{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:18:26Z","timestamp":1778080706605,"version":"3.51.4"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T00:00:00Z","timestamp":1678924800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T00:00:00Z","timestamp":1678924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC210B018"],"award-info":[{"award-number":["CUC210B018"]}],"id":[{"id":"10.13039\/501100012226","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":[[2023,5]]},"DOI":"10.1007\/s00521-022-08072-w","type":"journal-article","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T16:03:36Z","timestamp":1678982616000},"page":"9481-9500","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Spatial-aware topic-driven-based image Chinese caption for disaster news"],"prefix":"10.1007","volume":"35","author":[{"given":"Jinfei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8150-6366","authenticated-orcid":false,"given":"Yaping","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yana","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,16]]},"reference":[{"key":"8072_CR1","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1109\/CVPR.2015.7298935","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"8072_CR2","doi-asserted-by":"publisher","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, vol 37, pp 2048\u20132057. PMLR. https:\/\/doi.org\/10.5555\/3045118.3045336","DOI":"10.5555\/3045118.3045336"},{"key":"8072_CR3","doi-asserted-by":"publisher","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2017) Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 375\u2013383. https:\/\/doi.org\/10.1109\/CVPR.2017.345","DOI":"10.1109\/CVPR.2017.345"},{"key":"8072_CR4","doi-asserted-by":"publisher","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6077\u20136086. https:\/\/doi.org\/10.1109\/CVPR.2018.00636","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8072_CR5","doi-asserted-by":"publisher","unstructured":"Feng Y, Lapata M (2010) How many words is a picture worth? Automatic caption generation for news images. In: Proceedings of the 48th annual meeting of the association for computational linguistics, pp 1239\u20131249. https:\/\/doi.org\/10.5555\/1858681.1858807","DOI":"10.5555\/1858681.1858807"},{"key":"8072_CR6","doi-asserted-by":"publisher","unstructured":"Vijay K, Ramya D (2015) Generation of caption selection for news images using stemming algorithm. In: International conference on computation of power, energy, information and communication, pp 0536\u20130540. IEEE. https:\/\/doi.org\/10.1109\/ICCPEIC.2015.7259513","DOI":"10.1109\/ICCPEIC.2015.7259513"},{"key":"8072_CR7","doi-asserted-by":"publisher","unstructured":"Lu D, Whitehead S, Huang L, Ji H, Chang S-F (2018) Entity-aware image caption generation. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 4013\u20134023. https:\/\/doi.org\/10.18653\/v1\/D18-1435","DOI":"10.18653\/v1\/D18-1435"},{"key":"8072_CR8","doi-asserted-by":"publisher","unstructured":"Yang Z, Okazaki N (2020) Image caption generation for news articles. In: Proceedings of the 28th international conference on computational linguistics, pp 1941\u20131951. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.176","DOI":"10.18653\/v1\/2020.coling-main.176"},{"key":"8072_CR9","doi-asserted-by":"publisher","first-page":"143584","DOI":"10.1109\/ACCESS.2020.3013321","volume":"8","author":"Y Jing","year":"2020","unstructured":"Jing Y, Zhiwei X, Guanglai G (2020) Context-driven image caption with global semantic relations of the named entities. IEEE Access 8:143584\u2013143594. https:\/\/doi.org\/10.1109\/ACCESS.2020.3013321","journal-title":"IEEE Access"},{"key":"8072_CR10","doi-asserted-by":"publisher","unstructured":"Rashtchian C, Young P, Hodosh M, Hockenmaier J (2010) Collecting image annotations using Amazon\u2019s Mechanical Turk. In: Proceedings of the NAACL HLT 2010 workshop on creating speech and language data with Amazon\u2019s Mechanical Turk, pp 139\u2013147. https:\/\/doi.org\/10.5555\/1866696.1866717","DOI":"10.5555\/1866696.1866717"},{"key":"8072_CR11","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2:67\u201378. https:\/\/doi.org\/10.1162\/tacl_a_00166","journal-title":"Trans Assoc Comput