{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T01:26:24Z","timestamp":1744161984801,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:00:00Z","timestamp":1649635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:00:00Z","timestamp":1649635200000},"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":["J Supercomput"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s11227-022-04474-8","type":"journal-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T05:02:51Z","timestamp":1649653371000},"page":"15042-15059","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Hybrid deep learning model for answering visual medical questions"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0138-2226","authenticated-orcid":false,"given":"Karim","family":"Gasmi","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,11]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"He X, Cai Z, Wei W, Zhang Y, Mou L, Xing E, Xie P (2021) Towards visual question answering on pathology images. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 708\u2013718","key":"4474_CR1","DOI":"10.18653\/v1\/2021.acl-short.90"},{"doi-asserted-by":"crossref","unstructured":"Demner-Fushman D, Lin JJ (2006) Answer extraction, semantic clustering, and extractive summarization for clinical question answering. In: ACL","key":"4474_CR2","DOI":"10.3115\/1220175.1220281"},{"doi-asserted-by":"crossref","unstructured":"Lin JJ, Katz B (2003) Question answering from the web using knowledge annotation and knowledge mining techniques. In: CIKM \u201903","key":"4474_CR3","DOI":"10.1145\/956863.956886"},{"doi-asserted-by":"crossref","unstructured":"Popescu A-M, Etzioni O, Kautz HA (2003) Towards a theory of natural language interfaces to databases. In: IUI \u201903","key":"4474_CR4","DOI":"10.1145\/604045.604120"},{"unstructured":"Rinaldi F, Dowdall J, Schneider G, Persidis A (2004) Answering questions in the genomics domain. In: ACL 2004","key":"4474_CR5"},{"unstructured":"Katz B (1997) From sentence processing to information access on the world wide web. In: AAAI Spring Symposium on Natural Language Processing for the World Wide Web, vol. 1, p. 997","key":"4474_CR6"},{"unstructured":"Lin Z, Zhang D, Tac Q, Shi D, Haffari G, Wu Q, He M, Ge Z (2021) Medical visual question answering: a survey. arXiv preprint arXiv:2111.10056","key":"4474_CR7"},{"unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL","key":"4474_CR8"},{"key":"4474_CR9","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1207\/s15516709cog0101_3","volume":"1","author":"WG Lehnert","year":"1977","unstructured":"Lehnert WG (1977) Human and computational question answering. Cogn Sci 1:47\u201373","journal-title":"Cogn Sci"},{"doi-asserted-by":"crossref","unstructured":"Do T, Nguyen BX, Tjiputra E, Tran M, Tran QD, Nguyen A (2021) Multiple meta-model quantifying for medical visual question answering. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 64\u201374. Springer","key":"4474_CR10","DOI":"10.1007\/978-3-030-87240-3_7"},{"doi-asserted-by":"crossref","unstructured":"Liu B, Zhan L-M, Xu L, Ma L, Yang Y, Wu X-M (2021) Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE","key":"4474_CR11","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"4474_CR12","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.compeleceng.2017.01.016","volume":"58","author":"A Gassara","year":"2017","unstructured":"Gassara A, Rodriguez IB, Jmaiel M, Drira K (2017) A bigraphical multi-scale modeling methodology for system of systems. Comput Electr Eng 58:113\u2013125","journal-title":"Comput Electr Eng"},{"unstructured":"Monceaux L, Robba I (2002) Les analyseurs syntaxiques : atouts pour une analyse des questions dans un syst\u00e8me de question-r\u00e9ponse ? In: JEPTALNRECITAL","key":"4474_CR13"},{"unstructured":"Mendes S, Moriceau V (2004) L\u2019analyse des questions: int\u00e9r\u00eats pour la g\u00e9n\u00e9ration des r\u00e9ponses. In: Workshop Question-Response","key":"4474_CR14"},{"doi-asserted-by":"crossref","unstructured":"Ferret O, Grau B, Hurault-Plantet M, Illouz G, Jacquemin C, Masson N, Lecuyer P (2000) Qalc\u2013the question-answering system of limsi-cnrs. In: TREC","key":"4474_CR15","DOI":"10.6028\/NIST.SP.500-249.qa-limsi"},{"unstructured":"Grau B, Ligozat A-L, Robba I, Vilnat A, Monceaux L (2006) Frasques: a question-answering system in the equer evaluation campaign. In: LREC 2006, p. 2006","key":"4474_CR16"},{"unstructured":"Laurent D, S\u00e9gu\u00e9la P (2005) Qristal, syst\u00e8me de questions-r\u00e9ponses. In: Actes de la 12\u00e8me Conf\u00e9rence sur Le Traitement Automatique des Langues Naturelles. Articles longs, pp. 51\u201360","key":"4474_CR17"},{"doi-asserted-by":"crossref","unstructured":"Benamara F (2004) Cooperative question answering in restricted domains: the webcoop experiment. In: Proceedings of the Conference on Question Answering in Restricted Domains, pp. 31\u201338","key":"4474_CR18","DOI":"10.3115\/1067737.1067749"},{"key":"4474_CR19","first-page":"7","volume":"33","author":"JS Teillaud","year":"2017","unstructured":"Teillaud JS (2017) medecine\/sciences 2017: the french touch des avanc\u00e9es des connaissances biom\u00e9dicales en... langue fran\u00e7aise. M S-Med Sci 33:7\u20138","journal-title":"M S-Med Sci"},{"issue":"2","key":"4474_CR20","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3917\/rfla.062.0047","volume":"6","author":"P Zweigenbaum","year":"2001","unstructured":"Zweigenbaum P (2001) Traitements automatiques de la terminologie m\u00e9dicale. Revue fran\u00e7aise de linguistique appliqu\u00e9e 6(2):47\u201362","journal-title":"Revue fran\u00e7aise de linguistique appliqu\u00e9e"},{"issue":"6","key":"4474_CR21","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1002\/cpe.3047","volume":"27","author":"N Khabou","year":"2015","unstructured":"Khabou N, Rodriguez IB (2015) Threshold-based context analysis approach for ubiquitous systems. Concurr Comput Pract Exp 27(6):1378\u20131390","journal-title":"Concurr Comput Pract Exp"},{"unstructured":"Malinowski M, Fritz M (2014) A multi-world approach to question answering about real-world scenes based on uncertain input. In: NIPS","key":"4474_CR22"},{"key":"4474_CR23","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-016-0966-6","volume":"123","author":"A Agrawal","year":"2015","unstructured":"Agrawal A, Lu J, Antol S, Mitchell M, Zitnick CL, Parikh D, Batra D (2015) Vqa: visual question answering. Int J Comput Vision 123:4\u201331","journal-title":"Int J Comput Vision"},{"doi-asserted-by":"crossref","unstructured":"Goyal, Y, Khot, T, Summers-Stay, D, Batra, D, Parikh, D. (2017) Making the v in vqa matter: Elevating the role of image understanding in visual question answering. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6325\u20136334","key":"4474_CR24","DOI":"10.1109\/CVPR.2017.670"},{"unstructured":"Frome, A, Corrado, G.S, Shlens, J, Bengio, S, Dean, J, Ranzato, M, Mikolov, T.: Devise: a deep visual-semantic embedding model. In: NIPS (2013)","key":"4474_CR25"},{"key":"4474_CR26","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Commun ACM 60:84\u201390","journal-title":"Commun ACM"},{"unstructured":"Mikolov, T, Chen, K, Corrado, G.S, Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)","key":"4474_CR27"},{"key":"4474_CR28","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2019","unstructured":"Wang L, Li Y, Huang J, Lazebnik S (2019) Learning two-branch neural networks for image-text matching tasks. IEEE Trans Pattern Anal Mach Intell 41:394\u2013407","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"doi-asserted-by":"crossref","unstructured":"Huang, Y, Wang, W, Wang, L.: Instance-aware image and sentence matching with selective multimodal lstm. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7254\u20137262 (2017)","key":"4474_CR29","DOI":"10.1109\/CVPR.2017.767"},{"doi-asserted-by":"crossref","unstructured":"Dong, X, Zhu, L, Zhang, D, Yang, Y, Wu, F (2018): Fast parameter adaptation for few-shot image captioning and visual question answering. Proceedings of the 26th ACM international conference on Multimedia","key":"4474_CR30","DOI":"10.1145\/3240508.3240527"},{"unstructured":"Mao J, Gan C, Kohli P, Tenenbaum JB, Wu J (2019) The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA","key":"4474_CR31"},{"unstructured":"Yi K, Wu J, Gan C, Torralba A, Kohli P, Tenenbaum JB (2018) Neural-symbolic vqa: disentangling reasoning from vision and language understanding. In: NeurIPS","key":"4474_CR32"},{"doi-asserted-by":"crossref","unstructured":"Nguyen BD, Do T-T, Nguyen BX, Do TK, Tjiputra E, Tran QD (2019) Overcoming data limitation in medical visual question answering. In: MICCAI","key":"4474_CR33","DOI":"10.1007\/978-3-030-32251-9_57"},{"doi-asserted-by":"crossref","unstructured":"Masci J, Meier U, Ciresan DC, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: ICANN","key":"4474_CR34","DOI":"10.1007\/978-3-642-21735-7_7"},{"unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML","key":"4474_CR35"},{"doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. In: Valstar MF, French AP, Pridmore TP (eds) British Machine Vision Conference, BMVC 2014. Nottingham, UK","key":"4474_CR36","DOI":"10.5244\/C.28.6"},{"unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Bengio, Y, LeCun, Y (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, Conference Track Proceedings","key":"4474_CR37"},{"doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 16 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770\u2013778","key":"4474_CR38","DOI":"10.1109\/CVPR.2016.90"},{"key":"4474_CR39","doi-asserted-by":"publisher","first-page":"156","DOI":"10.3390\/fi12090156","volume":"12","author":"A Ghourabi","year":"2020","unstructured":"Ghourabi A, Mahmood MA, Alzubi QM (2020) A hybrid cnn-lstm model for sms spam detection in Arabic and English messages. Future Internet 12:156","journal-title":"Future Internet"},{"doi-asserted-by":"crossref","unstructured":"Song M, Zhao X, Liu Y, Zhao Z (2018) Text sentiment analysis based on convolutional neural network and bidirectional lstm model. In: ICPCSEE","key":"4474_CR40","DOI":"10.1007\/978-981-13-2206-8_6"},{"doi-asserted-by":"crossref","unstructured":"Cui Z, Ke R, Pu Z, Wang Y (2020) Stacked bidirectional and unidirectional lstm recurrent neural network for forecasting network-wide traffic state with missing values. ArXiv","key":"4474_CR41","DOI":"10.1016\/j.trc.2020.102674"},{"unstructured":"Abacha AB, Hasan SA, Datla V, Liu J, Demner-Fushman D, M\u00fcller H (2019) Vqa-med: overview of the medical visual question answering task at imageclef 2019. In: CLEF","key":"4474_CR42"},{"doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: ACL","key":"4474_CR43","DOI":"10.3115\/1073083.1073135"},{"key":"4474_CR44","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1093\/bioinformatics\/btx238","volume":"33","author":"G Sogancioglu","year":"2017","unstructured":"Sogancioglu G, \u00d6zt\u00fcrk H, \u00d6zg\u00fcr A (2017) Biosses: a semantic sentence similarity estimation system for the biomedical domain. Bioinformatics 33:49\u201358","journal-title":"Bioinformatics"},{"doi-asserted-by":"crossref","unstructured":"Wu Z, Palmer MS (1994) Verb semantics and lexical selection. In: 32nd Annual Meeting of the Association for Computational Linguistics, New Mexico State University, pp. 133\u2013138","key":"4474_CR45","DOI":"10.3115\/981732.981751"},{"unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y. (Eds) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","key":"4474_CR46"},{"unstructured":"Duchi JC, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res","key":"4474_CR47"},{"unstructured":"Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop, coursera: Neural networks for machine learning. University of Toronto, Technical Report","key":"4474_CR48"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04474-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-022-04474-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04474-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T22:25:15Z","timestamp":1726957515000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-022-04474-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,11]]},"references-count":48,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["4474"],"URL":"https:\/\/doi.org\/10.1007\/s11227-022-04474-8","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2022,4,11]]},"assertion":[{"value":"19 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}