{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:19:57Z","timestamp":1784229597766,"version":"3.55.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100019345","name":"King Salman Center for Disability Research","doi-asserted-by":"publisher","award":["KSRG-2024- 083"],"award-info":[{"award-number":["KSRG-2024- 083"]}],"id":[{"id":"10.13039\/501100019345","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-19733-w","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T14:45:55Z","timestamp":1760453155000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An innovative multi-head attention mechanism-driven recurrent neural network model with feature representation fusion for enhanced image captioning to assist individuals with visual impairments"],"prefix":"10.1038","volume":"15","author":[{"given":"Mashael M.","family":"Asiri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kholoud","family":"Alghamdi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad","family":"Alzahrani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahir Mohammed","family":"Sharif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"issue":"2","key":"19733_CR1","doi-asserted-by":"publisher","first-page":"35","DOI":"10.54216\/JCIM.020201","volume":"2","author":"D Prashar","year":"2020","unstructured":"Prashar, D., Chakraborty, G. & Jha, S. Energy efficient laser based embedded system for blind turn traffic control. J. Cybersecur. Inform. Manage. 2 (2), 35\u201343 (2020).","journal-title":"J. Cybersecur. Inform. Manage."},{"issue":"3","key":"19733_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617592","volume":"56","author":"T Ghandi","year":"2023","unstructured":"Ghandi, T., Pourreza, H. & Mahyar, H. Deep learning approaches on image captioning: A review. ACM Comput. Surveys. 56 (3), 1\u201339 (2023).","journal-title":"ACM Comput. Surveys"},{"key":"19733_CR3","doi-asserted-by":"crossref","unstructured":"Sharma, H., Agrahari, M., Singh, S. K., Firoj, M. & Mishra, R. K. February. Image captioning: a comprehensive survey. In 2020 International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC) (pp. 325\u2013328). IEEE. (2020).","DOI":"10.1109\/PARC49193.2020.236619"},{"key":"19733_CR4","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W. & Luo, J. Unsupervised image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 4125\u20134134). (2019).","DOI":"10.1109\/CVPR.2019.00425"},{"key":"19733_CR5","unstructured":"Herdade, S., Kappeler, A., Boakye, K. & Soares, J. Image captioning: transforming objects into words. Advances Neural Inform. Process. Systems, 32. (2019)."},{"key":"19733_CR6","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhou, X., Qiu, X. & Zhu, X. Improving image captioning with better use of captions. arXiv preprint arXiv:2006.11807. (2020).","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"19733_CR7","doi-asserted-by":"crossref","unstructured":"He, S. et al. Image captioning through image transformer. In Proceedings of the Asian conference on computer vision. (2020).","DOI":"10.1007\/978-3-030-69538-5_10"},{"issue":"1","key":"19733_CR8","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TPAMI.2022.3148210","volume":"45","author":"M Stefanini","year":"2022","unstructured":"Stefanini, M. et al. From show to tell: A survey on deep learning-based image captioning. IEEE Trans. Pattern Anal. Mach. Intell. 45 (1), 539\u2013559 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19733_CR9","doi-asserted-by":"crossref","unstructured":"Sidorov, O., Hu, R., Rohrbach, M. & Singh, A. Textcaps: a dataset for image captioning with reading comprehension. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16 (pp. 742\u2013758). Springer International Publishing. (2020).","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"19733_CR10","doi-asserted-by":"crossref","unstructured":"Jain, H., Dixit, A. & Sharma, A. Detecting image spam on social media platforms using deep learning techniques. Journal Cybersecur. & Inform. Management, 15(1). (2025).","DOI":"10.54216\/JCIM.150106"},{"key":"19733_CR11","doi-asserted-by":"crossref","unstructured":"Kalantari, F., Faez, K., Amindavar, H. & Nazari, S. Improved image reconstruction from brain activity through automatic image captioning. Scientific Reports, 15(1), p.4907. (2025).","DOI":"10.1038\/s41598-025-89242-3"},{"key":"19733_CR12","doi-asserted-by":"crossref","unstructured":"Cao, Z., Xia, J. & Zhou, M. De-confounding