{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:34:38Z","timestamp":1775666078957,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"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":["Discov Artif Intell"],"DOI":"10.1007\/s44163-025-00315-8","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T07:18:50Z","timestamp":1748503130000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Image captioning using bidirectional LSTM neural network"],"prefix":"10.1007","volume":"5","author":[{"given":"Farnaz","family":"Hoseini","sequence":"first","affiliation":[]},{"given":"Anaram Yaghoobi","family":"Notash","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"key":"315_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241225","author":"P Zhang","year":"2023","unstructured":"Zhang P, Wang S, Wang M, Li J, Wang X, Kwong S. Rethinking semantic image compression: scalable representation with cross-modality transfer. IEEE Trans Circuits Syst Video Technol. 2023. https:\/\/doi.org\/10.1109\/TCSVT.2023.3241225.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"20","key":"315_CR2","doi-asserted-by":"publisher","first-page":"2875","DOI":"10.1080\/13683500.2020.1849052","volume":"24","author":"E Avraham","year":"2021","unstructured":"Avraham E. From 9\/11 through Katrina to Covid-19: crisis recovery campaigns for American destinations. Curr Issue Tour. 2021;24(20):2875\u201389.","journal-title":"Curr Issue Tour"},{"key":"315_CR3","doi-asserted-by":"publisher","first-page":"101759","DOI":"10.1016\/j.media.2020.101759","volume":"65","author":"D Karimi","year":"2020","unstructured":"Karimi D, Dou H, Warfield SK, Gholipour A. Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. Med Image Anal. 2020;65:101759.","journal-title":"Med Image Anal"},{"key":"315_CR4","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/978-3-030-27544-0_13","volume-title":"RoboCup 2018: Robot World Cup XXII 22","author":"N Fiedler","year":"2019","unstructured":"Fiedler N, Bestmann M, Hendrich N. Imagetagger: an open source online platform for collaborative image labeling. In: Holz D, Genter K, Saad M, von Stryk O, editors. RoboCup 2018: Robot World Cup XXII 22. Cham: Springer International Publishing; 2019. p. 162\u20139."},{"key":"315_CR5","doi-asserted-by":"crossref","unstructured":"Zhang Y, Ling H, Gao J, Yin K, Lafleche JF, Barriuso A., Fidler S. Datasetgan: Efficient labeled data factory with minimal human effort. In\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021; 10145\u201310155.","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"315_CR6","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/9658350","author":"A Latif","year":"2019","unstructured":"Latif A, Rasheed A, Sajid U, Ahmed J, Ali N, Ratyal NI, Khalil T. Content-based image retrieval and feature extraction: a comprehensive review. Math Probl Eng. 2019. https:\/\/doi.org\/10.1155\/2019\/9658350.","journal-title":"Math Probl Eng"},{"issue":"2","key":"315_CR7","first-page":"897","volume":"19","author":"X Liao","year":"2020","unstructured":"Liao X, Yin J, Chen M, Qin Z. Adaptive payload distribution in multiple images steganography based on image texture features. IEEE Trans Dependable Secure Comput. 2020;19(2):897\u2013911.","journal-title":"IEEE Trans Dependable Secure Comput"},{"issue":"2","key":"315_CR8","doi-asserted-by":"publisher","first-page":"901","DOI":"10.3390\/su15020901","volume":"15","author":"N Mamat","year":"2023","unstructured":"Mamat N, Othman MF, Abdulghafor R, Alwan AA, Gulzar Y. Enhancing image annotation technique of fruit classification using a deep learning approach. Sustainability. 2023;15(2):901.","journal-title":"Sustainability"},{"key":"315_CR9","doi-asserted-by":"crossref","unstructured":"Chang CM, Mishra SD, Igarashi T. A hierarchical task assignment for manual image labeling. In\u00a02019 IEEE Symposium on Visual Languages and Human-Centric Computing (VL\/HCC). IEEE. 2019, October ; 139\u2013143","DOI":"10.1109\/VLHCC.2019.8818828"},{"issue":"6","key":"315_CR10","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.3390\/s22062188","volume":"22","author":"MM Monowar","year":"2022","unstructured":"Monowar MM, Hamid MA, Ohi AQ, Alassafi MO, Mridha MF. AutoRet: A self-supervised spatial recurrent network for content-based image retrieval. Sensors. 2022;22(6):2188.","journal-title":"Sensors"},{"key":"315_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106771","volume":"215","author":"G Algan","year":"2021","unstructured":"Algan G, Ulusoy I. Image classification with deep learning in the presence of noisy labels: a survey. Knowl-Based Syst. 2021;215: 106771.","journal-title":"Knowl-Based Syst"},{"key":"315_CR12","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5008854","author":"W Alsabhan","year":"2022","unstructured":"Alsabhan W, Alotaiby T. Automatic building extraction on satellite images using Unet and ResNet50. Comput Intell Neurosci. 