{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:10:21Z","timestamp":1787314221285,"version":"build-2736575974"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-24171-9","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T13:26:27Z","timestamp":1763472387000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Fusion of deep transfer learning models with Gannet optimisation algorithm for an advanced image captioning system for visual disabilities"],"prefix":"10.1038","volume":"15","author":[{"given":"Tareq M.","family":"Alkhaldi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mashael M.","family":"Asiri","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":[[2025,11,18]]},"reference":[{"key":"24171_CR1","first-page":"1","volume":"15","author":"H Jain","year":"2025","unstructured":"Jain, H., Dixit, A. & Sharma, A. Detecting image spam on social media platforms using deep learning techniques. J. Cybersecur. Inform. Manag. 15, 1 (2025).","journal-title":"J. Cybersecur. Inform. Manag."},{"key":"24171_CR2","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2020.02.041","volume":"396","author":"R Li","year":"2020","unstructured":"Li, R., Liang, H., Shi, Y., Feng, F. & Wang, X. Dual-CNN: A convolutional language decoder for paragraph image captioning. Neurocomputing 396, 92\u2013101 (2020).","journal-title":"Neurocomputing"},{"key":"24171_CR3","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Sharma, H., Dixit, P. Image captioning based on deep convolutional neural networks and LSTM. in Proc. 2nd Int. Conf. Power Electron. IoT Appl. Renew. Energy Control (PARC), Jan. 2022, pp. 1\u20134.","DOI":"10.1109\/PARC52418.2022.9726635"},{"issue":"3","key":"24171_CR4","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1007\/s10489-022-03624-y","volume":"53","author":"J Wei","year":"2023","unstructured":"Wei, J., Li, Z., Zhu, J. & Ma, H. Enhance understanding and reasoning ability for image captioning. Appl. Intell. 53(3), 2706\u20132722 (2023).","journal-title":"Appl. Intell."},{"key":"24171_CR5","doi-asserted-by":"crossref","unstructured":"Kwon, H., Lee, S. Toward backdoor attacks for image captioning model in deep neural networks. Secur. Commun. Netw. (2022).","DOI":"10.1155\/2022\/1525052"},{"key":"24171_CR6","doi-asserted-by":"publisher","first-page":"12015","DOI":"10.1088\/1742-6596\/1712\/1\/012015","volume":"1712","author":"G Geetha","year":"2020","unstructured":"Geetha, G., Kirthigadevi, T., Ponsam, G. G., Karthik, T. & Safa, M. Image captioning using deep convolutional neural networks (CNNs). J. Phys. Conf. Ser. 1712, 12015 (2020).","journal-title":"J. Phys. Conf. Ser."},{"issue":"1","key":"24171_CR7","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 learningbased image captioning. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 539\u2013559 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24171_CR8","first-page":"2","volume":"14","author":"KH Allehaibi","year":"2025","unstructured":"Allehaibi, K. H. Artificial intelligence based automated sign gesture recognition solutions for visually challenged people. J. Intell. Syst. Internet of Things 14, 2 (2025).","journal-title":"J. Intell. Syst. Internet of Things"},{"issue":"1","key":"24171_CR9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s11220-022-00400-7","volume":"23","author":"KP Deorukhkar","year":"2022","unstructured":"Deorukhkar, K. P. & Ket, S. Image captioning using hybrid LSTM-RNN with deep features. Sens. Imaging 23(1), 31 (2022).","journal-title":"Sens. Imaging"},{"issue":"2","key":"24171_CR10","first-page":"42","volume":"4","author":"S Gupta","year":"2021","unstructured":"Gupta, S. et al. Image caption generation and comprehensive comparison of image encoders. Full Length Article 4(2), 42\u20132 (2021).","journal-title":"Full Length Article"},{"key":"24171_CR11","first-page":"8","volume":"10","author":"SD Pujari","year":"2024","unstructured":"Pujari, S. D. & Patane, A. S. Image caption generation using deep learning techniques. Grenze Int. J. Eng. Technol. 10, 8 (2024).","journal-title":"Grenze Int. J. Eng. Technol."},{"key":"24171_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, P. & Katal, N. Deep learning based automatic image caption generation for visually impaired people. In Intelligent Systems and Applications in Computer Vision.