{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T23:05:59Z","timestamp":1772147159825,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-021-10632-6","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T23:10:27Z","timestamp":1618873827000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A novel automatic image caption generation using bidirectional long-short term memory framework"],"prefix":"10.1007","author":[{"given":"Zhongfu","family":"Ye","sequence":"first","affiliation":[]},{"given":"Rashid","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Nuzhat","family":"Naqvi","sequence":"additional","affiliation":[]},{"given":"M. Shujah","family":"Islam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"10632_CR1","doi-asserted-by":"crossref","unstructured":"Amritkar C, Jabade V (2018) Image caption generation using deep learning technique. IEEE 978\u20131\u20135386-5257-2\/18\/$31.00","DOI":"10.1109\/ICCUBEA.2018.8697360"},{"issue":"1","key":"10632_CR2","doi-asserted-by":"publisher","first-page":"102729","DOI":"10.1016\/j.dsp.2020.102729","volume":"4","author":"R Anuranji","year":"2020","unstructured":"Anuranji R, Srimathi H (2020) A supervised deep convolutional based bidirectional long short term memory video hashing for large scale video retrieval applications. Digital Signal Process 4(1):102729","journal-title":"Digital Signal Process"},{"key":"10632_CR3","doi-asserted-by":"crossref","unstructured":"Campi A, Guinea S, Spoletini P (2014) An operational semantics for XML fuzzy queries. eval (q, Ti) 1: 1","DOI":"10.5220\/0005155502050210"},{"issue":"3","key":"10632_CR4","first-page":"40","volume":"2","author":"SB Chandanapalli","year":"2019","unstructured":"Chandanapalli SB, Sreenivasa Reddy E, Rajya Lakshmi D (2019) Convolutional neural network for water quality prediction in WSN. J Network Commun Syst 2(3):40\u201347","journal-title":"J Network Commun Syst"},{"key":"10632_CR5","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.patrec.2018.12.018","volume":"132","author":"X Chen","year":"2020","unstructured":"Chen X, Zhang M, Wang Z, Zuo L, Li B, Yang Y (2020) Leveraging unpaired out-of-domain data for image captioning. Pattern Recogn Lett 132:132\u2013140","journal-title":"Pattern Recogn Lett"},{"key":"10632_CR6","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.cviu.2017.09.001","volume":"163","author":"G Christie","year":"2017","unstructured":"Christie G, Laddha A, Agrawal A, Antol S, Goyal Y, Kochersberger K, Batra D (2017) Resolving vision and language ambiguities together: Joint Segmentation & Prepositional Attachment Resolution in captioned scenes. Comput Vis Image Underst 163:101\u2013112","journal-title":"Comput Vis Image Underst"},{"key":"10632_CR7","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.jvcir.2018.05.008","volume":"55","author":"C Fan","year":"2018","unstructured":"Fan C, Zhang Z, Crandall DJ (2018) Deepdiary: Lifelogging image captioning and summarization. J Vis Commun Image Represent 55:40\u201355","journal-title":"J Vis Commun Image Represent"},{"issue":"4","key":"10632_CR8","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1109\/TPAMI.2012.118","volume":"35","author":"Y Feng","year":"2012","unstructured":"Feng Y, Lapata M (2012) Automatic caption generation for news images. IEEE Trans Pattern Anal Mach Intell 35(4):797\u2013812","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10632_CR9","unstructured":"George A, Rajakumar BR (2013) APOGA: An Adaptive Population Pool Size based Genetic Algorithm. AASRI Procedia - 2013 AASRI Conference on Intelligent Systems and Control,4, pp 288\u2013296."},{"key":"10632_CR10","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.image.2018.02.005","volume":"63","author":"J Guan","year":"2018","unstructured":"Guan J, Wang E (2018) Repeated review based image captioning for image evidence review. Signal Process Image Commun 63:141\u2013148","journal-title":"Signal Process Image Commun"},{"key":"10632_CR11","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2018.02.106","volume":"328","author":"X He","year":"2019","unstructured":"He X, Yang Y, Shi B, Bai X (2019) Vd-san: visual-densely semantic attention network for image caption generation. Neurocomputing 328:48\u201355","journal-title":"Neurocomputing"},{"key":"10632_CR12","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.patrec.2017.10.018","volume":"119","author":"X He","year":"2019","unstructured":"He X, Shi B, Bai X, Xia G-S, Zhang Z, Dong W (2019) Image caption generation with part of speech guidance. Pattern Recogn Lett 119:229\u2013237","journal-title":"Pattern Recogn Lett"},{"issue":"2","key":"10632_CR13","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/s11063-018-9836-2","volume":"49","author":"G Huang","year":"2018","unstructured":"Huang G, Hu H (2018) C-Rnn: a fine-grained language model for image captioning. Neural Process Lett 49(2):683\u2013691","journal-title":"Neural