{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:17:40Z","timestamp":1780586260790,"version":"3.54.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T00:00:00Z","timestamp":1684713600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T00:00:00Z","timestamp":1684713600000},"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":["Soft Comput"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00500-023-08448-7","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T15:01:43Z","timestamp":1684767703000},"page":"14205-14218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A novel method for image captioning using multimodal feature fusion employing mask RNN and LSTM models"],"prefix":"10.1007","volume":"27","author":[{"given":"Kumaravel","family":"Thangavel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natesan","family":"Palanisamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9156-2054","authenticated-orcid":false,"given":"Suresh","family":"Muthusamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5158-4857","authenticated-orcid":false,"given":"Om Prava","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7929-1194","authenticated-orcid":false,"given":"Suma Christal Mary","family":"Sundararajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3787-9712","authenticated-orcid":false,"given":"Hitesh","family":"Panchal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashok Kumar","family":"Loganathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7309-3138","authenticated-orcid":false,"given":"Ponarun","family":"Ramamoorthi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,22]]},"reference":[{"issue":"11","key":"8448_CR1","first-page":"229","volume":"9","author":"AG Chavan","year":"2021","unstructured":"Chavan AG, Rajpurohit K, Singh A, Kumar R, Bhonsle M (2021) Image captioning model for mobile app. IJCRT 9(11):229\u2013231","journal-title":"IJCRT"},{"key":"8448_CR2","doi-asserted-by":"publisher","unstructured":"Degadwala S, Vyas D, Biswas H, Chakraborty U, Saha S (2021) Image captioning using inception V3 transfer learning model. 2021 6th Int Conf Commun Electr Syst (ICCES), pp 1103\u20131108, https:\/\/doi.org\/10.1109\/ICCES51350.2021.9489111.","DOI":"10.1109\/ICCES51350.2021.9489111"},{"key":"8448_CR4","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1007\/s12559-022-10033-3","volume":"14","author":"S Fouladi","year":"2022","unstructured":"Fouladi S, Safaei AA, Mammone N et al (2022a) Efficient deep neural networks for classification of alzheimer\u2019s disease and mild cognitive impairment from scalp EEG recordings. CognComput 14:1247\u20131268. https:\/\/doi.org\/10.1007\/s12559-022-10033-3","journal-title":"CognComput"},{"key":"8448_CR3","doi-asserted-by":"publisher","first-page":"37681","DOI":"10.1007\/s11042-022-13506-7","volume":"81","author":"S Fouladi","year":"2022","unstructured":"Fouladi S, Safaei AA, Arshad NI et al (2022b) The use of artificial neural networks to diagnose Alzheimer\u2019s disease from brain images. Multimed Tools Appl 81:37681\u201337721. https:\/\/doi.org\/10.1007\/s11042-022-13506-7","journal-title":"Multimed Tools Appl"},{"key":"8448_CR5","doi-asserted-by":"publisher","unstructured":"Funckes N, Carrier E and Wolffe G (2021) An augmented image captioning model: incorporating hierarchical image information. 2021 20th IEEE Int Conf Mach Learn Appl (ICMLA), 2021, pp. 1608\u20131614, https:\/\/doi.org\/10.1109\/ICMLA52953.2021.00257","DOI":"10.1109\/ICMLA52953.2021.00257"},{"key":"8448_CR6","unstructured":"Gao J, Zhou Y, Yu P, & Gu J. (2020). Unsupervised cross-lingual image captioning.\u00a0ArXiv, abs\/2010.01288."},{"key":"8448_CR7","doi-asserted-by":"publisher","unstructured":"Gupta SC, Singh NR, Sharma T, Tyagi A and Majumda R (2021) generating image captions using deep learning and natural language processing. 2021 9th Int Conf Reliabil Infocom Technol Optim (Trends and Future Directions) (ICRITO), pp. 1\u20134, doi: https:\/\/doi.org\/10.1109\/ICRITO51393.2021.9596486.","DOI":"10.1109\/ICRITO51393.2021.9596486"},{"issue":"2","key":"8448_CR8","doi-asserted-by":"publisher","first-page":"163","DOI":"10.3390\/met10020163","volume":"10","author":"E Javaheri","year":"2020","unstructured":"Javaheri E, Kumala V, Javaheri A, Rawassizadeh R, Lubritz J, Graf B, Rethmeier M (2020) Quantifying mechanical properties of automotive steels with deep learning based computer vision algorithms. Metals 10(2):163. https:\/\/doi.org\/10.3390\/met10020163","journal-title":"Metals"},{"key":"8448_CR9","doi-asserted-by":"publisher","unstructured":"Lu Y, Guo C, Dai X and Wang YF (2021) Image Captioning on Fine Art Paintings via Virtual Paintings. 2021 IEEE 1st Int Conf Digital Twins Parallel Intell (DTPI), 2021, pp. 156\u2013159, https:\/\/doi.org\/10.1109\/DTPI52967.2021.9540081.","DOI":"10.1109\/DTPI52967.2021.9540081"},{"key":"8448_CR10","unstructured":"Mahmoudi, A. (2020). Water and wastewater industry and energy management."