{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T23:34:44Z","timestamp":1784158484280,"version":"3.55.0"},"reference-count":26,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T00:00:00Z","timestamp":1776556800000},"content-version":"vor","delay-in-days":108,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Applied Computational Intelligence and Soft Computing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>Generating accurate and contextually relevant captions for images remains a core challenge in vision\u2010language understanding. To address this, we propose the double\u2010attention transformer (DAT). This novel image captioning model integrates self\u2010attention and cross\u2010attention mechanisms to enhance intramodal feature learning and intermodal semantic alignment. Unlike conventional encoder\u2013decoder models, the DAT model enables richer contextual blending between visual and textual modalities, resulting in more precise and semantically coherent captions. Evaluated under a Flickr8k fine\u2010tuning regime using standard, publicly available pretrained encoder initializations, the DAT achieves a BLEU\u20104 score of 25.6, METEOR score of 22.3, CIDEr score of 79.2, and SPICE score of 15.8. It also consistently outperforms the baseline across precision (0.83), recall (0.78), and F1 score (0.80) metrics. Within this setting, the contribution is architectural, and the results indicate competitive performance among methods evaluated under the same fine\u2010tuning conditions. These results demonstrate the effectiveness of dual attention mechanisms, particularly in fine\u2010grained semantic representation and caption generation under low\u2010resource conditions. The DAT model offers a lightweight yet robust framework suitable for real\u2010time image captioning applications where computational resources are constrained.<\/jats:p>","DOI":"10.1155\/acis\/5733967","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T05:38:06Z","timestamp":1776663486000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Double\u2010Attention Transformer for Cross\u2010Modal Image Captioning: Enhancing Visual\u2013Linguistic Alignment on Low\u2010Resource Datasets"],"prefix":"10.1155","volume":"2026","author":[{"given":"Muhammad","family":"Aoun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4649-2376","authenticated-orcid":false,"given":"Tehseen","family":"Mazhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tariq","family":"Shahzad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wajahat","family":"Waheed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5320-1012","authenticated-orcid":false,"given":"Habib","family":"Hamam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,19]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"publisher","DOI":"10.3390\/engproc2023059182"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02725-6"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.5455\/jjee.204-1728140025"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18467-7"},{"key":"e_1_2_10_5_2","unstructured":"HafethD. A.andKolliasS. Insights Into Object Semantics: Leveraging Transformer 2024."},{"key":"e_1_2_10_6_2","first-page":"1","article-title":"A Review of Deep Learning Image Captioning Approaches","volume":"12","author":"Thakare Y. A.","year":"2024","journal-title":"Journal of Integrated Science and Technology"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103672"},{"key":"e_1_2_10_8_2","unstructured":"RotsteinN. BensaidD. BrodyS. GanzR. andKimmelR. Fusecap: Leveraging Large Language Models for Enriched Fused Image Captions 2023 5689\u20135700."},{"key":"e_1_2_10_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3356551"},{"key":"e_1_2_10_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01341-8"},{"key":"e_1_2_10_11_2","unstructured":"YangX. WuY. YangM. ChenH. andGengX. Exploring Diverse In-Context Configurations for Image Captioning 2023 1\u201320."},{"key":"e_1_2_10_12_2","first-page":"1","article-title":"Improving Multimodal Datasets With Image Captioning","author":"Nguyen T.","year":"2023","journal-title":"NeurIPS"},{"key":"e_1_2_10_13_2","doi-asserted-by":"crossref","unstructured":"ZengZ. ZhangH. LuR. WangD. ChenB. andWangZ. ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 23465\u201323476 https:\/\/doi.org\/10.1109\/CVPR52729.2023.02247.","DOI":"10.1109\/CVPR52729.2023.02247"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"RamosR. MartinsB. ElliottD. andKementchedjhievaY. Smallcap: Lightweight Image Captioning Prompted With Retrieval Augmentation 2023 Proceedings of the IEEE conference on computer vision and pattern Recognition 2023 2840\u20132849 https:\/\/doi.org\/10.1109\/CVPR52729.2023.00278.","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23031286"},{"key":"e_1_2_10_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118669"},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92788-x"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03560-z"},{"key":"e_1_2_10_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2025.100680"},{"key":"e_1_2_10_20_2","unstructured":"LiJ. LiD. XiongC. andHoiS. BLIP-2: Bootstrapping Language-Image Pre-Training With Frozen Image Encoders and Large Language Models Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2023 CVPR 19730\u201319742."},{"key":"e_1_2_10_21_2","unstructured":"WangP. YangA. MenonA.et al. OFA: Unifying Architectures Tasks and Modalities Through a Simple Sequence-to-Sequence Learning Framework Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023."},{"key":"e_1_2_10_22_2","first-page":"2345","article-title":"Vision Transformer for Dense Prediction: A Survey","volume":"45","author":"Zhu X.","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_10_23_2","first-page":"2048","article-title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","volume":"34","author":"Yang Z.","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_2_10_24_2","unstructured":"TouvronH. MartinL. StoneK.et al. LLaMA: Open and Efficient Foundation Language Models 2023."},{"key":"e_1_2_10_25_2","unstructured":"RadfordA. KimJ. W. HallacyC.et al. Learning Transferable Visual Models From Natural Language Supervision International Conference on Machine Learning (ICML) 2023."},{"key":"e_1_2_10_26_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Alayrac J.","year":"2023"}],"container-title":["Applied Computational Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/acis\/5733967","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/acis\/5733967","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/acis\/5733967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T05:38:13Z","timestamp":1776663493000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/acis\/5733967"}},"subtitle":[],"editor":[{"given":"Vivek","family":"Bhardwaj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/acis\/5733967"],"URL":"https:\/\/doi.org\/10.1155\/acis\/5733967","archive":["Portico"],"relation":{},"ISSN":["1687-9724","1687-9732"],"issn-type":[{"value":"1687-9724","type":"print"},{"value":"1687-9732","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-08-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5733967"}}