{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:12:10Z","timestamp":1782965530356,"version":"3.54.5"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T00:00:00Z","timestamp":1642032000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T00:00:00Z","timestamp":1642032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s11042-021-11895-9","type":"journal-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T19:03:50Z","timestamp":1642100630000},"page":"10017-10037","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":73,"title":["Incorporating attentive multi-scale context information for image captioning"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6653-4991","authenticated-orcid":false,"given":"Jeripothula","family":"Prudviraj","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yenduri","family":"Sravani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. Krishna","family":"Mohan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"key":"11895_CR1","doi-asserted-by":"crossref","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","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"11895_CR2","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2018.00636"},{"key":"11895_CR3","unstructured":"Arik SO, Pfister T (2019) Tabnet: attentive interpretable tabular learning. arXiv:1908.07442"},{"key":"11895_CR4","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"},{"key":"11895_CR5","doi-asserted-by":"publisher","first-page":"100240","DOI":"10.1016\/j.bdr.2021.100240","volume":"25","author":"B Breve","year":"2021","unstructured":"Breve B, Caruccio L, Cirillo S, Deufemia V, Polese G (2021) Dependency visualization in data stream profiling. Big Data Research 25:100240","journal-title":"Big Data Research"},{"issue":"4","key":"11895_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3397462","volume":"12","author":"L Caruccio","year":"2020","unstructured":"Caruccio L, Cirillo S (2020) Incremental discovery of imprecise functional dependencies. Journal of Data and Information Quality (JDIQ) 12(4):1\u201325","journal-title":"Journal of Data and Information Quality (JDIQ)"},{"key":"11895_CR7","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua TS (2017) Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5659\u20135667","DOI":"10.1109\/CVPR.2017.667"},{"key":"11895_CR8","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587"},{"key":"11895_CR9","doi-asserted-by":"crossref","unstructured":"Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 801\u2013818","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"11895_CR10","doi-asserted-by":"crossref","unstructured":"Chen S, Zhao Q (2018) Boosted attention: leveraging human attention for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 68\u201384","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"11895_CR11","doi-asserted-by":"crossref","unstructured":"Chen X, Lawrence Zitnick C (2015) Mind\u2019s eye: a recurrent visual representation for image caption generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2422\u20132431","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"11895_CR12","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. arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"issue":"3","key":"11895_CR13","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1038\/nrn755","volume":"3","author":"M Corbetta","year":"2002","unstructured":"Corbetta M, Shulman GL (2002) Control of goal-directed and stimulus-driven attention in the brain. Nature Reviews Neuroscience 3(3):201\u2013215","journal-title":"Nature Reviews Neuroscience"},{"key":"11895_CR14","doi-asserted-by":"crossref","unstructured":"Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10578\u201310587","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"11895_CR15","doi-asserted-by":"crossref","unstructured":"Dai Z, Yang Z, Yang Y, Carbonell J, Le QV, Salakhutdinov R (2019) Transformer-xl: attentive language models beyond a fixed-length context. arXiv:1901.02860","DOI":"10.18653\/v1\/P19-1285"},{"key":"11895_CR16","unstructured":"Elliott D, Keller F (2013) Image description using visual dependency representations. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1292\u20131302"},{"key":"11895_CR17","doi-asserted-by":"crossref","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: European conference on computer vision, pp 15\u201329. Springer","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"11895_CR18","doi-asserted-by":"crossref","unstructured":"Firat O, Cho K, Bengio Y (2016) Multi-way, multilingual neural machine translation with a shared attention mechanism. arXiv:1601.01073","DOI":"10.18653\/v1\/N16-1101"},{"issue":"12","key":"11895_CR19","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TPAMI.2016.2642953","volume":"39","author":"K Fu","year":"2016","unstructured":"Fu K, Jin J, Cui R, Sha F, Zhang C (2016) Aligning where to see and what to tell: image captioning with region-based attention and scene-specific contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(12):2321\u20132334","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"11895_CR20","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2017.127"},{"key":"11895_CR21","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, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"11895_CR22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computation 9(8):1735\u20131780","journal-title":"Neural Computation"},{"issue":"6","key":"11895_CR23","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1145\/3295748","volume":"51","author":"M Hossain","year":"2019","unstructured":"Hossain M, Sohel F, Shiratuddin MF, Laga H (2019) A comprehensive