{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:17:47Z","timestamp":1740107867202,"version":"3.37.3"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T00:00:00Z","timestamp":1555372800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61762038","61861016","61741108"],"award-info":[{"award-number":["61762038","61861016","61741108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Humanity and Social Science Foundation of the Ministry of Education","award":["17YJAZH117","16YJAZH029"],"award-info":[{"award-number":["17YJAZH117","16YJAZH029"]}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20171BAB202023"],"award-info":[{"award-number":["20171BAB202023"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Plan of Jiangxi Provincial Science and Technology Department","award":["20171BBG70093"],"award-info":[{"award-number":["20171BBG70093"]}]},{"name":"Science and Technology Projects of Jiangxi Provincial Department of Education","award":["GJJ160497","GJJ160509","GJJ160531"],"award-info":[{"award-number":["GJJ160497","GJJ160509","GJJ160531"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1007\/s00500-019-03973-w","type":"journal-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T11:03:01Z","timestamp":1555412581000},"page":"1377-1397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Novel model to integrate word embeddings and syntactic trees for automatic caption generation from images"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8375-0039","authenticated-orcid":false,"given":"Hongbin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diedie","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renzhong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghong","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,16]]},"reference":[{"key":"3973_CR1","unstructured":"Aker A, Gaizauskas R (2010) Generating image descriptions using dependency relational patterns. In Proceedings of annual meeting of the Association for Computational Linguistics"},{"key":"3973_CR2","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C et al (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00636"},{"key":"3973_CR3","unstructured":"Andrew G, Arora R, Bilmes J, Livescu K (2013) Deep canonical correlation analysis. In: Proceedings of international conference on machine learning, JMLR W&CP, vol 28, no. 3, pp 1247\u20131255"},{"key":"3973_CR4","doi-asserted-by":"crossref","unstructured":"Berg TL, Berg AC, Shih J (2010) Automatic attribute discovery and characterization from noisy web data. In: Proceedings of European conference on computer vision","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"3973_CR5","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MJ (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"3973_CR6","unstructured":"Bo L, Ren X, Fox D (2009) Efficient match kernels between sets of features for visual recognition. In: Proceedings of advances in neural information processing systems, pp 135\u2013143"},{"key":"3973_CR7","unstructured":"Bo L, Ren X, Fox D (2010) Kernel descriptors for visual recognition. In Proceedings of advances in neural information processing systems, pp 1734\u20131742"},{"key":"3973_CR8","doi-asserted-by":"crossref","unstructured":"Chen K, Gao J, Nevatia R (2018) Knowledge aided consistency for weakly supervised phrase grounding. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2018.00425"},{"key":"3973_CR9","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"3973_CR10","unstructured":"Yang Y, Teo CL, Daume H, III, Aloimonos Y (2011) Corpus-guided sentence generation of natural images. In: Proceedings of conference on empirical methods on natural language processing, pp 444\u2013454"},{"key":"3973_CR11","doi-asserted-by":"crossref","unstructured":"Deshpande A, Aneja J, Wang L, Schwing A, Forsyth DA (2018) Diverse and controllable image captioning with part-of-speech guidance. In: Proceedings of advances in neural information processing systems","DOI":"10.1109\/CVPR.2019.01095"},{"key":"3973_CR12","doi-asserted-by":"crossref","unstructured":"Devlin J, Cheng H, Fang H, Gupta S, Deng L, He X, Zweig G, Mitchell M (2015) Language models for image captioning: the quirks and what works. In: Proceedings of annual meeting of the Association for Computational Linguistics","DOI":"10.3115\/v1\/P15-2017"},{"key":"3973_CR13","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of IEEE conference on computer vision and pattern recognition","DOI":"10.21236\/ADA623249"},{"key":"3973_CR14","unstructured":"Elamri C, de Planque T (2016) Automated neural image caption generator for visually impaired people [EB\/OL]. Stanford CS224D"},{"key":"3973_CR15","doi-asserted-by":"crossref","unstructured":"Elliott D, de Vries AP (2015) Describing images using inferred visual dependency representations. In: Proceedings of Annual Meeting of the Association for Computational Linguistics","DOI":"10.3115\/v1\/P15-1005"},{"key":"3973_CR16","doi-asserted-by":"crossref","unstructured":"Fang H, Gupta S, Iandola F, Srivastava R, Deng L, Dollar P, Gao J, He X, Mitchell M, Platt J, Zitnick CL, Zweig G (2015) From captions to visual concepts and back. In: Proceedings of IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"3973_CR17","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"Ali Farhadi","year":"2010","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. In: Proceedings of European Conference on Computer Vision, pp 15\u201329"},{"issue":"4","key":"3973_CR18","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1109\/TPAMI.2012.118","volume":"35","author":"Y Feng","year":"2013","unstructured":"Feng Y, Lapata M (2013) 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":"3973_CR19","doi-asserted-by":"crossref","unstructured":"Gan Z, Gan C, He X et al (2017) Semantic compositional networks for visual captioning. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.127"},{"key":"3973_CR20","doi-asserted-by":"crossref","unstructured":"Gu J, Cai J, Wang G et al (2017) Stack-captioning: coarse-to-fine learning for image captioning. In: Proceedings of computer vision and pattern recognition","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"3973_CR21","unstructured":"Gupta A, Verma Y, Jawahar CV (2012) Choosing linguistics over vision to describe images. In: Proceedings of AAAI conference on artificial intelligence"},{"key":"3973_CR22","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of IEEE international conference on computer vision, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5186","key":"3973_CR23","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5186):504\u2013507","journal-title":"Science"},{"key":"3973_CR24","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Osindero S, Teh Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18:1527\u20131554","journal-title":"Neural Comput"},{"key":"3973_CR25","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Intell Res 47:853\u2013899","journal-title":"J Artif Intell Res"},{"issue":"1","key":"3973_CR26","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1023\/A:1007617005950","volume":"42","author":"T Hofmann","year":"2001","unstructured":"Hofmann T (2001) Unsupervised learning by probabilistic latent semantic analysis. Mach Learn 42(1):177\u2013196","journal-title":"Mach Learn"},{"issue":"2","key":"3973_CR28","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/s11263-011-0494-3","volume":"100","author":"S Hwang","year":"2012","unstructured":"Hwang S, Grauman K (2012) Learning the relative importance of objects from tagged images for retrieval and cross-modal search. Int J Comput Vis 100(2):134\u2013153","journal-title":"Int J Comput Vis"},{"key":"3973_CR29","doi-asserted-by":"crossref","unstructured":"Jeon J, Lavrenko V, Manmatha R (2003) Automatic image annotation and retrieval using cross-media relevance models. In: Proceedings of the Special Interest Group on Information Retrieval, pp 119\u2013126","DOI":"10.1145\/860435.860459"},{"key":"3973_CR30","doi-asserted-by":"crossref","unstructured":"Jia X, Gavves E, Fernando B, Tuytelaars T (2015) Guiding the long-short term memory model for image caption generation. In: Proceedings of international conference on computer vision","DOI":"10.1109\/ICCV.2015.277"},{"key":"3973_CR31","unstructured":"Karpathy A, Joulin A, Fei-Fei L (2014) Deep fragment embeddings for bidirectional image sentence mapping. In: Proceedings of advances in neural information processing systems"},{"key":"3973_CR32","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. In: Proceedings of international conference on machine learning, JMLR Workshop, pp 595\u2013603"},{"key":"3973_CR33","unstructured":"Kiros R, Salakhutdinov R, Zemel RS (2015) Unifying visual-semantic embeddings with multimodal neural language models. In: Proceedings of advances in neural information processing systems deep learning workshop"},{"key":"3973_CR34","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of conference on advances in neural information processing systems, pp 1106\u20131114"},{"issue":"12","key":"3973_CR35","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, Dhar S et al (2013) Baby talk: 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":"3973_CR36","unstructured":"Kuznetsova P, Ordonez V, Berg AC, Berg TL, Choi Y (2012) Collective generation of natural image descriptions. In: Proceedings of annual meeting of the Association for Computational Linguistics"},{"key":"3973_CR37","unstructured":"Lebret R, Pinheiro PO, Collobert R (2015) Phrase-based image captioning. In: Proceedings of international conference on machine learning"},{"key":"3973_CR38","unstructured":"Li S, Kulkarni G, Berg TL, Berg AC, Choi Y (2011) Composing simple image descriptions using web-scale n-grams. In: Proceedings of conference on natural language learning"},{"key":"3973_CR39","doi-asserted-by":"crossref","unstructured":"Li P, Ma J, Gao S (2012) Learning to summarize web image and text mutually. In: Proceedings of international conference on multimedia retrieval","DOI":"10.1145\/2324796.2324832"},{"key":"3973_CR40","unstructured":"Li D, Huang Q, He X (2018) Generating diverse and accurate visual captions by comparative adversarial learning [EB\/OL]. arXiv.org"},{"key":"3973_CR41","doi-asserted-by":"crossref","unstructured":"Liu C, Mao J, Sha F, Yuille A (2017) Attention