Process Lett"},{"issue":"7","key":"10632_CR14","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1016\/j.cviu.2012.03.002","volume":"116","author":"M Jamieson","year":"2012","unstructured":"Jamieson M, Eskin Y, Fazly A, Stevenson S, Dickinson SJ (2012) Discovering hierarchical object models from captioned images. Comput Vis Image Underst 116(7):842\u2013853","journal-title":"Comput Vis Image Underst"},{"issue":"3","key":"10632_CR15","doi-asserted-by":"publisher","first-page":"51","DOI":"10.3390\/a12030051","volume":"12","author":"Q Ji","year":"2019","unstructured":"Ji Q, Huang J, He W, Sun Y (2019) 'Optimized Deep Convolutional Neural Networks for Identification of Macular Diseases from Optical Coherence Tomography Images. Algorithms 12(3):51","journal-title":"Algorithms"},{"issue":"3","key":"10632_CR16","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1197\/jamia.M2945","volume":"16","author":"CE Kahn","year":"2009","unstructured":"Kahn CE, Rubin DL (2009) Automated semantic indexing of figure captions to improve radiology image retrieval. J Am Med Inform Assoc 16(3):380\u2013386","journal-title":"J Am Med Inform Assoc"},{"key":"10632_CR17","unstructured":"Karpathy A, Joulin A, Fei-Fei LF (2014) Deep fragment embeddings for bidirectional image sentence mapping. In advances in neural information processing systems (pp. 1889-1897)"},{"key":"10632_CR18","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1016\/j.neucom.2017.07.014","volume":"272","author":"P Kinghorn","year":"2018","unstructured":"Kinghorn P, Zhang L, Shao L (2018) A region-based image caption generator with refined descriptions. Neurocomputing 272:416\u2013424","journal-title":"Neurocomputing"},{"key":"10632_CR19","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.compind.2018.01.015","volume":"97","author":"Q Liu","year":"2018","unstructured":"Liu Q, Chen Y, Wang J, Zhang S (2018) Multi-view pedestrian captioning with an attention topic Cnn model. Comput Ind 97:47\u201353","journal-title":"Comput Ind"},{"issue":"2","key":"10632_CR20","doi-asserted-by":"publisher","first-page":"102178","DOI":"10.1016\/j.ipm.2019.102178","volume":"57","author":"M Liu","year":"2020","unstructured":"Liu M, Li L, Hu H, Guan W, Tian J (2020) Image Caption Generation with Dual Attention Mechanism. Inf Process Manag 57(2):102178","journal-title":"Inf Process Manag"},{"issue":"4","key":"10632_CR21","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","volume":"56","author":"X Lu","year":"2017","unstructured":"Lu X, Wang B, Zheng X, Li X (2017) Exploring models and data for remote sensing image caption generation. IEEE Trans Geosci Remote Sens 56(4):2183\u20132195","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"4","key":"10632_CR22","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1111\/apa.14574","volume":"108","author":"S Manti","year":"2019","unstructured":"Manti S, Parisi GF, Giacchi V, Sciacca P, Tardino L, Cuppari C, Salpietro C, Chikermane A, Leonardi S (2019) Pilot study shows right ventricular diastolic function impairment in young children with obstructive respiratory disease. Acta Paediatr 108(4):740\u2013744","journal-title":"Acta Paediatr"},{"key":"10632_CR23","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.knosys.2015.07.006","volume":"89","author":"S Mirjalili","year":"2015","unstructured":"Mirjalili S (2015) Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm. Knowl-Based Syst 89:228\u2013249","journal-title":"Knowl-Based Syst"},{"issue":"190","key":"10632_CR24","doi-asserted-by":"publisher","first-page":"102840","DOI":"10.1016\/j.cviu.2019.102840","volume":"1","author":"M Nabati","year":"2020","unstructured":"Nabati M, Behrad A (2020) Video captioning using boosted and parallel Long Short-Term Memory networks. Comput Vis Image Understand 1(190):102840","journal-title":"Comput Vis Image Understand"},{"key":"10632_CR25","doi-asserted-by":"crossref","unstructured":"Parisi GF, Herman T, van Meel ER, Ciet P, Kemner-van de Corput MP, Reiss IK, Jaddoe VWV, de Jongste JC, Tiddens HAWM, Duijts L (2017) Influence of early growth on childhood lung function assessed by magnetic resolution imaging and spirometry. The Generation R Study","DOI":"10.1183\/1393003.congress-2017.PA4154"},{"issue":"3","key":"10632_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.46253\/jcmps.v2i3.a1","volume":"2","author":"RK Poluru","year":"2019","unstructured":"Poluru RK, Lokesh Kumar R (2019) Enhancement of ATC by optimizing TCSC configuration using adaptive moth flame optimization algorithm. J Computation Mech Power Syst Control 2(3):1\u20139","journal-title":"J Computation Mech Power Syst Control"},{"key":"10632_CR27","doi-asserted-by":"crossref","unstructured":"Rajakumar BR (2013) Static and adaptive mutation techniques for genetic algorithm: a systematic comparative analysis. Int J Comput Sci Eng 8(2):180\u2013193","DOI":"10.1504\/IJCSE.2013.053087"},{"issue":"1","key":"10632_CR28","first-page":"11","volume":"10","author":"BR