{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T15:44:16Z","timestamp":1767109456060,"version":"3.41.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T00:00:00Z","timestamp":1751068800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T00:00:00Z","timestamp":1751068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04115-w","type":"journal-article","created":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T08:01:02Z","timestamp":1751097662000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Efficient EPReLU-CSGNN-MALSTCAM and SSOA-Based Explainable Artificial Intelligence (XAI) to Generate Textual Explanations"],"prefix":"10.1007","volume":"6","author":[{"given":"B. P.","family":"Sheela","sequence":"first","affiliation":[]},{"given":"H.","family":"Girisha","sequence":"additional","affiliation":[]},{"given":"B.","family":"Sreepathi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,28]]},"reference":[{"issue":"1","key":"4115_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-022-00571-w","volume":"9","author":"MA Al-Malla","year":"2022","unstructured":"Al-Malla MA, Jafar A, Ghneim N. Image captioning model using attention and object features to mimic human image understanding. J Big Data. 2022;9(1):1\u201316. https:\/\/doi.org\/10.1186\/s40537-022-00571-w.","journal-title":"J. Big Data"},{"key":"4115_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2020.3042484","volume":"8","author":"S Amirian","year":"2020","unstructured":"Amirian S, Rasheed K, Taha TR, Arabnia HR. Automatic image and video caption generation with deep learning: a concise review and algorithmic overlap. IEEE Access. 2020;8:1\u201315. https:\/\/doi.org\/10.1109\/ACCESS.2020.3042484.","journal-title":"IEEE Access"},{"key":"4115_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.displa.2021.102069","volume":"70","author":"C Bai","year":"2021","unstructured":"Bai C, Zheng A, Huang Y, Pan X, Chen N. Boosting convolutional image captioning with semantic content and visual relationship. Displays. 2021;70:1\u201314. https:\/\/doi.org\/10.1016\/j.displa.2021.102069.","journal-title":"Displays"},{"issue":"17","key":"4115_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.heliyon.2024.e36272","volume":"10","author":"A Bhuiyan","year":"2024","unstructured":"Bhuiyan A, Hossain E, Hoque MM, Dewan MAA. Enhancing image caption generation through context-aware attention mechanism. Heliyon. 2024;10(17):1\u201317. https:\/\/doi.org\/10.1016\/j.heliyon.2024.e36272.","journal-title":"Heliyon"},{"key":"4115_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2022.3161428","volume":"10","author":"R Castro","year":"2022","unstructured":"Castro R, Pineda I, Lim W, Morocho-Cayamcela ME. Deep learning approaches based on transformer architectures for image captioning tasks. IEEE Access. 2022;10:1\u201316. https:\/\/doi.org\/10.1109\/ACCESS.2022.3161428.","journal-title":"IEEE Access"},{"key":"4115_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTARS.2023.3305889","volume":"16","author":"R Du","year":"2023","unstructured":"Du R, Cao W, Zhang W, Zhi G, Sun X, Li S, Li J. From plane to hierarchy: deformable transformer for remote sensing image captioning. IEEE J Sel Top Appl Earth Observ Remote Sens. 2023;16:1\u201314. https:\/\/doi.org\/10.1109\/JSTARS.2023.3305889.","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"4115_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-024-02026-6","volume":"132","author":"V Gabeff","year":"2024","unstructured":"Gabeff V, Ru\u00dfwurm M, Tuia D, Mathis A. WildCLIP: scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models. Int J Comput Vis. 2024;132:1\u201317. https:\/\/doi.org\/10.1007\/s11263-024-02026-6.","journal-title":"Int J Comput Vis"},{"key":"4115_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JSTARS.2020.3013818","volume":"13","author":"G Hoxha","year":"2020","unstructured":"Hoxha G, Melgani F, Demir B. Toward remote sensing image retrieval under a deep image captioning perspective. IEEE J Sel Top Appl Earth Observ Remote Sens. 2020;13:1\u201314. https:\/\/doi.org\/10.1109\/JSTARS.2020.3013818.","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"4115_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2021.107928","volume":"115","author":"J Ji","year":"2021","unstructured":"Ji J, Du Z, Zhang X. Divergent-convergent attention for image captioning. Pattern Recogn. 