survey of deep learning for image captioning. ACM Computing Surveys (CSUR) 51(6):118","journal-title":"ACM Computing Surveys (CSUR)"},{"issue":"8","key":"11895_CR24","doi-asserted-by":"publisher","first-page":"12525","DOI":"10.1007\/s11042-020-10292-y","volume":"80","author":"HY Hsieh","year":"2021","unstructured":"Hsieh HY, Huang SA, Leu JS (2021) Implementing a real-time image captioning service for scene identification using embedded system. Multimedia Tools and Applications 80(8):12525\u201312537","journal-title":"Multimedia Tools and Applications"},{"key":"11895_CR25","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, pp 4634\u20134643","DOI":"10.1109\/ICCV.2019.00473"},{"key":"11895_CR26","doi-asserted-by":"crossref","unstructured":"Jiang W, Ma L, Jiang YG, Liu W, Zhang T (2018) Recurrent fusion network for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 499\u2013515","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"11895_CR27","unstructured":"Kalchbrenner N, Blunsom P (2013) Recurrent continuous translation models. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1700\u20131709"},{"key":"11895_CR28","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, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"11895_CR29","unstructured":"Karpathy A, Joulin A, Fei-Fei LF (2014) Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in neural information processing systems, pp 1889\u20131897"},{"key":"11895_CR30","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. In: International conference on machine learning, pp 595\u2013603"},{"issue":"12","key":"11895_CR31","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 AC, Berg TL (2013) Babytalk: understanding and generating simple image descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(12):2891\u20132903","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"11895_CR32","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","DOI":"10.1609\/aaai.v31i1.11236"},{"issue":"3","key":"11895_CR33","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1109\/TMM.2017.2751140","volume":"20","author":"L Li","year":"2017","unstructured":"Li L, Tang S, Zhang Y, Deng L, Tian Q (2017) Gla: Global\u2013local attention for image description. IEEE Transactions on Multimedia 20(3):726\u2013737","journal-title":"IEEE Transactions on Multimedia"},{"key":"11895_CR34","unstructured":"Li S, Kulkarni G, Berg TL, Berg AC, Choi Y (2011) Composing simple image descriptions using web-scale n-grams. In: Proceedings of the fifteenth conference on computational natural language learning, pp 220\u2013228. Association for Computational Linguistics"},{"key":"11895_CR35","doi-asserted-by":"crossref","unstructured":"Li Z, Li Y, Lu H (2019) Improve image captioning by self-attention International conference on neural information processing, pp 91\u201398. Springer","DOI":"10.1007\/978-3-030-36802-9_11"},{"key":"11895_CR36","unstructured":"Lin CY (2004) Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp 74\u201381"},{"key":"11895_CR37","doi-asserted-by":"crossref","unstructured":"Lin TY, 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","DOI":"10.1109\/CVPR.2017.106"},{"key":"11895_CR38","doi-asserted-by":"crossref","unstructured":"Lin TY, 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, pp 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11895_CR39","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2017.345"},{"key":"11895_CR40","unstructured":"Ma X, Pino J, Cross J, Puzon L, Gu J (2019) Monotonic multihead attention. arXiv:1909.12406"},{"key":"11895_CR41","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2014) Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv:1412.6632"},{"key":"11895_CR42","unstructured":"Mitchell M, Han X, Dodge J, Mensch A, Goyal A, Berg A, Yamaguchi K, Berg T, Stratos K, Daum\u00e9 H III (2012) Midge: generating image descriptions from computer vision detections. In: Proceedings of the 13th conference of the european chapter of the association for computational linguistics, pp 747\u2013756. Association for Computational Linguistics"},{"key":"11895_CR43","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2text: describing images using 1 million captioned photographs. In: Advances in neural information processing systems, pp 1143\u20131151"},{"key":"11895_CR44","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (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":"11895_CR45","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch"},{"key":"11895_CR46","doi-asserted-by":"crossref","unstructured":"Pedersoli M, Lucas T, Schmid C, Verbeek J (2017) Areas of attention for image captioning. In: Proceedings of the IEEE international conference on computer vision, pp 1242\u20131250","DOI":"10.1109\/ICCV.2017.140"},{"issue":"6","key":"11895_CR47","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1109\/TMM.2018.2877885","volume":"21","author":"Y Peng","year":"2018","unstructured":"Peng Y, Qi J (2018) Show and tell in the loop: cross-modal circular correlation learning. IEEE Transactions on Multimedia 21(6):1538\u20131550","journal-title":"IEEE Transactions on Multimedia"},{"issue":"1-3","key":"11895_CR48","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1080\/135062800394667","volume":"7","author":"RA Rensink","year":"2000","unstructured":"Rensink RA (2000) The dynamic representation of scenes. Visual Cognition 7(1-3):17\u201342","journal-title":"Visual Cognition"},{"key":"11895_CR49","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.neucom.2019.08.012","volume":"367","author":"J Su","year":"2019","unstructured":"Su J, Tang J, Lu Z, Han X, Zhang H (2019) A neural image captioning model