Feature Fusion Transformer Network for Image Captioning in Assistive Navigation Applications for the Visually Impaired (IEEE Transactions on Instrumentation and Measurement, 2025).","DOI":"10.1109\/TIM.2025.3553260"},{"key":"19733_CR13","doi-asserted-by":"crossref","unstructured":"Deepak, G. et al. K.V. and Automatic image captioning system using a deep learning approach. Soft Computing, pp.1\u20139. (2023).","DOI":"10.1007\/s00500-023-08544-8"},{"key":"19733_CR14","doi-asserted-by":"crossref","unstructured":"Al Badarneh, I., Hammo, B. H. & Al-Kadi, O. An ensemble model with an attention-based mechanism for image captioning. Computers and Electrical Engineering, 123, p.110077. (2025).","DOI":"10.1016\/j.compeleceng.2025.110077"},{"key":"19733_CR15","doi-asserted-by":"crossref","unstructured":"Padate, R. & Kalla, M. Automated Image Captioning System with Deep Learning Enabled Optimized Approachpp.1\u201321 (Multimedia Tools and Applications, 2024).","DOI":"10.1007\/s11042-024-19927-w"},{"key":"19733_CR16","doi-asserted-by":"crossref","unstructured":"Lee, H., Song, J., Hwang, K. & Kang, M. Auto-Scenario Generator for Autonomous Vehicle Safety: Multimodal Attention-based Image Captioning Model Using Digital Twin Data (IEEE Access, 2024).","DOI":"10.1109\/ACCESS.2024.3487588"},{"key":"19733_CR17","doi-asserted-by":"publisher","first-page":"104633","DOI":"10.1109\/ACCESS.2023.3317276","volume":"11","author":"MA Arasi","year":"2023","unstructured":"Arasi, M. A. et al. Automated image captioning using sparrow search algorithm with improved deep learning model. IEEE Access. 11, 104633\u2013104642 (2023).","journal-title":"IEEE Access."},{"key":"19733_CR18","first-page":"12","volume":"3","author":"SP Deore","year":"2023","unstructured":"Deore, S. P., Bagwan, T. S., Bhukan, P. S., Rajpal, H. T. & Gade, S. B. Enhancing image captioning and auto-tagging through a FCLN with faster R-CNN integration. Inf. Dyn. Appl. 3, 12\u201320 (2023).","journal-title":"Inf. Dyn. Appl."},{"issue":"20","key":"19733_CR19","doi-asserted-by":"publisher","first-page":"59413","DOI":"10.1007\/s11042-023-17849-7","volume":"83","author":"KM Safiya","year":"2024","unstructured":"Safiya, K. M. & Pandian, R. A real-time image captioning framework using computer vision to help the visually impaired. Multimedia Tools Appl. 83 (20), 59413\u201359438 (2024).","journal-title":"Multimedia Tools Appl."},{"key":"19733_CR20","doi-asserted-by":"crossref","unstructured":"Hossain, M. I. A., Anjom, J. & Chowdhury, R. I. Towards walkable footpath detection for the visually impaired on Bangladeshi roads with smartphones using deep edge intelligence. Array, 26, p.100388. (2025).","DOI":"10.1016\/j.array.2025.100388"},{"key":"19733_CR21","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.procs.2025.01.005","volume":"252","author":"SS More","year":"2025","unstructured":"More, S. S. et al. Empowering the visually impaired: YOLOv8-based object detection in android applications. Procedia Comput. Sci. 252, 457\u2013469 (2025).","journal-title":"Procedia Comput. Sci."},{"key":"19733_CR22","doi-asserted-by":"crossref","unstructured":"Anwar, M. et al. E-GlauNet: A CNN-Based ensemble deep learning model for glaucoma detection and staging using retinal fundus images. Computers Mater. & Continua, 84(2). (2025).","DOI":"10.32604\/cmc.2025.065141"},{"issue":"4","key":"19733_CR23","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1108\/JET-03-2024-0024","volume":"18","author":"H Nguyen","year":"2024","unstructured":"Nguyen, H., Huynh, T., Tran, N. & Nguyen, T. MyUEVision: an application generating image caption for assisting visually impaired people. J. Enabling Technol. 18 (4), 248\u2013264 (2024).","journal-title":"J. Enabling Technol."},{"key":"19733_CR24","doi-asserted-by":"crossref","unstructured":"Qazi, N., Dewaji, I. & Khan, N. June. Vision Transformer Based Image Captioning for the Visually Impaired. In 14th International Conference on Human Interaction and Emerging Technologies: Artificial Intelligence & Future Applications, IHIET-FS 2025, June 10\u201312, 2025, University of East London, London, United Kingdom. (Vol. 196, pp. 153\u2013162). AHFE International. (2025).","DOI":"10.54941\/ahfe1005964"},{"issue":"41","key":"19733_CR25","doi-asserted-by":"publisher","first-page":"88859","DOI":"10.1007\/s11042-024-18966-7","volume":"83","author":"AK Muhammed Kunju","year":"2024","unstructured":"Muhammed Kunju, A. K., Baskar, S., Zafar, S., AR, B., A, S. K. & S, R. and A transformer based real-time photo captioning framework for visually impaired people with visual attention. Multimedia Tools Appl. 83 (41), 88859\u201388878 (2024).","journal-title":"Multimedia Tools Appl."