2021;115:1\u201312. https:\/\/doi.org\/10.1016\/j.patcog.2021.107928.","journal-title":"Pattern Recogn"},{"key":"4115_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIP.2020.3004729","volume":"29","author":"J Ji","year":"2020","unstructured":"Ji J, Xu C, Zhang X, Wang B, Song X. Spatio-temporal memory attention for image captioning. IEEE Trans Image Process. 2020;29:1\u201314. https:\/\/doi.org\/10.1109\/TIP.2020.3004729.","journal-title":"IEEE Trans Image Process"},{"key":"4115_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2022.3198234","volume":"19","author":"H Kandala","year":"2022","unstructured":"Kandala H, Saha S, Banerjee B, Zhu XX. Exploring transformer and multilabel classification for remote sensing image captioning. IEEE Geosci Remote Sens Lett. 2022;19:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2022.3198234.","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"4115_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2021.108285","volume":"122","author":"JH Lim","year":"2022","unstructured":"Lim JH, Chan CS, Ng KW, Fan L, Yang Q. Protect, show, attend and tell: empowering image captioning models with ownership protection. Pattern Recogn. 2022;122:1\u201313. https:\/\/doi.org\/10.1016\/j.patcog.2021.108285.","journal-title":"Pattern Recogn"},{"issue":"2","key":"4115_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1049\/ipr2.12367","volume":"16","author":"G Luo","year":"2022","unstructured":"Luo G, Cheng L, Jing C, Zhao C, Song G. A thorough review of models, evaluation metrics, and datasets on image captioning. IET Image Process. 2022;16(2):1\u201322. https:\/\/doi.org\/10.1049\/ipr2.12367.","journal-title":"IET Image Process"},{"key":"4115_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2023.109420","volume":"138","author":"Y Ma","year":"2023","unstructured":"Ma Y, Ji J, Sun X, Zhou Y, Ji R. Towards local visual modeling for image captioning. Pattern Recogn. 2023;138:1\u201332. https:\/\/doi.org\/10.1016\/j.patcog.2023.109420.","journal-title":"Pattern Recogn"},{"key":"4115_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10","author":"VQ Nguyen","year":"2022","unstructured":"Nguyen VQ, Suganuma M, Okatani T. GRIT faster and better image captioning transformer using dual visual features. Eur Conf Comput Vis. 2022. https:\/\/doi.org\/10.1007\/978-3-031-20059-5_10.","journal-title":"Eur Conf Comput Vis"},{"key":"4115_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412898","author":"J Perez-Martin","year":"2020","unstructured":"Perez-Martin J, Bustos B, P\u00e9rez J. Attentive visual semantic specialized network for video captioning. Proc Int Conf Pattern Recognit. 2020. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412898.","journal-title":"Proc Int Conf Pattern Recognit"},{"key":"4115_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.rineng.2023.101107","volume":"18","author":"AM Rinaldi","year":"2023","unstructured":"Rinaldi AM, Russo C, Tommasino C. Automatic image captioning combining natural language processing and deep neural networks. Results Eng. 2023;18:1\u201314. https:\/\/doi.org\/10.1016\/j.rineng.2023.101107.","journal-title":"Results Eng"},{"key":"4115_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/PARC49193.2020.236619","volume":"2020","author":"H Sharma","year":"2020","unstructured":"Sharma H, Agrahari M, Singh SK, Firoj M, Mishra RK. Image captioning: a comprehensive survey. Int Conf Power Electron IoT Appl Renew Energy Control. 2020;2020:1\u20134. https:\/\/doi.org\/10.1109\/PARC49193.2020.236619.","journal-title":"Int Conf Power Electron IoT Appl Renew Energy Control"},{"issue":"7","key":"4115_CR19","doi-asserted-by":"publisher","first-page":"102127","DOI":"10.1016\/j.jksuci.2024.102127","volume":"36","author":"A Thobhani","year":"2024","unstructured":"Thobhani A, Zou B, Kui X, Al-Shargabi AA, Derea Z, Abdussalam A, Asham MA. A novel image captioning model with visual-semantic similarities and visual representations re-weighting. J King Saud Univ-Comput Inf Sci. 2024;36(7):102127. https:\/\/doi.org\/10.1016\/j.jksuci.2024.102127.","journal-title":"J King Saud Univ-Comput Inf Sci"},{"key":"4115_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/computers13120305","volume":"13","author":"S Tyagi","year":"2024","unstructured":"Tyagi S, Oki OA, Verma V, Gupta S, Vijarania M. Novel advance image caption generation utilizing vision transformer and generative adversarial networks. Computers. 