{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:22:14Z","timestamp":1791303734333,"version":"4.1.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,5,11]],"date-time":"2025-05-11T00:00:00Z","timestamp":1746921600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,11]],"date-time":"2025-05-11T00:00:00Z","timestamp":1746921600000},"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":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s13042-025-02634-9","type":"journal-article","created":{"date-parts":[[2025,5,11]],"date-time":"2025-05-11T07:07:34Z","timestamp":1746947254000},"page":"6561-6576","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing visual contextual semantic information for image captioning"],"prefix":"10.1007","volume":"16","author":[{"given":"Ronggui","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixia","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,11]]},"reference":[{"key":"2634_CR1","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2014) Show and tell: a neural image caption generator. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"2634_CR2","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville AC, Salakhutdinov R, Zemel RS, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning. https:\/\/api.semanticscholar.org\/CorpusID:1055111"},{"key":"2634_CR3","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2017) Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2634_CR4","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick RB, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2634_CR5","doi-asserted-by":"crossref","unstructured":"Luo Y, Ji J, Sun X, Cao L, Wu Y, Huang F, Lin C-W, Ji R (2021) Dual-level collaborative transformer for image captioning. arXiv:2101.06462","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"2634_CR6","doi-asserted-by":"crossref","unstructured":"Jiang H, Misra I, Rohrbach M, Learned-Miller EG, Chen X (2020) In defense of grid features for visual question answering. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10264\u201310273","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"2634_CR7","doi-asserted-by":"crossref","unstructured":"Nguyen V-Q, Suganuma M, Okatani T (2022) Grit: faster and better image captioning transformer using dual visual features. arXiv:2207.09666","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"2634_CR8","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.neunet.2022.01.011","volume":"148","author":"T Xian","year":"2022","unstructured":"Xian T, Li Z, Zhang C, Ma H (2022) Dual global enhanced transformer for image captioning. Neural Netw 148:129\u2013141","journal-title":"Neural Netw"},{"key":"2634_CR9","doi-asserted-by":"crossref","unstructured":"Wu M-K, Zhang X, Sun X, Zhou Y, Chen C, Gu J, Sun X, Ji R (2022) Difnet: boosting visual information flow for image captioning. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 17999\u201318008","DOI":"10.1109\/CVPR52688.2022.01749"},{"key":"2634_CR10","doi-asserted-by":"crossref","unstructured":"Xiong Y, Liao R, Zhao H, Hu R, Bai M, Yumer E, Urtasun R (2019) Upsnet: a unified panoptic segmentation network. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 8810\u20138818","DOI":"10.1109\/CVPR.2019.00902"},{"key":"2634_CR11","doi-asserted-by":"crossref","unstructured":"Zeng P, Zhang H, Song J, Gao L (2022) S2 transformer for image captioning. In: International joint conference on artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:250630409","DOI":"10.24963\/ijcai.2022\/224"},{"key":"2634_CR12","doi-asserted-by":"crossref","unstructured":"Gao Y-M, Wang N, Suo W, Sun M, Wang P (2022) Improving image captioning via enhancing dual-side context awareness. In: Proceedings of the 2022 international conference on multimedia retrieval","DOI":"10.1145\/3512527.3531379"},{"key":"2634_CR13","doi-asserted-by":"publisher","first-page":"3723","DOI":"10.1109\/TMM.2022.3164787","volume":"25","author":"Y Ma","year":"2023","unstructured":"Ma Y, Ji J, Sun X, Zhou Y, Wu Y, Huang F, Ji R (2023) Knowing what it is: semantic-enhanced dual attention transformer. IEEE Trans Multim 25:3723\u20133736","journal-title":"IEEE Trans Multim"},{"key":"2634_CR14","doi-asserted-by":"crossref","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. https:\/\/api.semanticscholar.org\/CorpusID:13272863","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"2634_CR15","unstructured":"Gupta A, Verma Y, Jawahar CV (2012) Choosing linguistics over vision to describe images. In: AAAI conference on artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:16610834"},{"key":"2634_CR16","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2text: describing images using 1 million captioned photographs. In: Neural information processing systems. https:\/\/api.semanticscholar.org\/CorpusID:14579301"},{"key":"2634_CR17","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, Li S, Choi Y, Berg AC, Berg TL (2013) Babytalk: understanding and generating simple image descriptions. IEEE Trans Pattern Anal Mach Intell 35:2891\u20132903","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2634_CR18","unstructured":"Mitchell M, Dodge J, Goyal A, Yamaguchi K, Stratos K, Han X, Mensch AC, Berg AC, Berg TL, Daum\u00e9 H (2012) Midge: generating image descriptions from computer vision detections. In: Conference of the European chapter of the association for computational linguistics. https:\/\/api.semanticscholar.org\/CorpusID:2972357"},{"key":"2634_CR19","doi-asserted-by":"crossref","unstructured":"Ushiku Y, Yamaguchi M, Mukuta Y, Harada T (2015) Common subspace for model and similarity: phrase learning for caption generation from images. 