},{"key":"8448_CR11","doi-asserted-by":"crossref","unstructured":"Nejatishahidin, N., Fayyazsanavi, P., & Kosecka, J. (2022). Object pose estimation using mid-level visual representations. ArXiv, abs\/2203.01449.","DOI":"10.1109\/IROS47612.2022.9981452"},{"key":"8448_CR12","doi-asserted-by":"publisher","first-page":"635","DOI":"10.37394\/23203.2020.15.63","volume":"15","author":"M Nivedita","year":"2020","unstructured":"Nivedita M, Asnathvictyphamila Y (2020) A survey on different deep learning architectures for image captioning. WSEAS Trans Syst Control 15:635\u2013646","journal-title":"WSEAS Trans Syst Control"},{"key":"8448_CR13","doi-asserted-by":"publisher","unstructured":"Puscasiu A, Fanca A, Gota D-I.and Valean H, (2020) Automated image captioning. 2020 IEEE Intl Conf Autom, Quality Test Robot (AQTR), 2020, pp 1\u20136, https:\/\/doi.org\/10.1109\/AQTR49680.2020.9129930.","DOI":"10.1109\/AQTR49680.2020.9129930"},{"key":"8448_CR14","unstructured":"Rane P, Sargar AM, & Shaikh F (2018). Self-critical sequence training for image captioning. IJRESM. Vol.1, No.9, pp: 234\u2013238"},{"key":"8448_CR15","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1109\/ICSSIT48917.2020.9214109","volume":"2020","author":"SS Rawat","year":"2020","unstructured":"Rawat SS, Rawat KS, Nijhawan R (2020) A novel convolutional neural network-gated recurrent unit approach for image captioning. Third Int Conf Smart Syst Inv Technol (ICSSIT) 2020:704\u2013708. https:\/\/doi.org\/10.1109\/ICSSIT48917.2020.9214109","journal-title":"Third Int Conf Smart Syst Inv Technol (ICSSIT)"},{"issue":"1","key":"8448_CR16","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1080\/02522667.2020.1715602","volume":"41","author":"Saloni Kalra & Alka Leekha","year":"2020","unstructured":"Saloni Kalra & Alka Leekha (2020) Survey of convolutional neural networks for image captioning. J Inf Optim Sci 41(1):239\u2013260. https:\/\/doi.org\/10.1080\/02522667.2020.1715602","journal-title":"J Inf Optim Sci"},{"key":"8448_CR17","first-page":"325","volume":"2020","author":"H Sharma","year":"2020","unstructured":"Sharma H, Agrahari M, Singh SK, Firoj M, Mishra RK (2020) Image captioning: a comprehensive survey. Int Conf Power Electr IoT Appl Renew Energy Control (PARC) 2020:325\u2013328","journal-title":"Int Conf Power Electr IoT Appl Renew Energy Control (PARC)"},{"issue":"4","key":"8448_CR18","first-page":"222","volume":"8","author":"NN Shinde","year":"2020","unstructured":"Shinde NN, Gawde N, Paradkar N (2020a) Social media image caption generation using deep learning. Int J Eng Develop Res 8(4):222\u2013228","journal-title":"Int J Eng Develop Res"},{"key":"8448_CR19","unstructured":"Shinde, D.V., Dave, M.P., Singh, A., & Dubey, A.C. (2020b). Image caption generator using big data and machine learning. Vol.7, No.4, pp: 6197\u20136201"},{"key":"8448_CR20","doi-asserted-by":"publisher","first-page":"01","DOI":"10.1109\/SSCI50451.2021.9659834","volume":"2021","author":"IR Turkerud","year":"2021","unstructured":"Turkerud IR, Mengshoel OJ (2021) Image captioning using deep learning: text augmentation by paraphrasing via backtranslation. IEEE Symp Ser Comput Intell (SSCI) 2021:01\u201310. https:\/\/doi.org\/10.1109\/SSCI50451.2021.9659834","journal-title":"IEEE Symp Ser Comput Intell (SSCI)"},{"key":"8448_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2543-5_10","volume-title":"Computational intelligence in pattern recognition","author":"P Waghmare","year":"2022","unstructured":"Waghmare P, Shinde S (2022) Image Caption Generation Using neural network models and LSTM hierarchical structure. In: Das AK, Nayak J, Naik B, Dutta S, Pelusi D (eds) Computational intelligence in pattern recognition. Advances in Intelligent Systems and Computing, Springer, Singapore. https:\/\/doi.org\/10.1007\/978-981-16-2543-5_10"},{"key":"8448_CR22","doi-asserted-by":"publisher","unstructured":"YV SS, Choubey Y and Naik D, (2021) Image captioning with attention based model.\u00a02021 5th Int Conf Comput Methodol Commun (ICCMC), pp. 1051\u20131055, https:\/\/doi.org\/10.1109\/ICCMC51019.2021.9418347.","DOI":"10.1109\/ICCMC51019.2021.9418347"},{"key":"8448_CR23","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1007\/s00542-019-04473-5","volume":"27","author":"Z Zeng","year":"2021","unstructured":"Zeng Z, Li X (2021) Application of human computing in image captioning under deep learning. MicrosystTechnol 27:1687\u20131692. https:\/\/doi.org\/10.1007\/s00542-019-04473-5","journal-title":"MicrosystTechnol"},{"key":"8448_CR24","first-page":"14810","volume":"2021","author":"D Zhao","year":"2021","unstructured":"Zhao D, Wang A, Russakovsky O (2021) Understanding and evaluating racial biases in image captioning. IEEE\/CVF Int Conf Comput vis (ICCV) 2021:14810\u201314820","journal-title":"IEEE\/CVF Int Conf Comput vis (ICCV)"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-08448-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-023-08448-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-08448-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T17:12:29Z","timestamp":1692897149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-023-08448-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,22]]},"references-count":24,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8448"],"URL":"https:\/\/doi.org\/10.1007\/s00500-023-08448-7","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,22]]},"assertion":[{"value":"3 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have not disclosed any competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}