Rajakumar","year":"2013","unstructured":"Rajakumar BR (2013) Impact of static and adaptive mutation techniques on the performance of genetic algorithm. In J Hybrid Intell Syst 10(1):11\u201322","journal-title":"In J Hybrid Intell Syst"},{"key":"10632_CR29","unstructured":"Rajakumar BR, George A (2012) A New Adaptive Mutation Technique for Genetic Algorithm. In: proceedings of IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) pp1\u20137"},{"issue":"2","key":"10632_CR30","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MMUL.2018.112135923","volume":"25","author":"R Shetty","year":"2018","unstructured":"Shetty R, Tavakoli HR, Laaksonen J (2018) Image and video captioning with augmented neural architectures. IEEE MultiMedia 25(2):34\u201346","journal-title":"IEEE MultiMedia"},{"key":"10632_CR31","doi-asserted-by":"crossref","unstructured":"Swamy SM, Rajakumar BR, Valarmathi IR (2013) Design of Hybrid Wind and Photovoltaic Power System using Opposition-based Genetic Algorithm with Cauchy Mutation. IET Chennai Fourth International Conference on Sustainable Energy and Intelligent Systems, pp 504\u2013510","DOI":"10.1049\/ic.2013.0361"},{"key":"10632_CR32","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.neucom.2018.12.026","volume":"333","author":"YH Tan","year":"2019","unstructured":"Tan YH, Chan CS (2019) Phrase-based image caption generator with hierarchical Lstm network. Neurocomputing 333:86\u2013100","journal-title":"Neurocomputing"},{"key":"10632_CR33","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.image.2018.06.002","volume":"67","author":"C Wu","year":"2018","unstructured":"Wu C, Wei Y, Chu X, Su F, Wang L (2018) Modeling visual and word-conditional semantic attention for image captioning. Signal Process Image Commun 67:100\u2013107","journal-title":"Signal Process Image Commun"},{"issue":"6","key":"10632_CR34","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2018","unstructured":"Wu Q, Shen C, Wang P, Dick A, van den Hengel A (2018) Image captioning and visual question answering based on attributes and external knowledge. IEEE Trans Pattern Anal Mach Intell 40(6):1367\u20131381","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10632_CR35","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.jvcir.2018.12.027","volume":"58","author":"N Xu","year":"2019","unstructured":"Xu N, Liu A-A, Liu J, Nie W, Su Y (2019) Scene graph Captioner: image captioning based on structural visual representation. J Vis Commun Image Represent 58:477\u2013485","journal-title":"J Vis Commun Image Represent"},{"key":"10632_CR36","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.neucom.2018.10.059","volume":"330","author":"A Yuan","year":"2019","unstructured":"Yuan A, Li X, Lu X (2019) 3g structure for image caption generation. Neurocomputing 330:17\u201328","journal-title":"Neurocomputing"},{"key":"10632_CR37","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1016\/j.neucom.2018.11.004","volume":"329","author":"D Zhao","year":"2019","unstructured":"Zhao D, Chang Z, Guo S (2019) A multimodal fusion approach for image captioning. Neurocomputing 329:476\u2013485","journal-title":"Neurocomputing"},{"issue":"3","key":"10632_CR38","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1049\/iet-cvi.2018.5005","volume":"13","author":"H Zheng","year":"2018","unstructured":"Zheng H, Wu J, Liang R, Li Y, Li X (2018) Multi-task learning for captioning images with novel words. IET Comput Vis 13(3):294\u2013301","journal-title":"IET Comput Vis"},{"key":"10632_CR39","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.neucom.2019.04.099","volume":"390","author":"X Zhou","year":"2020","unstructured":"Zhou X, Lin J, Zhang Z, Shao Z, Chen S, Liu H (2020) Improved Itracker combined with bidirectional long short-term memory for 3d gaze estimation using appearance cues. Neurocomputing 390:217\u2013225","journal-title":"Neurocomputing"},{"key":"10632_CR40","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.neucom.2018.08.069","volume":"319","author":"X Zhu","year":"2018","unstructured":"Zhu X, Li L, Liu J, Li Z, Peng H, Niu X (2018) Image captioning with triple-attention and stack parallel Lstm. Neurocomputing 319:55\u201365","journal-title":"Neurocomputing"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10632-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-10632-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10632-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,20]],"date-time":"2021-04-20T00:07:29Z","timestamp":1618877249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-10632-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":40,"alternative-id":["10632"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10632-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,19]]},"assertion":[{"value":"28 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}