2022. https:\/\/doi.org\/10.1155\/2022\/5008854.","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"315_CR13","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s40745-021-00344-x","volume":"10","author":"A Kurani","year":"2023","unstructured":"Kurani A, Doshi P, Vakharia A, Shah M. A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting. Ann Data Sci. 2023;10(1):183\u2013208.","journal-title":"Ann Data Sci"},{"issue":"2","key":"315_CR14","doi-asserted-by":"publisher","first-page":"106041","DOI":"10.1016\/j.isci.2023.106041","volume":"26","author":"S Hilliard","year":"2023","unstructured":"Hilliard S, Mosoyan K, Branciamore S, Gogoshin G, Zhang A, Simons DL, Rodin AS. Bow-tie architectures in biological and artificial neural networks: Implications for network evolution and assay design. Iscience. 2023;26(2):106041.","journal-title":"Iscience"},{"key":"315_CR15","doi-asserted-by":"publisher","first-page":"102075","DOI":"10.1016\/j.csite.2022.102075","volume":"34","author":"J Garc\u00eda-Morales","year":"2022","unstructured":"Garc\u00eda-Morales J, Cervantes-Bobadilla M, Hern\u00e1ndez-P\u00e9rez JA, Saavedra-Ben\u00edtez YI, Adam-Medina M, Guerrero-Ram\u00edrez GV. Inverse artificial neural network control design for a double tube heat exchanger. Case Stud Therm Eng. 2022;34:102075.","journal-title":"Case Stud Therm Eng"},{"key":"315_CR16","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/11171.001.0001","volume-title":"Deep learning","author":"JD Kelleher","year":"2019","unstructured":"Kelleher JD. Deep learning. Cambridge: MIT press; 2019."},{"key":"315_CR17","doi-asserted-by":"crossref","unstructured":"Albawi S, Mohammed TA, Al-Zawi S. Understanding of a convolutional neural network. In\u00a02017 international conference on engineering and technology (ICET). Ieee. 2017, August; 1\u20136.","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"315_CR18","doi-asserted-by":"crossref","unstructured":"Qi X., Wang T., Liu J. Comparison of support vector machine and softmax classifiers in computer vision. In\u00a02017 Second International Conference on Mechanical, Control and Computer Engineering (ICMCCE). IEEE. 2017, December; 151\u2013155.","DOI":"10.1109\/ICMCCE.2017.49"},{"key":"315_CR19","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D. 2020;404:132306.","journal-title":"Physica D"},{"key":"315_CR20","doi-asserted-by":"publisher","first-page":"109686","DOI":"10.1016\/j.petrol.2021.109686","volume":"208","author":"R Huang","year":"2022","unstructured":"Huang R, Wei C, Wang B, Yang J, Xu X, Wu S, Huang S. Well performance prediction based on Long Short-Term Memory (LSTM) neural network. J Petrol Sci Eng. 2022;208:109686.","journal-title":"J Petrol Sci Eng"},{"key":"315_CR21","doi-asserted-by":"crossref","unstructured":"Srikanth M, Varner J, Bowden M, Moldovan D. Exploiting ontologies for automatic image annotation. In\u00a0Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval. 2005, August; 552\u2013558","DOI":"10.1145\/1076034.1076128"},{"issue":"6","key":"315_CR22","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84\u201390.","journal-title":"Commun ACM"},{"key":"315_CR23","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation.\u00a0arXiv preprint. 2014. arXiv:1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"key":"315_CR24","unstructured":"Kiros R, Salakhutdinov R, Zemel R. Multimodal neural language models. In\u00a0International conference on machine learning. PMLR. 2014, June; 595\u2013603."},{"issue":"4","key":"315_CR25","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2016","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D. Show and tell: Lessons learned from the 2015 mscoco image captioning challenge. IEEE Trans Pattern Anal Mach Intell. 2016;39(4):652\u201363.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"315_CR26","doi-asserted-by":"crossref","unstructured":"Jia X, Gavves E, Fernando B, Tuytelaars T. Guiding the long-short term memory model for image caption generation. In\u00a0Proceedings of the IEEE international conference on computer vision. 2015; 2407\u20132415.","DOI":"10.1109\/ICCV.2015.277"},{"key":"315_CR27","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Qiu Z, Mei T. Boosting image captioning with attributes. In\u00a0Proceedings of the IEEE international conference on computer vision. 2017; 4894\u20134902.","DOI":"10.1109\/ICCV.2017.524"},{"key":"315_CR28","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J. Image captioning with semantic attention. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 4651\u20134659.","DOI":"10.1109\/CVPR.2016.503"},{"issue":"12","key":"315_CR29","doi-asserted-by":"publisher","first-page":"6025","DOI":"10.1109\/TIP.2018.2864920","volume":"27","author":"L Song","year":"2018","unstructured":"Song L, Liu J, Qian B, Sun M, Yang K, Sun M, Abbas S. A deep multi-modal CNN for multi-instance multi-label image classification. IEEE Trans Image Process. 2018;27(12):6025\u201338.","journal-title":"IEEE Trans Image Process"},{"issue":"2s","key":"315_CR30","first-page":"1","volume":"14","author":"C Wang","year":"2018","unstructured":"Wang C, Yang H, Meinel C. Image captioning with deep bidirectional LSTMs and multi-task learning. ACM Trans Multimedia Comput Commun Appl (TOMM). 2018;14(2s):1\u201320.","journal-title":"ACM Trans Multimedia Comput Commun Appl (TOMM)"},{"key":"315_CR31","doi-asserted-by":"crossref","unstructured":"Gu J, Cai J, Wang G, Chen T. Stack-captioning: Coarse-to-fine learning for image captioning. In\u00a0Proceedings of the AAAI conference on artificial intelligence. 2018, April; 32(1).","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"315_CR32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3539344","author":"J Zhang","year":"2025","unstructured":"Zhang J, Zhang K, Xie Y, Wang Z. Deep reciprocal learning for image captioning. IEEE Trans Circuits Syst Video Technol. 2025. https:\/\/doi.org\/10.1109\/TCSVT.2025.3539344.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"315_CR33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3525158","author":"AA Liu","year":"2025","unstructured":"Liu AA, Wu Q, Xu N, Tian H, Wang L. Enriched image captioning based on knowledge divergence and focus. IEEE Trans Circuits Syst Video Technol. 2025. https:\/\/doi.org\/10.1109\/TCSVT.2024.3525158.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"315_CR34","doi-asserted-by":"publisher","first-page":"110077","DOI":"10.1016\/j.compeleceng.2025.110077","volume":"123","author":"I Al Badarneh","year":"2025","unstructured":"Al Badarneh I, Hammo BH, Al-Kadi O. An ensemble model with attention based mechanism for image captioning. Comput Electr Eng. 2025;123:110077.","journal-title":"Comput Electr Eng"},{"key":"315_CR35","doi-asserted-by":"publisher","first-page":"117273","DOI":"10.1016\/j.image.2025.117273","volume":"133","author":"MJ Parseh","year":"2025","unstructured":"Parseh MJ, Ghadiri S. Graph-based image captioning with semantic and spatial features. Signal Process Image Commun. 2025;133:117273.","journal-title":"Signal Process Image Commun"},{"issue":"9","key":"315_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3671000","volume":"20","author":"C Cai","year":"2025","unstructured":"Cai C, Yap KH, Wang S. Toward attribute-controlled fashion image captioning. ACM Trans Multimed Comput Commun Appl. 2025;20(9):1\u201318.","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"315_CR37","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/978-3-031-55048-5_6","volume-title":"Reliability engineering for industrial processes: an analytics perspective","author":"P Singh","year":"2024","unstructured":"Singh P, Raja F, Sharma H. Generating image captions in hindi based on encoder-decoder based deep learning techniques. In: Kapur PK, Pham H, Singh G, Kumar V, editors. Reliability engineering for industrial processes: an analytics perspective. Cham: Springer Nature Switzerland; 2024. p. 81\u201394."},{"key":"315_CR38","first-page":"301","volume-title":"International conference on data science and network engineering","author":"P Singh","year":"2023","unstructured":"Singh P, Agrawal C, Bansal R. Performance Analysis of Image Caption Generation Techniques Using CNN-Based Encoder\u2013Decoder Architecture. In: Namasudra S, Trivedi MC, Crespo RG, Lorenz P, editors. International conference on data science and network engineering. Singapore: Springer Nature Singapore; 2023. p. 301\u201313."},{"key":"315_CR39","doi-asserted-by":"crossref","unstructured":"Singh P, Gupta P, Jain H. A comparative study of machine learning based image captioning models. In\u00a02022 6th international conference on trends in electronics and informatics (ICOEI). IEEE. 2022, April; 1555\u20131560.","DOI":"10.1109\/ICOEI53556.2022.9777153"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00315-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-025-00315-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00315-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T19:02:32Z","timestamp":1748545352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-025-00315-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,29]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["315"],"URL":"https:\/\/doi.org\/10.1007\/s44163-025-00315-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5293120\/v1","asserted-by":"object"}]},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,29]]},"assertion":[{"value":"19 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"80"}}