with caption-to-images semantic constructor. Neurocomputing 367:144\u2013151","journal-title":"Neurocomputing"},{"key":"11895_CR50","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems 27:3104\u20133112"},{"key":"11895_CR51","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"10","key":"11895_CR52","doi-asserted-by":"publisher","first-page":"2686","DOI":"10.1109\/TMM.2019.2904878","volume":"21","author":"JH Tan","year":"2019","unstructured":"Tan JH, Chan CS, Chuah JH (2019) Comic: toward a compact image captioning model with attention. IEEE Transactions on Multimedia 21(10):2686\u20132696","journal-title":"IEEE Transactions on Multimedia"},{"issue":"7","key":"11895_CR53","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.3390\/sym13071184","volume":"13","author":"P Tian","year":"2021","unstructured":"Tian P, Mo H, Jiang L (2021) Image caption generation using multi-level semantic context information. Symmetry 13(7):1184","journal-title":"Symmetry"},{"key":"11895_CR54","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":"11895_CR55","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Anne Hendricks L, Rohrbach M, Mooney R, Darrell T, Saenko K (2017) Captioning images with diverse objects. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5753\u20135761","DOI":"10.1109\/CVPR.2017.130"},{"key":"11895_CR56","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"},{"issue":"3","key":"11895_CR57","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1109\/TMM.2019.2931815","volume":"22","author":"L Wu","year":"2019","unstructured":"Wu L, Xu M, Wang J, Perry S (2019) Recall what you see continually using gridlstm in image captioning. IEEE Transactions on Multimedia 22 (3):808\u2013818","journal-title":"IEEE Transactions on Multimedia"},{"key":"11895_CR58","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 the IEEE conference on computer vision and pattern recognition, pp 203\u2013212","DOI":"10.1109\/CVPR.2016.29"},{"issue":"6","key":"11895_CR59","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2017","unstructured":"Wu Q, Shen C, Wang P, Dick A, van den Hengel A (2017) Image captioning and visual question answering based on attributes and external knowledge. IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (6):1367\u20131381","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"11895_CR60","doi-asserted-by":"publisher","first-page":"2942","DOI":"10.1109\/TMM.2019.2915033","volume":"21","author":"X Xiao","year":"2019","unstructured":"Xiao X, Wang L, Ding K, Xiang S, Pan C (2019) Deep hierarchical encoder\u2013decoder network for image captioning. IEEE Transactions on Multimedia 21(11):2942\u20132956","journal-title":"IEEE Transactions on Multimedia"},{"key":"11895_CR61","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, pp 2048\u20132057"},{"key":"11895_CR62","unstructured":"Yang Y, Teo CL, Daum\u00e9 H III, Aloimonos Y (2011) Corpus-guided sentence generation of natural images. In: Proceedings of the conference on empirical methods in natural language processing, pp 444\u2013454. Association for Computational Linguistics"},{"key":"11895_CR63","doi-asserted-by":"crossref","unstructured":"Yang Z, Zhang YJ, ur Rehman S, Huang Y (2017) Image captioning with object detection and localization. In: International conference on image and graphics, pp 109\u2013118. Springer","DOI":"10.1007\/978-3-319-71589-6_10"},{"key":"11895_CR64","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Qiu Z, Mei T (2017) Boosting image captioning with attributes. In: Proceedings of the IEEE international conference on computer vision, pp 4894\u20134902","DOI":"10.1109\/ICCV.2017.524"},{"key":"11895_CR65","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":"11895_CR66","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122"},{"issue":"6","key":"11895_CR67","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"},{"key":"11895_CR68","doi-asserted-by":"publisher","first-page":"27638","DOI":"10.1109\/ACCESS.2021.3058425","volume":"9","author":"S Zhang","year":"2021","unstructured":"Zhang S, Zhang Y, Chen Z, Li Z (2021) Vsam-based visual keyword generation for image caption. IEEE Access 9:27638\u201327649","journal-title":"IEEE Access"},{"key":"11895_CR69","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.neucom.2018.02.112","volume":"395","author":"X Zhang","year":"2020","unstructured":"Zhang X, He S, Song X, Lau RW, Jiao J, Ye Q (2020) Image captioning via semantic element embedding. Neurocomputing 395:212\u2013221","journal-title":"Neurocomputing"},{"key":"11895_CR70","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1109\/TIP.2019.2928144","volume":"29","author":"L Zhou","year":"2019","unstructured":"Zhou L, Zhang Y, Jiang YG, Zhang T, Fan W (2019) Re-caption: saliency-enhanced image captioning through two-phase learning. IEEE Trans Image Process 29:694\u2013709","journal-title":"IEEE Trans Image Process"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11895-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11895-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11895-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T16:16:44Z","timestamp":1677773804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11895-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,13]]},"references-count":70,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["11895"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11895-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,13]]},"assertion":[{"value":"27 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Jeripthula Prudiraj, Yenduri Sravani, and C. Krishna Mohan declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}