\u00a0141\u2013157 (CRC Press, 2023).","DOI":"10.1201\/9781003453406-12"},{"key":"24171_CR13","doi-asserted-by":"crossref","unstructured":"Da Silva, J.R.B., Soares, J.V.B., Gomes, L.R., Sicchar, J.R. An approach to the use of stereo vision system and AI for the accessibility of the visually impaired. In 2024 International Conference on Control, Automation and Diagnosis (ICCAD) (pp. 1\u20136). IEEE (2024).","DOI":"10.1109\/ICCAD60883.2024.10553945"},{"key":"24171_CR14","doi-asserted-by":"crossref","unstructured":"Vamsi, T.M.N., Shankar, K.R., Karthik, G., Puruvi, M., Chanti, B. Deep Learning\u2013Based Surrounding Descriptor for the Visually Challenged. In XVIII International Conference on Data Science and Intelligent Analysis of Information (pp. 155\u2013163). Cham: Springer Nature Switzerland (2023).","DOI":"10.1007\/978-3-031-51167-7_15"},{"key":"24171_CR15","doi-asserted-by":"crossref","unstructured":"Kushal, K., Manoj, M., Reddy, K., Nair, P.C. An In-Depth Exploration of Image Captioning Training Approaches and Performance Analysis. In 2024 IEEE 9th International Conference for Convergence in Technology (I2CT) (pp. 1\u20137). IEEE (2024).","DOI":"10.1109\/I2CT61223.2024.10544337"},{"key":"24171_CR16","doi-asserted-by":"crossref","unstructured":"Bipin, P.B., Abirami, S. Smart Assistant for Visually Impaired People using Deep Learning Algorithms. In 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS) (pp. 389\u2013395). IEEE (2023).","DOI":"10.1109\/ICSCSS57650.2023.10169851"},{"key":"24171_CR17","unstructured":"Bindu, M.G.H., Vatsal, B.S.S., Teja, L.D., Kumar, T.P., Raju, T.J., Keerthi, C. Attention-Augmented LSTM Networks for Image Caption Generation using VGG16 Embeddings (2024)."},{"key":"24171_CR18","doi-asserted-by":"crossref","unstructured":"Hafeth, D.A., Lal, G., Al-Khafajiy, M., Baker, T., Kollias, S. Cloud-IoT Application for Scene Understanding in Assisted Living: Unleashing the Potential of Image Captioning and Large Language Model (ChatGPT). In 2023 16th International Conference on Developments in eSystems Engineering (DeSE) (pp. 150\u2013155). IEEE (2023).","DOI":"10.1109\/DeSE60595.2023.10468995"},{"key":"24171_CR19","doi-asserted-by":"crossref","unstructured":"Anwar, Q.M.I.H., Satyamurty, C.V., Godi, R.K. Enhancing Accessibility: Image Captioning for Visually Impaired Individuals in the Realm of ECE Advancements. In 2024 4th International Conference on Technological Advancements in Computational Sciences (ICTACS) (pp. 317\u2013321). IEEE (2024).","DOI":"10.1109\/ICTACS62700.2024.10840791"},{"key":"24171_CR20","doi-asserted-by":"crossref","unstructured":"Qazi, N., Dewaji, I., Khan, N. 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\/ahfe10059725964"},{"issue":"20","key":"24171_CR21","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. Multimed. Tools Appl. 83(20), 59413\u201359438 (2024).","journal-title":"Multimed. Tools Appl."},{"issue":"1","key":"24171_CR22","doi-asserted-by":"publisher","first-page":"7366","DOI":"10.1038\/s41598-025-91802-6","volume":"15","author":"L Chen","year":"2025","unstructured":"Chen, L. et al. Boosting adversarial transferability in vision-language models via multimodal feature heterogeneity. Sci. Rep. 15(1), 7366 (2025).","journal-title":"Sci. Rep."},{"issue":"41","key":"24171_CR23","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. A transformer based real-time photo captioning framework for visually impaired people with visual attention. Multimed. Tools Appl. 83(41), 88859\u201388878 (2024).","journal-title":"Multimed. Tools Appl."},{"key":"24171_CR24","unstructured":"Prottasha, N.J., et al. PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models. arXiv preprint arXiv:2504.14117. (2025)"},{"key":"24171_CR25","doi-asserted-by":"publisher","first-page":"146","DOI":"10.24237\/djes.2024.17310","volume":"8","author":"AJ Yousif","year":"2024","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. Sci. 8, 146\u2013162 (2024).","journal-title":"Diyala J. Eng. Sci."},{"issue":"9","key":"24171_CR26","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.3390\/app15094909","volume":"15","author":"JP Venugopal","year":"2025","unstructured":"Venugopal, J. P. et al. DCAT: A novel transformer-based approach for dynamic context-aware image captioning in the tamil language. Appl. Sci. 15(9), 4909 (2025).","journal-title":"Appl. Sci."