Linguist"},{"key":"8072_CR12","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8072_CR13","doi-asserted-by":"publisher","unstructured":"Yao T, Pan Y, Li Y, Tao M (2018) Exploring visual relationship for image captioning. In: European conference on computer vision. Springer, pp 711\u2013727. https:\/\/doi.org\/10.1007\/978-3-030-01264-9_42","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"8072_CR14","doi-asserted-by":"publisher","unstructured":"Yang X, Tang K, Zhang H, Cai J (2019) Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10685\u201310694. https:\/\/doi.org\/10.1109\/TPAMI.2020.3042192","DOI":"10.1109\/TPAMI.2020.3042192"},{"key":"8072_CR15","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. https:\/\/doi.org\/10.1016\/j.neucom.2018.05.080","journal-title":"Neurocomputing"},{"key":"8072_CR16","doi-asserted-by":"publisher","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth DA (2010) Every picture tells a story: generating sentences from images. In: European conference on computer vision, pp 15\u201329. https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"8072_CR17","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.5555\/2986459.2986587","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. https:\/\/doi.org\/10.5555\/2986459.2986587","journal-title":"Adv Neural Inf Process Syst"},{"key":"8072_CR18","doi-asserted-by":"publisher","unstructured":"Yang Y, Teo C, Daum\u00e9\u00a0III H, Aloimonos Y (2011) Corpus-guided sentence generation of natural images. In: Proceedings of the 2011 conference on empirical methods in natural language processing, pp 444\u2013454. https:\/\/doi.org\/10.5555\/2145432.2145484","DOI":"10.5555\/2145432.2145484"},{"issue":"12","key":"8072_CR19","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/CVPR.2011.5995466","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni G, Premraj V, Ordonez V, Dhar S, Li S, Choi Y, Berg AC, Berg TL (2013) Babytalk: understanding and generating simple image descriptions. IEEE Trans Pattern Anal Mach Intell 35(12):2891\u20132903. https:\/\/doi.org\/10.1109\/CVPR.2011.5995466","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8072_CR20","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s00521-015-1846-7","volume":"27","author":"L Bai","year":"2015","unstructured":"Bai L, Li K, Pei J, Jiang S (2015) Main objects interaction activity recognition in real images. Neural Comput Appl 27:335\u2013348. https:\/\/doi.org\/10.1007\/s00521-015-1846-7","journal-title":"Neural Comput Appl"},{"key":"8072_CR21","doi-asserted-by":"publisher","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, pp 7008\u20137024. https:\/\/doi.org\/10.1109\/CVPR.2017.131","DOI":"10.1109\/CVPR.2017.131"},{"key":"8072_CR22","doi-asserted-by":"publisher","unstructured":"Wu Q, Shen C, Liu L, Dick A, Van Den\u00a0Hengel A (2016) What value do explicit high level concepts have in vision to language problems?. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 203\u2013212. https:\/\/doi.org\/10.1109\/CVPR.2016.29","DOI":"10.1109\/CVPR.2016.29"},{"key":"8072_CR23","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1109\/CVPR.2016.503","DOI":"10.1109\/CVPR.2016.503"},{"key":"8072_CR24","doi-asserted-by":"publisher","unstructured":"Gan Z, Gan C, He X, Pu Y, Tran K, Gao J, Carin L, Deng L (2017) Semantic compositional networks for visual captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5630\u20135639. https:\/\/doi.org\/10.1109\/CVPR.2017.127","DOI":"10.1109\/CVPR.2017.127"},{"key":"8072_CR25","doi-asserted-by":"publisher","unstructured":"Lu J, Yang J, Batra D, Parikh D (2018) Neural baby talk. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7219\u20137228. https:\/\/doi.org\/10.1109\/CVPR.2018.00754","DOI":"10.1109\/CVPR.2018.00754"},{"key":"8072_CR26","doi-asserted-by":"publisher","unstructured":"Agrawal H, Desai K, Wang Y, Chen X, Jain R, Johnson M, Batra D, Parikh D, Lee S, Anderson P (2019) Nocaps: novel object captioning at scale. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8948\u20138957. https:\/\/doi.org\/10.1109\/ICCV.2019.00904","DOI":"10.1109\/ICCV.2019.00904"},{"key":"8072_CR27","doi-asserted-by":"publisher","unstructured":"Li L, Gan Z, Cheng Y, Liu J (2019) Relation-aware graph attention network for visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10313\u201310322. https:\/\/doi.org\/10.1109\/ICCV.2019.01041","DOI":"10.1109\/ICCV.2019.01041"},{"key":"8072_CR28","doi-asserted-by":"publisher","unstructured":"Johnson J, Krishna R, Stark M, Li L-J, Shamma D, Bernstein M, Fei-Fei L (2015) Image retrieval using scene graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3668\u20133678. https:\/\/doi.org\/10.1109\/CVPR.2015.7298990","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"8072_CR29","doi-asserted-by":"publisher","first-page":"17899","DOI":"10.1007\/s00521-019-04515-z","volume":"32","author":"N Gupta","year":"2020","unstructured":"Gupta N, Jalal A (2020) Integration of textual cues for fine-grained image captioning using deep CNN and LSTM. Neural Comput Appl 32:17899\u201317908. https:\/\/doi.org\/10.1007\/s00521-019-04515-z","journal-title":"Neural Comput Appl"},{"key":"8072_CR30","doi-asserted-by":"publisher","unstructured":"Lu J, Batra D, Parikh D, Lee S (2019) Vilbert: pretraining task-agnostic visiolin-guistic representations for vision-and-language tasks. In: Advances in neural in- formation processing systems, pp 13\u201323. https:\/\/doi.org\/10.5555\/3454287.3454289","DOI":"10.5555\/3454287.3454289"},{"key":"8072_CR31","doi-asserted-by":"publisher","unstructured":"Li G, Duan N, Fang Y, Jiang D, Zhou M (2020) Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. In: AAAI, pp 11336\u201311344. https:\/\/doi.org\/10.1609\/aaai.v34i07.6795","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"8072_CR32","doi-asserted-by":"publisher","unstructured":"Zhou L, Palangi H, Zhang L, Hu H, Corso JJ, Gao J (2019) Unified vision-language pre-training for image captioning and vqa. In: Proceedings of the AAAI conference on artificial intelligence, pp 13041\u201313049. https:\/\/doi.org\/10.1609\/AAAI.V34I07.7005","DOI":"10.1609\/AAAI.V34I07.7005"},{"key":"8072_CR33","doi-asserted-by":"publisher","unstructured":"Li X, Yin X, Li C, Zhang P, Hu X, Zhang L, Wang L, Hu H, Dong L, Wei F (2020) Oscar: object-semantics aligned pre-training for vision-language tasks. In: Computer vision\u2013ECCV 2020. Lecture notes in computer science, pp 121\u2013137. https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"8072_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCYB.2020.2997034","volume":"1","author":"M Liu","year":"2020","unstructured":"Liu M, Hu H, Li L, Yu Y, Guan W (2020) Chinese image caption generation via visual attention and topic modeling. IEEE Trans Cybern 1:1\u201311. https:\/\/doi.org\/10.1109\/TCYB.2020.2997034","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"8072_CR35","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. https:\/\/doi.org\/10.1016\/j.ipm.2019.102178","journal-title":"Inf Process Manag"},{"key":"8072_CR36","doi-asserted-by":"publisher","first-page":"104543","DOI":"10.1109\/ACCESS.2020.2999568","volume":"8","author":"B Wang","year":"2020","unstructured":"Wang B, Wang C, Zhang Q, Su Y, Wang Y, Xu Y (2020) Cross-lingual image caption generation based on visual attention model. IEEE Access 8:104543\u2013104554. https:\/\/doi.org\/10.1109\/ACCESS.2020.2999568","journal-title":"IEEE Access"},{"key":"8072_CR37","doi-asserted-by":"publisher","unstructured":"Wu J, Zheng H, Zhao B, Li Y, Yan B, Liang R, Wang W, Zhou S, Lin G, Fu Y, et al (2017) Ai challenger: a large-scale dataset for going deeper in image understanding. In: IEEE international conference on multimedia and expo, pp 1480\u20131485. https:\/\/doi.org\/10.1109\/ICME.2019.00256","DOI":"10.1109\/ICME.2019.00256"},{"key":"8072_CR38","doi-asserted-by":"crossref","unstructured":"Tran A, Mathews A, Xie L (2020) Transform and tell: entity-aware news image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13035\u201313045","DOI":"10.1109\/CVPR42600.2020.01305"},{"issue":"1","key":"8072_CR39","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L-J, Shamma DA et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis 123(1):32\u201373. https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int J Comput Vis"},{"key":"8072_CR40","doi-asserted-by":"publisher","unstructured":"Xu H, Jiang C, Liang X, Li Z (2019) Spatial-aware