{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:19:57Z","timestamp":1792783197131,"version":"4.5.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T00:00:00Z","timestamp":1632441600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T00:00:00Z","timestamp":1632441600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Nanjing Institute of Technology High-level Scientific Research Foundation for the introduction of talent","award":["YKJ201918"],"award-info":[{"award-number":["YKJ201918"]}],"id":[{"id":"https:\/\/ror.org\/00n6txq60","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["No.20KJB510049"],"award-info":[{"award-number":["No.20KJB510049"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61902179"],"award-info":[{"award-number":["No.61902179"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s00521-021-06557-8","type":"journal-article","created":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T12:53:16Z","timestamp":1632487996000},"page":"2207-2216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A topic-based multi-channel attention model under hybrid mode for image caption"],"prefix":"10.1007","volume":"34","author":[{"given":"Kui","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,24]]},"reference":[{"issue":"11","key":"6557_CR1","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao ZQ, Zheng P, Xu ST, Wu X (2019) Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst 30(11):3212\u20133232","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6557_CR2","doi-asserted-by":"publisher","first-page":"102601","DOI":"10.1016\/j.bspc.2021.102601","volume":"68","author":"\u015e \u00d6zt\u00fcrk","year":"2021","unstructured":"\u00d6zt\u00fcrk \u015e (2021) Class-driven content-based medical image retrieval using hash codes of deep features. Biomed Signal Process Control 68:102601","journal-title":"Biomed Signal Process Control"},{"key":"6557_CR3","doi-asserted-by":"publisher","first-page":"113693","DOI":"10.1016\/j.eswa.2020.113693","volume":"161","author":"\u015e \u00d6zt\u00fcrk","year":"2020","unstructured":"\u00d6zt\u00fcrk \u015e (2020) Stacked auto-encoder based tagging with deep features for content-based medical image retrieval. Expert Syst Appl 161:113693","journal-title":"Expert Syst Appl"},{"key":"6557_CR4","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1016\/j.procs.2021.02.106","volume":"183","author":"\u015e \u00d6zt\u00fcrk","year":"2021","unstructured":"\u00d6zt\u00fcrk \u015e (2021) Convolutional neural network based dictionary learning to create hash codes for content-based image retrieval. Proced Comput Sci 183:624\u2013629","journal-title":"Proced Comput Sci"},{"issue":"7553","key":"6557_CR5","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"6557_CR6","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural networks 61:85\u2013117","journal-title":"Neural networks"},{"issue":"2","key":"6557_CR7","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s00521-019-04324-4","volume":"32","author":"A Miguel","year":"2020","unstructured":"Miguel A, Gonzalo J, Garc\u00eda-Lagos F (2020) Advances in computational intelligence. Neural Comput Appl 32(2):309\u2013311","journal-title":"Neural Comput Appl"},{"issue":"3\u20134","key":"6557_CR8","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1561\/2000000039","volume":"7","author":"L Deng","year":"2014","unstructured":"Deng L, Yu D (2014) Deep learning: methods and applications. Found Trends Signal Process 7(3\u20134):197\u2013387","journal-title":"Found Trends Signal Process"},{"key":"6557_CR9","first-page":"1143","volume":"24","author":"V Ordonez","year":"2011","unstructured":"Ordonez V, Kulkarni G, Berg T (2011) Im2text: Describing images using 1 million captioned photographs. Adv Neural Inf Process Syst 24:1143\u20131151","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"6557_CR10","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1109\/TMM.2011.2129502","volume":"13","author":"JH Su","year":"2011","unstructured":"Su JH, Chou CL, Lin CY, Tseng VS (2011) Effective semantic annotation by image-to-concept distribution model. IEEE Trans Multimed 13(3):530\u2013538","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"6557_CR11","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":"6557_CR12","doi-asserted-by":"crossref","unstructured":"Ballan L, Uricchio T, Seidenari L, Del Bimbo A (2014) A cross-media model for automatic image annotation. In Proceedings of international conference on multimedia retrieval pp. 73\u201380","DOI":"10.1145\/2578726.2578728"},{"issue":"1","key":"6557_CR13","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/s11263-010-0338-6","volume":"90","author":"A Makadia","year":"2010","unstructured":"Makadia A, Pavlovic V, Kumar S (2010) Baselines for image annotation. Int J Comput Vis 90(1):88\u2013105","journal-title":"Int J Comput Vis"},{"issue":"1","key":"6557_CR14","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/s00521-018-3627-6","volume":"32","author":"AM Zahangir","year":"2020","unstructured":"Zahangir AM, Mahmudul H, Chris Y, Taha TM, Asari VK (2020) Improved inception-residual convolutional neural network for object recognition. Neural Comput Appl 32(1):279\u2013293","journal-title":"Neural Comput Appl"},{"issue":"2","key":"6557_CR15","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1007\/s10489-020-01873-3","volume":"51","author":"K Qian","year":"2021","unstructured":"Qian K, Tian L, Liu Y, Wen X, Bao J (2021) Image robust recognition based on feature-entropy-oriented differential fusion capsule network. Appl Intell 51(2):1108\u20131117","journal-title":"Appl Intell"},{"key":"6557_CR16","doi-asserted-by":"crossref","unstructured":"LeCun Y, Kavukcuoglu K, Farabet C (2010). Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE international symposium on circuits and systems pp. 253-256","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"6557_CR17","doi-asserted-by":"crossref","unstructured":"Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops pp. 806\u2013813","DOI":"10.1109\/CVPRW.2014.131"},{"issue":"01","key":"6557_CR18","doi-asserted-by":"publisher","first-page":"33","DOI":"10.36548\/jscp.2019.1.004","volume":"1","author":"JS Raj","year":"2019","unstructured":"Raj JS, Ananthi JV (2019) Recurrent neural networks and nonlinear prediction in support vector machines. J Soft Comput Paradigm (JSCP) 1(01):33\u201340","journal-title":"J Soft Comput Paradigm (JSCP)"},{"key":"6557_CR19","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, pp. 740-755. Springer, Cham","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6557_CR20","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation, In: EMNLP","DOI":"10.3115\/v1\/D14-1179"},{"issue":"12","key":"6557_CR21","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6557_CR22","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.neucom.2019.12.118","volume":"388","author":"S Du","year":"2020","unstructured":"Du S, Li T, Yang Y, Horng SJ (2020) Multivariate time series forecasting via attention-based encoder-decoder framework. Neurocomputing 388:269\u2013279","journal-title":"Neurocomputing"},{"key":"6557_CR23","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. pp. 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"6557_CR24","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning. pp. 2048\u20132057, PMLR"},{"key":"6557_CR25","doi-asserted-by":"crossref","unstructured":"Li L, Tang S, Deng L, Zhang Y, Tian Q (2017) Image caption with global-local attention. In: Proceedings of the AAAI conference on artificial intelligence (Vol. 31, No. 1)","DOI":"10.1609\/aaai.v31i1.11236"},{"issue":"2","key":"6557_CR26","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"},{"key":"6557_CR27","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":"6557_CR28","first-page":"1","volume":"80","author":"W Zhang","year":"2020","unstructured":"Zhang W, Tang S, Su J, Xiao J, Zhuang Y (2020) Tell and guess: cooperative learning for natural image caption generation with hierarchical refined attention. Multimed Tools Appl 80:1\u201316","journal-title":"Multimed Tools Appl"},{"issue":"6245","key":"6557_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1126\/science.aaa8685","volume":"349","author":"J Hirschberg","year":"2015","unstructured":"Hirschberg J, Manning CD (2015) Advances in natural language processing. Science 349(6245):261\u2013266","journal-title":"Science"},{"key":"6557_CR30","doi-asserted-by":"crossref","unstructured":"Yang X, Zhu X, Zhao H, Zhang Q, Feng Y (2019) Enhancing unsupervised pretraining with external knowledge for natural language inference. In: Canadian conference on artificial intelligence. pp. 413\u2013419. Springer, Cham","DOI":"10.1007\/978-3-030-18305-9_38"},{"issue":"1","key":"6557_CR31","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1038\/nrn.2016.150","volume":"18","author":"MAL Ralph","year":"2017","unstructured":"Ralph MAL, Jefferies E, Patterson K, Rogers TT (2017) The neural and computational bases of semantic cognition. Nat Rev Neurosci 18(1):42\u201355","journal-title":"Nat Rev Neurosci"},{"key":"6557_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41562-020-01034-z","volume":"5","author":"RL Jackson","year":"2021","unstructured":"Jackson RL, Rogers TT, Ralph MAL (2021) Reverse-engineering the cortical architecture for controlled semantic cognition. Nat Hum Behav 5:1\u201313","journal-title":"Nat Hum Behav"},{"key":"6557_CR33","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.neucom.2018.05.080","volume":"311","author":"S Bai","year":"2018","unstructured":"Bai S, An S (2018) A survey on automatic image caption generation. Neurocomputing 311:291\u2013304","journal-title":"Neurocomputing"},{"key":"6557_CR34","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.patrec.2019.03.021","volume":"123","author":"S Ding","year":"2019","unstructured":"Ding S, Qu S, Xi Y, Sangaiah AK, Wan S (2019) Image caption generation with high-level image features. Pattern Recognition Lett 123:89\u201395","journal-title":"Pattern Recognition Lett"},{"key":"6557_CR35","doi-asserted-by":"crossref","unstructured":"Khademi M, Schulte O (2018) Image caption generation with hierarchical contextual visual spatial attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. pp. 1943\u20131951","DOI":"10.1109\/CVPRW.2018.00260"},{"key":"6557_CR36","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"6557_CR37","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"6557_CR38","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: Proceedings of the 40th annual meeting of the association for computational linguistics. pp. 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"6557_CR39","doi-asserted-by":"crossref","unstructured":"Yang J, Wang M, Zhou H, Zhao C, Zhang W, Yu Y, Li L (2020) Towards making the most of bert in neural machine translation. In: Proceedings of the AAAI conference on artificial intelligence 34(5):9378\u20139385","DOI":"10.1609\/aaai.v34i05.6479"},{"key":"6557_CR40","doi-asserted-by":"crossref","unstructured":"Denkowski M, Lavie A (2014) Meteor universal: Language specific translation evaluation for any target language. In: Proceedings of the ninth workshop on statistical machine translation. pp. 376\u2013380","DOI":"10.3115\/v1\/W14-3348"},{"key":"6557_CR41","unstructured":"Lin C Y (2004) Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out. pp. 74\u201381"},{"key":"6557_CR42","doi-asserted-by":"crossref","unstructured":"Sun S, Nenkova A (2019) The feasibility of embedding based automatic evaluation for single document summarization. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). pp. 1216\u20131221","DOI":"10.18653\/v1\/D19-1116"},{"key":"6557_CR43","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., & Parikh, D. (2015). Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"6557_CR44","doi-asserted-by":"crossref","unstructured":"Wang Z, Huang Z, Luo Y (2020) Human consensus-oriented image captioning. In: Proceedings of international joint conference on artificial intelligence, IJCAI. pp. 659\u2013665","DOI":"10.24963\/ijcai.2020\/92"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06557-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06557-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06557-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:53:57Z","timestamp":1673301237000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06557-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,24]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["6557"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06557-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,24]]},"assertion":[{"value":"31 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}