{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:22:48Z","timestamp":1772119368048,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Thu Dau Mot University, Binh Duong, Vietnam"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00500-023-09100-0","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T07:02:37Z","timestamp":1692687757000},"page":"14647-14658","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A novel deep fuzzy neural network semantic-enhanced method for automatic image captioning"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7291-4168","authenticated-orcid":false,"given":"Tham","family":"Vo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,22]]},"reference":[{"key":"9100_CR1","doi-asserted-by":"crossref","unstructured":"Antol S, Agrawal A, Lu J, Mitchell M, Batra D, Zitnick CL, Parikh D (2015) Vqa: Visual question answering. In: Proceedings of the IEEE international conference on computer vision","DOI":"10.1109\/ICCV.2015.279"},{"key":"9100_CR2","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR"},{"issue":"4","key":"9100_CR3","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1109\/TFUZZ.2016.2574915","volume":"25","author":"Y Deng","year":"2016","unstructured":"Deng Y, Ren Z, Kong Y, Bao F, Dai Q (2016) A hierarchical fused fuzzy deep neural network for data classification. IEEE Trans Fuzzy Syst 25(4):1006\u20131012","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"9100_CR4","unstructured":"Devlin J, Gupta S, Girshick R, Mitchell M, Zitnick CL (2015) Exploring nearest neighbor approaches for image captioning, arXiv preprint arXiv:1505.04467"},{"key":"9100_CR5","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"9100_CR6","doi-asserted-by":"crossref","unstructured":"Fang F, Wang H, Tang P (2018) Image captioning with word level attention. In: 25th IEEE International Conference on Image Processing (ICIP)","DOI":"10.1109\/ICIP.2018.8451558"},{"key":"9100_CR7","doi-asserted-by":"crossref","unstructured":"Gan Z, Gan C, He X, Pu Y, Tran K, Gao J, Deng L (2017) Semantic compositional networks for visual captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.127"},{"issue":"7","key":"9100_CR8","doi-asserted-by":"publisher","first-page":"5411","DOI":"10.1007\/s00500-020-05539-7","volume":"25","author":"D Han","year":"2021","unstructured":"Han D, Zhou S, Li KC, de Mello RF (2021) Cross-modality co-attention networks for visual question answering. Soft Comput 25(7):5411\u20135421","journal-title":"Soft Comput"},{"key":"9100_CR9","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.90"},{"key":"9100_CR10","doi-asserted-by":"crossref","unstructured":"Huang L, Wang W, Chen J, Wei XY (2019) Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV.2019.00473"},{"key":"9100_CR11","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"18","key":"9100_CR12","doi-asserted-by":"publisher","first-page":"8827","DOI":"10.1007\/s00500-018-3482-5","volume":"23","author":"GU Kaya","year":"2019","unstructured":"Kaya GU, Erkaymaz O, Sarac Z (2019) A new adaptive neuro-fuzzy solution for optimization of the parameters in the digital holography setup. Soft Comput 23(18):8827\u20138837","journal-title":"Soft Comput"},{"issue":"12","key":"9100_CR13","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni G, Premraj V, Ordonez V, Dhar S, Li S, Choi Y, Berg TL (2013) Babytalk: understanding and generating simple image descriptions. IEEE Trans Pattern Anal Mach Intell 35(12):2891\u20132903","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9100_CR14","unstructured":"Lebret R, Pinheiro P, Collobert R (2015) Phrase-based image captioning. In: International Conference on Machine Learning (PMLR)"},{"issue":"5","key":"9100_CR15","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1109\/91.963761","volume":"9","author":"FJ Lin","year":"2001","unstructured":"Lin FJ, Lin CH, Shen PH (2001) Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive. IEEE Trans Fuzzy Syst 9(5):751\u2013759","journal-title":"IEEE Trans Fuzzy Syst"},{"issue":"1","key":"9100_CR16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/TFUZZ.2005.861604","volume":"14","author":"CT Lin","year":"2006","unstructured":"Lin CT, Yeh CM, Liang SF, Chung JF, Kumar N (2006) Support-vector-based fuzzy neural network for pattern classification. IEEE Trans Fuzzy Syst 14(1):31\u201341","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"9100_CR17","doi-asserted-by":"crossref","unstructured":"Manning CD, Surdeanu M, Bauer J, Finkel JR, Bethard S, McClosky D (2014) The Stanford CoreNLP natural language processing toolkit. In: Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations","DOI":"10.3115\/v1\/P14-5010"},{"key":"9100_CR18","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations (ICRL)"},{"key":"9100_CR19","unstructured":"Mikolov T, Grave \u00c9, Bojanowski P, Puhrsch C, Joulin A (2018) Advances in Pre-Training Distributed Word Representations. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation"},{"key":"9100_CR20","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","DOI":"10.3115\/v1\/D14-1162"},{"key":"9100_CR21","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems"},{"key":"9100_CR22","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2017.131"},{"key":"9100_CR23","doi-asserted-by":"crossref","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition","DOI":"10.1109\/ICCV.2015.314"},{"key":"9100_CR24","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to Sequence Learning with Neural Networks. In: Advances in Neural Information Processing Systems"},{"issue":"3","key":"9100_CR25","doi-asserted-by":"publisher","first-page":"2165","DOI":"10.1007\/s00500-020-05288-7","volume":"25","author":"S Tu","year":"2021","unstructured":"Tu S, Ur Rehman S, Waqas M, Ur Rehman O, Shah Z, Yang Z, Koubaa A (2021) ModPSO-CNN: an evolutionary convolution neural network with application to visual recognition. Soft Comput 25(3):2165\u20132176","journal-title":"Soft Comput"},{"key":"9100_CR26","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: A neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"9100_CR27","doi-asserted-by":"crossref","unstructured":"Wang C, Yang H, Bartz C, Meinel C (2016) Image captioning with deep bidirectional LSTMs. In: Proceedings of the 24th ACM international conference on Multimedia, pp. 988\u2013997","DOI":"10.1145\/2964284.2964299"},{"key":"9100_CR28","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J, You Q, Jin H, Wang Z, Fang C, Luo J (2016) In: Proceedings of the IEEE conference on computer vision and pattern recognition"},{"issue":"6","key":"9100_CR29","doi-asserted-by":"publisher","first-page":"2743","DOI":"10.1109\/TIP.2018.2889922","volume":"28","author":"N Yu","year":"2018","unstructured":"Yu N, Hu X, Song B, Yang J, Zhang J (2018) Topic-oriented image captioning based on order-embedding. IEEE Trans Image Process 28(6):2743\u20132754","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"9100_CR30","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1007\/s00500-019-03973-w","volume":"24","author":"H Zhang","year":"2020","unstructured":"Zhang H, Qiu D, Wu R, Ji D, Li G, Niu Z, Li T (2020) Novel model to integrate word embeddings and syntactic trees for automatic caption generation from images. Soft Comput 24(2):1377\u20131397","journal-title":"Soft Comput"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-09100-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-023-09100-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-09100-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T11:14:58Z","timestamp":1729941298000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-023-09100-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,22]]},"references-count":30,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["9100"],"URL":"https:\/\/doi.org\/10.1007\/s00500-023-09100-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-610265\/v1","asserted-by":"object"}]},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,22]]},"assertion":[{"value":"3 August 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 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":"Dr. Tham Vo has received a research grant from Nguyen Tat Thanh University, Ho Chi Minh City, Vietnam. She and the remaining authors have no other conflicts of interest or financial ties.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}