2024;13:1\u201323. https:\/\/doi.org\/10.3390\/computers13120305.","journal-title":"Computers"},{"key":"4115_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2022.117174","volume":"201","author":"C Wang","year":"2021","unstructured":"Wang C, Shen Y, Ji L. Geometry attention transformer with position-aware LSTMs for image captioning. Expert Syst Appl. 2021;201:1\u201322. https:\/\/doi.org\/10.1016\/j.eswa.2022.117174.","journal-title":"Expert Syst Appl"},{"key":"4115_CR22","doi-asserted-by":"crossref","unstructured":"Wang Q, Huang W, Zhang X, Li X (2020) Word \u2013 Sentence Framework for Remote Sensing Image Captioning. IEEE Trans Geosci Remote Sens 59(12):1\u201312. https:\/\/scholar.google.com\/citations?user=uhC3hycAAAAJ&hl=en&oi=sra","DOI":"10.1109\/TGRS.2020.3044054"},{"issue":"9","key":"4115_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCSVT.2022.3155795","volume":"32","author":"T Xian","year":"2022","unstructured":"Xian T, Li Z, Tang Z, Ma H. Adaptive path selection for dynamic image captioning. IEEE Trans Circuits Syst Video Technol. 2022;32(9):1\u201315. https:\/\/doi.org\/10.1109\/TCSVT.2022.3155795.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4115_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/rs16214083","volume":"16","author":"Y Yang","year":"2024","unstructured":"Yang Y, Liu T, Pu Y, Liu L, Zhao Q, Wan Q. Remote sensing image change captioning using multi-attentive network with diffusion model. Remote Sens. 2024;16:1\u201318. https:\/\/doi.org\/10.3390\/rs16214083.","journal-title":"Remote Sens"},{"key":"4115_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3224244","volume":"60","author":"X Ye","year":"2022","unstructured":"Ye X, Wang S, Gu Y, Wang J, Wang R, Hou B, Giunchiglia F, Jiao L. A joint-training two-stage method for remote sensing image captioning. IEEE Trans Geosci Remote Sens. 2022;60:1\u201316. https:\/\/doi.org\/10.1109\/TGRS.2022.3224244.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"4115_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-021-10632-6","volume":"80","author":"Z Ye","year":"2021","unstructured":"Ye Z, Khan R, Naqvi N, Islam MS. A novel automatic image caption generation using bidirectional long-short term memory framework. Multimedia Tools Appl. 2021;80:1\u201326. https:\/\/doi.org\/10.1007\/s11042-021-10632-6.","journal-title":"Multimedia Tools Appl."},{"key":"4115_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMM.2021.3072479","volume":"24","author":"L Yu","year":"2021","unstructured":"Yu L, Zhang J, Wu Q. Dual attention on pyramid feature maps for image captioning. IEEE Trans Multimedia. 2021;24:1\u201312. https:\/\/doi.org\/10.1109\/TMM.2021.3072479.","journal-title":"IEEE Trans Multimedia"},{"key":"4115_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2021.115462","volume":"184","author":"J Zhang","year":"2021","unstructured":"Zhang J, Li K, Wang Z, Zhao X, Wang Z. Visual enhanced gLSTM for image captioning. Expert Syst Appl. 2021;184:1\u20139. https:\/\/doi.org\/10.1016\/j.eswa.2021.115462.","journal-title":"Expert Syst Appl"},{"issue":"10","key":"4115_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/e26100876","volume":"26","author":"F Zhao","year":"2024","unstructured":"Zhao F, Yu Z, Wang T, Lv Y. Image captioning based on semantic scenes. Entropy. 2024;26(10):1\u201320. https:\/\/doi.org\/10.3390\/e26100876.","journal-title":"Entropy"},{"key":"4115_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3070383","volume":"60","author":"R Zhao","year":"2021","unstructured":"Zhao R, Shi Z, Zou Z. High-resolution remote sensing image captioning based on structured attention. IEEE Trans Geosci Remote Sens. 2021;60:1\u201314. https:\/\/doi.org\/10.1109\/TGRS.2021.3070383.","journal-title":"IEEE Trans Geosci Remote Sens"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04115-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04115-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04115-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T08:01:06Z","timestamp":1751097666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04115-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,28]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["4115"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04115-w","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,28]]},"assertion":[{"value":"11 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 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":"No author has disclosed any conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"594"}}