graph relation network for large-scale object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9298\u20139307. https:\/\/doi.org\/10.1109\/CVPR.2019.00952","DOI":"10.1109\/CVPR.2019.00952"},{"issue":"4","key":"8072_CR41","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. https:\/\/doi.org\/10.1109\/TPAMI.2012.118","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8072_CR42","doi-asserted-by":"publisher","unstructured":"Biten AF, Gomez L, Rusinol M, Karatzas D (2019) Good news, everyone! context driven entity-aware captioning for news images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12466\u201312475. https:\/\/doi.org\/10.1109\/CVPR.2019.01275","DOI":"10.1109\/CVPR.2019.01275"},{"issue":"6","key":"8072_CR43","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"Adv Neural Inf Process Syst"},{"key":"8072_CR44","doi-asserted-by":"publisher","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, pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"8072_CR45","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 6000\u20136010. https:\/\/doi.org\/10.5555\/3295222.3295349","DOI":"10.5555\/3295222.3295349"},{"key":"8072_CR46","doi-asserted-by":"publisher","unstructured":"Monti F, Boscaini D, Masci J, Rodola E, Svoboda J, Bronstein MM (2017) Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5115\u20135124. https:\/\/doi.org\/10.1109\/CVPR.2017.576","DOI":"10.1109\/CVPR.2017.576"},{"key":"8072_CR47","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125. https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"issue":"6","key":"8072_CR48","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):89\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun ACM"},{"key":"8072_CR49","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR, pp 1\u201315"},{"key":"8072_CR50","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"8072_CR51","doi-asserted-by":"publisher","unstructured":"Banerjee S, Lavie A (2005) Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, pp 65\u201372. https:\/\/doi.org\/10.3115\/1626355.1626389","DOI":"10.3115\/1626355.1626389"},{"key":"8072_CR52","unstructured":"Lin C-Y (2004) Rouge: a package for automatic evaluation of summaries. In: Proceedings of the 42nd association for computational linguistics, pp 74\u201381"},{"key":"8072_CR53","doi-asserted-by":"publisher","unstructured":"Vedantam R, Lawrence\u00a0Zitnick 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. https:\/\/doi.org\/10.1109\/CVPR.2015.7299087","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"8072_CR54","doi-asserted-by":"publisher","unstructured":"Anderson P, Fernando B, Johnson M, Gould S (2016) Spice: semantic propositional image caption evaluation. In: European conference on computer vision. Springer, pp 382\u2013398. https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"8072_CR55","doi-asserted-by":"publisher","unstructured":"Ramos J et al (2003) Using tf-idf to determine word relevance in document queries. In: Proceedings of the 1st instructional conference on machine learning, vol 242. Citeseer, pp 29\u201348. https:\/\/doi.org\/10.5120\/ijca2018917395.","DOI":"10.5120\/ijca2018917395"},{"key":"8072_CR56","doi-asserted-by":"publisher","unstructured":"Huang L, Wang W, Chen J, Wei X-Y (2019) Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4634\u20134643. https:\/\/doi.org\/10.1109\/ICCV.2019.00473","DOI":"10.1109\/ICCV.2019.00473"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08072-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-08072-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-08072-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T14:52:58Z","timestamp":1744210378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-08072-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,16]]},"references-count":56,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["8072"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-08072-w","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,16]]},"assertion":[{"value":"31 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2023","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 concerning the publication of this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}