},{"key":"19733_CR26","doi-asserted-by":"crossref","unstructured":"Uikey, J. et al. January. Visual Understanding and Navigation for the Visually Impaired Using Image Captioning. In 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI) (pp. 531\u2013536). IEEE. (2025).","DOI":"10.1109\/IC3ECSBHI63591.2025.10991312"},{"key":"19733_CR27","doi-asserted-by":"crossref","unstructured":"Yousif, A. J. & Al-Jammas, M. H. A lightweight visual Understanding system for enhanced assistance to the visually impaired using an embedded platform. Diyala J. Eng. Sciences, pp.146\u2013162. (2024).","DOI":"10.24237\/djes.2024.17310"},{"key":"19733_CR28","doi-asserted-by":"crossref","unstructured":"Jenisha, J. & Priyadharsini, C. March. Enhanced Vision: Hybrid Deep Learning Based Model for Image Captioning and Audio Synthesis. In 2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS) (Vol. 1, pp. 2502\u20132507). IEEE. (2024).","DOI":"10.1109\/ICACCS60874.2024.10717173"},{"key":"19733_CR29","doi-asserted-by":"crossref","unstructured":"Biswas, A. & Branicki, M. A unified framework for the analysis of accuracy and stability of a class of approximate Gaussian filters for the Navier\u2013Stokes equations. Nonlinearity, 37(12), p.125013. (2024).","DOI":"10.1088\/1361-6544\/ad805b"},{"key":"19733_CR30","doi-asserted-by":"crossref","unstructured":"Rastogi, D. et al. Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks. Life, 15(3), p.327. (2025).","DOI":"10.3390\/life15030327"},{"key":"19733_CR31","unstructured":"Putra, B. P. E., Prasetyo, H. & Suryani, E. Residual Transformer Fusion Network for Salt and Pepper Image Denoising. arXiv preprint arXiv:2502.09000. (2025)."},{"key":"19733_CR32","doi-asserted-by":"crossref","unstructured":"Hemal, M. M. & Saha, S. Explainable deep learning-based meta-classifier approach for multi-label classification of retinal diseases. Array, p.100402. (2025).","DOI":"10.1016\/j.array.2025.100402"},{"key":"19733_CR33","doi-asserted-by":"crossref","unstructured":"Yu, Y., Yang, H., Peng, F. & Wang, X. Drilling Condition Identification Method for Imbalanced Datasets. Applied Sciences, 15(6), p.3362. (2025).","DOI":"10.3390\/app15063362"},{"key":"19733_CR34","doi-asserted-by":"crossref","unstructured":"Xi, H. et al. Prediction of Lithium Battery Voltage and State of Charge Using Multi-Head Attention BiLSTM Neural Network. Applied Sciences, 15(6), p.3011. (2025).","DOI":"10.3390\/app15063011"},{"key":"19733_CR35","unstructured":"https:\/\/www.kaggle.com\/datasets\/adityajn105\/flickr8k"},{"key":"19733_CR36","unstructured":"https:\/\/www.kaggle.com\/datasets\/hsankesara\/flickr-image-dataset"},{"key":"19733_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T. Y. et al. September. Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740\u2013755). Springer, Cham. (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19733_CR38","doi-asserted-by":"publisher","first-page":"45219","DOI":"10.1109\/ACCESS.2022.3169781","volume":"10","author":"JW Bae","year":"2022","unstructured":"Bae, J. W., Lee, S. H., Kim, W. Y., Seong, J. H. & Seo, D. H. Image captioning model using part-of-speech guidance module for description with diverse vocabulary. IEEE Access. 10, 45219\u201345229 (2022).","journal-title":"IEEE Access."},{"key":"19733_CR39","doi-asserted-by":"crossref","unstructured":"Redondo, A. et al. Multiclass classification of oral mucosal lesions by deep learning from clinical images without performing any restrictions. Biomedical Signal Processing and Control, 111, p.108337. (2026).","DOI":"10.1016\/j.bspc.2025.108337"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19733-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19733-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19733-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T14:46:05Z","timestamp":1760453165000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19733-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["19733"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-19733-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"assertion":[{"value":"14 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"35845"}}