correctness in neural image captioning. In: Proceedings of AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"3973_CR42","doi-asserted-by":"crossref","unstructured":"Liu X, Li H, Shao J (2018) Show, tell and discriminate: image captioning by self-retrieval with partially labeled data. In: Proceedings of European conference on computer vision","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"3973_CR43","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"2","key":"3973_CR44","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"David G Lowe","year":"2004","unstructured":"Lowe David G (2004) Distinctive image features from scale-invariant key points. Int J Comput Vision 60(2):91\u2013110","journal-title":"Int J Comput Vision"},{"key":"3973_CR45","unstructured":"Maas AL, Daly RE, Pham PT, Huang D, Ng AY, Potts C (2011) Learning word vectors for sentiment analysis. In: Proceedings of the annual meeting of the Association for Computational Linguistics: Human Language Technologies, pp 142\u2013150"},{"key":"3973_CR46","first-page":"316","volume-title":"Lecture Notes in Computer Science","author":"Ameesh Makadia","year":"2008","unstructured":"Makadia A, Pavlovic V, Kumar S (2008) A new baseline for image annotation. In: Proceedings of European conference on computer vision, pp 316\u2013329"},{"key":"3973_CR47","unstructured":"Mansimov E, Parisotto E, Ba JL et al (2016) Generating images from captions with attention. In: Proceedings of international conference on learning representations"},{"key":"3973_CR48","unstructured":"Mao J, Xu W, Yang Y, Wang J, Yuille AL (2015) Deep captioning with multimodal recurrent neural networks (m-RNN). In: Proceedings of international conference on learning representations"},{"key":"3973_CR49","unstructured":"Mason R (2013) Domain-independent captioning of domain-specific images. In: Proceedings of North American Association for Computational Linguistics, pp 69\u201376"},{"key":"3973_CR50","unstructured":"Mason R, Charniak E (2013) Annotation of online shopping images without labeled training examples. In: Proceedings of human language technologies: conference of the North American Chapter of the Association of Computational Linguistics"},{"key":"3973_CR51","unstructured":"Mikolov T, Sutskever I, Chen K et al (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of conference on advances in neural information processing systems"},{"key":"3973_CR52","unstructured":"Mitchell M, Dodge J, Goyal A et al (2012) Midge: generating image descriptions from computer vision detections. In: Proceedings of European Association for Computational Linguistics, pp 747\u2013756"},{"key":"3973_CR53","doi-asserted-by":"crossref","unstructured":"Monay F, Gatica-Perez D (2004) PLSA-based image auto annotation: constraining the latent space. In: Proceedings of ACM international conference on multimedia, pp 348\u2013351","DOI":"10.1145\/1027527.1027608"},{"key":"3973_CR54","unstructured":"Mukuta Y, Harada T (2014) Probabilistic partial canonical correlation analysis. In: Proceedings of international conference on machine learning, pp 1449\u20131457"},{"issue":"7","key":"3973_CR55","first-page":"971","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietikainen M, Maenpaa T (2002) Multi-resolution grayscale and rotation invariant texture classification with local binary patterns. IEEE 24(7):971\u2013987","journal-title":"IEEE"},{"key":"3973_CR56","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0079-6123(06)55002-2","volume":"155","author":"A Oliva","year":"2006","unstructured":"Oliva A, Torralba A (2006) Building the gist of a scene: the role of global image features in recognition. Prog Brain Res Visual Percept 155:23\u201336","journal-title":"Prog Brain Res Visual Percept"},{"key":"3973_CR57","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2Text: describing images using 1 million captioned photographs. In: Conference on neural information processing systems"},{"key":"3973_CR58","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of annual meeting of the Association for Computational Linguistics, pp 311\u2013318"},{"key":"3973_CR59","doi-asserted-by":"crossref","unstructured":"Pedersoli M, Lucas T, Schmid C, Verbeek J (2017) Areas of attention for image captioning. In: Proceedings of international conference on computer vision","DOI":"10.1109\/ICCV.2017.140"},{"key":"3973_CR60","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of conference on empirical methods on natural language processing","DOI":"10.3115\/v1\/D14-1162"},{"key":"3973_CR61","unstructured":"Pinheiro P, Lebret R, Collobert R (2015) Simple image description generator via a linear phrase-based model. In: Proceedings of international conference on learning representations workshop"},{"key":"3973_CR62","doi-asserted-by":"crossref","unstructured":"Quan R, Han J, Zhang D, Nie F (2016) Object co-segmentation via graph optimized-flexible manifold ranking. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.81"},{"key":"3973_CR63","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Proceedings of MICCAI","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3973_CR64","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of international conference on learning representations"},{"key":"3973_CR65","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher R, Karpathy A, Le QV, Manning CD, Ng AY (2014) Grounded compositional semantics for finding and describing images with sentences. Trans Assoc Comput Linguist 2:207\u2013218","journal-title":"Trans Assoc Comput Linguist"},{"key":"3973_CR66","unstructured":"Sutskever I, Vinyals O, Le Q (2014) Sequence to sequence learning with neural networks. In: Proceedings of NIPS"},{"key":"3973_CR67","doi-asserted-by":"crossref","unstructured":"Ushiku Y, Harada T, Kuniyoshi Y (2011) Automatic sentence generation from images. In: Proceedings of ACM multimedia conference, pp 1533\u20131536","DOI":"10.1145\/2072298.2072058"},{"key":"3973_CR68","doi-asserted-by":"crossref","unstructured":"Vedaldi A, Gulshan V, Varma M, Zisserman A (2009) Multiple kernels for object detection. In: Proceedings of international conference on computer vision, pp 606\u2013613","DOI":"10.1109\/ICCV.2009.5459183"},{"key":"3973_CR69","doi-asserted-by":"crossref","unstructured":"Vittayakorn S, Umeda T, Murasaki K, Sudo K, Okatani T, Yamaguchi K (2016) Automatic attribute discovery with neural activations. In: Proceedings of European conference on computer vision","DOI":"10.1007\/978-3-319-46493-0_16"},{"key":"3973_CR70","unstructured":"Wang Q, Chan AB (2018) CNN\u2009+\u2009CNN: convolutional decoders for image captioning [EB\/OL]. arXiv.org"},{"key":"3973_CR71","doi-asserted-by":"crossref","unstructured":"Wang J, Madhyastha P, Specia L (2018) Object counts! bringing explicit detections back into image captioning. In: Proceedings of North American Chapter of the Association for Computational Linguistics","DOI":"10.18653\/v1\/N18-1198"},{"key":"3973_CR72","doi-asserted-by":"crossref","unstructured":"Wu Q, Shen C, Liu L, Dick A, van den Hengel A (2016) What value do explicit high level concepts have in vision to language problems?. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.29"},{"key":"3973_CR73","doi-asserted-by":"crossref","unstructured":"Xiao F, Sigal L, Lee YJ (2017) Weakly-supervised visual grounding of phrases with linguistic structures. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.558"},{"key":"3973_CR74","unstructured":"Xu K, Ba JL, Kiros R et al (2015) Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of international conference on machine learning"},{"key":"3973_CR75","doi-asserted-by":"crossref","unstructured":"Xu N, Price B, Cohen S, Yang J, Huang TS (2016) Deep interactive object selection. In Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.47"},{"key":"3973_CR76","unstructured":"Yang J, Yu K, Gong Y et al. (2009) Linear spatial pyramid matching using sparse coding for image classification. In: IEEE conference on computer vision and pattern recognition, pp 1794\u20131801"},{"issue":"8","key":"3973_CR77","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/JPROC.2010.2050411","volume":"98","author":"B Yao","year":"2010","unstructured":"Yao B, Yang X, Lin L, Lee MW, Zhu S-C (2010) I2t: image parsing to text description. Proc IEEE 98(8):1485\u20131508","journal-title":"Proc IEEE"},{"key":"3973_CR78","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: Proceedings of computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.503"},{"key":"3973_CR79","unstructured":"You Q, You Q, Luo J 2018) Image captioning at will: a versatile scheme for effectively injecting sentiments into image descriptions [EB\/OL]. arXiv.org"},{"issue":"11","key":"3973_CR27","first-page":"2542","volume":"53","author":"H Zhang","year":"2016","unstructured":"Zhang H, Ji D, Yin L, Ren Y, Niu Z (2016) Caption generation from product image based on tag refinement and syntactic tree. J Comput Res Dev 53(11):2542\u20132555","journal-title":"J Comput Res Dev"},{"key":"3973_CR80","doi-asserted-by":"crossref","unstructured":"Zhang Z, Xie Y, Xing F et al. (2017) MDNet: a semantically and visually interpretable medical image diagnosis network. In: Proceedings of IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.378"},{"key":"3973_CR81","doi-asserted-by":"crossref","unstructured":"Zheng S, Jayasumana S, Romera-Paredes B, Vineet V, Su Z, Du D, Huang C, Torr PHS (2015) Conditional random fields as recurrent neural networks. In: Proceedings of international conference on computer vision","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-019-03973-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-019-03973-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-019-03973-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T02:11:23Z","timestamp":1663294283000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-019-03973-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,16]]},"references-count":81,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["3973"],"URL":"https:\/\/doi.org\/10.1007\/s00500-019-03973-w","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"type":"print","value":"1432-7643"},{"type":"electronic","value":"1433-7479"}],"subject":[],"published":{"date-parts":[[2019,4,16]]},"assertion":[{"value":"16 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}