},{"key":"24171_CR27","doi-asserted-by":"crossref","unstructured":"Ingale, S.P., Bamnote, G.R. Advancements in Image Captioning using Deep Learning Techniques for Enhanced Descriptive Models. In 2024 2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIEI) (pp. 1\u20136). IEEE (2024).","DOI":"10.1109\/IDICAIEI61867.2024.10842893"},{"key":"24171_CR28","first-page":"1","volume":"8","author":"I Al Badarneh","year":"2025","unstructured":"Al Badarneh, I., Al Mahmoud, R. H., Hammo, B. H. & Al-Kadi, O. Attention-based transformer model for Arabic image captioning. Neural Comput. Appl. 8, 1\u201333 (2025).","journal-title":"Neural Comput. Appl."},{"issue":"5","key":"24171_CR29","doi-asserted-by":"publisher","first-page":"15363","DOI":"10.1007\/s11042-021-11877-x","volume":"83","author":"K Shaheed","year":"2024","unstructured":"Shaheed, K. & Qureshi, I. A hybrid proposed image quality assessment and enhancement framework for finger vein recognition. Multimed. Tools Appl. 83(5), 15363\u201315388 (2024).","journal-title":"Multimed. Tools Appl."},{"key":"24171_CR30","first-page":"1","volume":"8","author":"YR Haddadi","year":"2024","unstructured":"Haddadi, Y. R., Mansouri, B. & Khodja, F. Z. I. A novel medical image enhancement algorithm based on CLAHE and pelican optimization. Multimed. Tools Appl. 8, 1\u201320 (2024).","journal-title":"Multimed. Tools Appl."},{"issue":"3","key":"24171_CR31","first-page":"19","volume":"16","author":"M Archana","year":"2024","unstructured":"Archana, M. & Velmurugan, T. Enhancing sentiment analysis in electronic product reviews using machine learning algorithms. Int. J. Comput. Inf. Syst. Ind. Manag. Appl. 16(3), 19\u201319 (2024).","journal-title":"Int. J. Comput. Inf. Syst. Ind. Manag. Appl."},{"key":"24171_CR32","doi-asserted-by":"crossref","unstructured":"Kalabarige, L. R., Ramana, A. V., Rao, R. S. & Holla, M. R. Boosting pineapple maturity classification: impact of data augmentation and visual transformer integration with transfer learning. IEEE Access. (2024).","DOI":"10.1109\/ACCESS.2024.3519753"},{"issue":"3","key":"24171_CR33","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/s12046-024-02538-4","volume":"49","author":"M Somesha","year":"2024","unstructured":"Somesha, M. & Pais, A. R. DeepEPhishNet: a deep learning framework for email phishing detection using word embedding algorithms. S\u0101dhan\u0101 49(3), 212 (2024).","journal-title":"S\u0101dhan\u0101"},{"issue":"12","key":"24171_CR34","doi-asserted-by":"publisher","first-page":"3998","DOI":"10.3390\/buildings14123998","volume":"14","author":"X Wang","year":"2024","unstructured":"Wang, X., Zhong, Y., Zhu, F. & Huang, J. Digital industrial design method in architectural design by machine learning optimization: Towards sustainable construction practices of geopolymer concrete. Buildings 14(12), 3998 (2024).","journal-title":"Buildings"},{"key":"24171_CR35","unstructured":"https:\/\/www.kaggle.com\/datasets\/adityajn105\/flickr8k"},{"key":"24171_CR36","unstructured":"https:\/\/www.kaggle.com\/datasets\/hsankesara\/flickr-image-dataset"},{"key":"24171_CR37","doi-asserted-by":"crossref","unstructured":"Arasi, M. A. et al. Automated image captioning using sparrow search algorithm with improved deep learning model. IEEE Access (2023).","DOI":"10.1109\/ACCESS.2023.3317276"},{"key":"24171_CR38","doi-asserted-by":"publisher","first-page":"142643","DOI":"10.1109\/ACCESS.2023.3342703","volume":"11","author":"RO Alnashwan","year":"2023","unstructured":"Alnashwan, R. O. et al. Lighting search algorithm with convolutional neural network-based image captioning system for natural language processing. IEEE Access 11, 142643\u2013142651 (2023).","journal-title":"IEEE Access"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24171-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24171-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24171-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T02:02:33Z","timestamp":1763863353000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24171-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["24171"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-24171-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"16 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 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":"40446"}}