer encoding visual and textual features for image captioning","author":"Chang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133362_bib0006","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"5659","article-title":"SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning","author":"Chen","year":"2017"},{"key":"10.1016\/j.eswa.2026.133362_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109948","article-title":"ENVQA: Improving visual question answering model by enriching the visual feature","volume":"142","author":"Chowdhury","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0008","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.eswa.2026.133362_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112135","article-title":"Key region semantic information augmented transformer for image captioning","volume":"161","author":"Deng","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18009","article-title":"Injecting semantic concepts into end-to-end image captioning","author":"Fang","year":"2022"},{"issue":"3","key":"10.1016\/j.eswa.2026.133362_bib0011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3617592","article-title":"Deep learning approaches on image captioning: A review","volume":"56","author":"Ghandi","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.eswa.2026.133362_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10327","article-title":"Normalized and geometry-aware self-attention network for image captioning","author":"Guo","year":"2020"},{"key":"10.1016\/j.eswa.2026.133362_bib0013","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume":"32","author":"Herdade","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133362_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106384","article-title":"Dual-spatial normalized transformer for image captioning","volume":"123","author":"Hu","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0015","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"},{"key":"10.1016\/j.eswa.2026.133362_bib0016","first-page":"8942","article-title":"Adaptively aligned image captioning via adaptive attention time","volume":"32","author":"Huang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133362_bib0017","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"Karpathy","year":"2015"},{"key":"10.1016\/j.eswa.2026.133362_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17969","article-title":"Beyond a pre-trained object detector: Cross-modal textual and visual context for image captioning","author":"Kuo","year":"2022"},{"key":"10.1016\/j.eswa.2026.133362_bib0019","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"8928","article-title":"Entangled transformer for image captioning","author":"Li","year":"2019"},{"key":"10.1016\/j.eswa.2026.133362_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17990","article-title":"Comprehending and ordering semantics for image captioning","author":"Li","year":"2022"},{"key":"10.1016\/j.eswa.2026.133362_bib0021","series-title":"Proceedings of the ACL workshop on text summarization branches out","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.eswa.2026.133362_bib0022","series-title":"Proceedings of the 13th european conference on computer vision","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.133362_bib0023","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3242","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"Lu","year":"2017"},{"key":"10.1016\/j.eswa.2026.133362_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23359","article-title":"Semantic-conditional diffusion networks for image captioning","author":"Luo","year":"2023"},{"key":"10.1016\/j.eswa.2026.133362_bib0025","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2286","article-title":"Dual-level collaborative transformer for image captioning","volume":"vol. 35","author":"Luo","year":"2021"},{"key":"10.1016\/j.eswa.2026.133362_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109420","article-title":"Towards local visual modeling for image captioning","volume":"138","author":"Ma","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133362_bib0027","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., & Yuille, A. (2014). Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv preprint arXiv: 1412.6632."},{"key":"10.1016\/j.eswa.2026.133362_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10971","article-title":"X-linear attention networks for image captioning","author":"Pan","year":"2020"},{"key":"10.1016\/j.eswa.2026.133362_bib0029","series-title":"Proceedings of the 40th annual meeting of the association for computational linguistics","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.eswa.2026.133362_bib0030","series-title":"2020 3rd international conference on communication system, computing and IT applications (CSCITA)","first-page":"174","article-title":"Encoder-decoder architecture for image caption generation","author":"Parikh","year":"2020"},{"issue":"6","key":"10.1016\/j.eswa.2026.133362_bib0031","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0032","first-page":"1","article-title":"A dual-feature-based adaptive shared transformer network for image captioning","volume":"73","author":"Shi","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"6","key":"10.1016\/j.eswa.2026.133362_bib0033","doi-asserted-by":"crossref","first-page":"4794","DOI":"10.1007\/s10489-024-05416-y","article-title":"Visual contextual relationship augmented transformer for image captioning","volume":"54","author":"Su","year":"2024","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0034","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.1016\/j.eswa.2026.133362_bib0035","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/TKDE.2018.2837745","article-title":"Robust image hashing with tensor decomposition","volume":"31","author":"Tang","year":"2018","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.133362_bib0036","series-title":"Advances in neural information processing systems","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.eswa.2026.133362_bib0037","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"},{"key":"10.1016\/j.eswa.2026.133362_bib0038","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.eswa.2026.133362_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2585","article-title":"End-to-end transformer based model for image captioning","volume":"vol. 36","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133362_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104574","article-title":"Sequential transformer via an outside-in attention for image captioning","volume":"108","author":"Wei","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18020","article-title":"DifNet: Boosting visual information flow for image captioning","author":"Wu","year":"2022"},{"key":"10.1016\/j.eswa.2026.133362_bib0042","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.neunet.2022.01.011","article-title":"Dual global enhanced transformer for image captioning","volume":"148","author":"Xian","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.133362_bib0043","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"},{"issue":"1","key":"10.1016\/j.eswa.2026.133362_bib0044","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/s00530-023-01230-7","article-title":"BENet: Bi-directional enhanced network for image captioning","volume":"30","author":"Yan","year":"2024","journal-title":"Multimedia Systems"},{"key":"10.1016\/j.eswa.2026.133362_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10685","article-title":"Auto-encoding scene graphs for image captioning","author":"Yang","year":"2019"},{"key":"10.1016\/j.eswa.2026.133362_bib0046","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4651","article-title":"Image captioning with semantic attention","author":"You","year":"2016"},{"key":"10.1016\/j.eswa.2026.133362_bib0047","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","volume":"2","author":"Young","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"12","key":"10.1016\/j.eswa.2026.133362_bib0048","doi-asserted-by":"crossref","first-page":"4467","DOI":"10.1109\/TCSVT.2019.2947482","article-title":"Multimodal transformer with multi-view visual representation for image captioning","volume":"30","author":"Yu","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"6","key":"10.1016\/j.eswa.2026.133362_bib0049","doi-asserted-by":"crossref","first-page":"4829","DOI":"10.1109\/TCSVT.2023.3336371","article-title":"SPT: Spatial pyramid transformer for image captioning","volume":"34","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"8","key":"10.1016\/j.eswa.2026.133362_bib0050","doi-asserted-by":"crossref","first-page":"4257","DOI":"10.1109\/TCSVT.2023.3243725","article-title":"Cross on cross attention: Deep fusion transformer for image captioning","volume":"33","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133362_bib0051","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TIP.2025.3528216","article-title":"Intra- and inter-head orthogonal attention for image captioning","volume":"34","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133362_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15465","article-title":"RSTNet: Captioning with adaptive attention on visual and non-visual words","author":"Zhang","year":"2021"},{"issue":"1","key":"10.1016\/j.eswa.2026.133362_bib0053","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s10489-023-05198-9","article-title":"Integrating grid features and geometric coordinates for enhanced image captioning","volume":"54","author":"Zhao","year":"2024","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.133362_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113127","article-title":"From multi-scale grids to dynamic regions: dual-relation enhanced transformer for image captioning","volume":"311","author":"Zhou","year":"2025","journal-title":"Knowledge-Based Systems"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022712?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426022712?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T07:45:49Z","timestamp":1790322349000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426022712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":54,"alternative-id":["S0957417426022712"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133362","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Context-guided deep interaction networks for image captioning","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133362","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133362"}}