2015 IEEE international conference on computer vision (ICCV), pp 2668\u20132676","DOI":"10.1109\/ICCV.2015.306"},{"key":"2634_CR20","unstructured":"Mao J, Xu W, Yang Y, Wang J, Yuille AL (2014) Explain images with multimodal recurrent neural networks. arXiv:1410.1090"},{"key":"2634_CR21","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2018) Exploring visual relationship for image captioning. In: European conference on computer vision. https:\/\/api.semanticscholar.org\/CorpusID:52304560","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"2634_CR22","doi-asserted-by":"crossref","unstructured":"Huang L, Wang W, Chen J, Wei X-Y (2019) Attention on attention for image captioning. In: 2019 IEEE\/CVF international conference on computer vision (ICCV), pp 4633\u20134642","DOI":"10.1109\/ICCV.2019.00473"},{"key":"2634_CR23","doi-asserted-by":"crossref","unstructured":"Pan Y, Yao T, Li Y, Mei T (2020) X-linear attention networks for image captioning. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10968\u201310977","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"2634_CR24","doi-asserted-by":"crossref","unstructured":"Cornia M, Stefanini M, Baraldi L, Cucchiara R (2019) Meshed-memory transformer for image captioning. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10575\u201310584","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"2634_CR25","doi-asserted-by":"crossref","unstructured":"Guo L, Liu J, Zhu X, Yao P, Lu S, Lu H (2020) Normalized and geometry-aware self-attention network for image captioning. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10324\u201310333","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"2634_CR26","doi-asserted-by":"crossref","unstructured":"Li G, Zhu L, Liu P, Yang Y (2019) Entangled transformer for image captioning. In: 2019 IEEE\/CVF international conference on computer vision (ICCV), pp 8927\u20138936","DOI":"10.1109\/ICCV.2019.00902"},{"key":"2634_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109420","volume":"138","author":"Y Ma","year":"2023","unstructured":"Ma Y, Ji J, Sun X, Zhou Y, Ji R (2023) Towards local visual modeling for image captioning. Pattern Recognit 138:109420","journal-title":"Pattern Recognit"},{"key":"2634_CR28","doi-asserted-by":"crossref","unstructured":"Zhang X, Sun X, Luo Y, Ji J, Zhou Y, Wu Y, Huang F, Ji R (2021) Rstnet: captioning with adaptive attention on visual and non-visual words. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 15460\u201315469","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"2634_CR29","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu J, Sun Y (2022) End-to-end transformer based model for image captioning. In: AAAI conference on artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:247778466","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"2634_CR30","doi-asserted-by":"publisher","first-page":"3962","DOI":"10.1109\/TMM.2022.3169061","volume":"25","author":"J Ji","year":"2023","unstructured":"Ji J, Huang X, Sun X, Zhou Y, Luo G, Cao L, Liu J, Shao L, Ji R (2023) Multi-branch distance-sensitive self-attention network for image captioning. IEEE Trans Multim 25:3962\u20133974","journal-title":"IEEE Trans Multim"},{"key":"2634_CR31","doi-asserted-by":"crossref","unstructured":"Fei Z (2022) Attention-aligned transformer for image captioning. In: AAAI conference on artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:250288254","DOI":"10.1609\/aaai.v36i1.19940"},{"key":"2634_CR32","doi-asserted-by":"publisher","first-page":"4829","DOI":"10.1109\/TCSVT.2023.3336371","volume":"34","author":"H Zhang","year":"2024","unstructured":"Zhang H, Zeng P, Gao L, Lyu X, Song J, Shen HT (2024) Spt: spatial pyramid transformer for image captioning. IEEE Trans Circuits Syst Video Technol 34:4829\u20134842","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2634_CR33","doi-asserted-by":"publisher","first-page":"7706","DOI":"10.1109\/TCSVT.2022.3181490","volume":"32","author":"W Jiang","year":"2022","unstructured":"Jiang W, Zhou W, Hu H (2022) Double-stream position learning transformer network for image captioning. IEEE Trans Circuits Syst Video Technol 32:7706\u20137718","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2634_CR34","doi-asserted-by":"publisher","first-page":"5762","DOI":"10.1109\/TCSVT.2022.3155795","volume":"32","author":"T Xian","year":"2022","unstructured":"Xian T, Li Z, Tang Z, Ma H (2022) Adaptive path selection for dynamic image captioning. IEEE Trans Circuits Syst Video Technol 32:5762\u20135775","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2634_CR35","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.1109\/TCSVT.2023.3243725","volume":"33","author":"J Zhang","year":"2023","unstructured":"Zhang J, Xie Y, Ding W, Wang Z (2023) Cross on cross attention: deep fusion transformer for image captioning. IEEE Trans Circuits Syst Video Technol 33:4257\u20134268","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2634_CR36","first-page":"1","volume":"73","author":"Y Shi","year":"2024","unstructured":"Shi Y, Xia J, Zhou M, Cao Z (2024) A dual-feature-based adaptive shared transformer network for image captioning. IEEE Trans Instrum Meas 73:1\u201313","journal-title":"IEEE Trans Instrum Meas"},{"key":"2634_CR37","unstructured":"Vaswani A, Shazeer NM, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Neural information processing systems. https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"2634_CR38","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2016) Self-critical sequence training for image captioning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1179\u20131195","DOI":"10.1109\/CVPR.2017.131"},{"key":"2634_CR39","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie SJ, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. https:\/\/api.semanticscholar.org\/CorpusID:14113767","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2634_CR40","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2014) Deep visual-semantic alignments for generating image descriptions. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"2634_CR41","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: Annual meeting of the association for computational linguistics. https:\/\/api.semanticscholar.org\/CorpusID:11080756","DOI":"10.3115\/1073083.1073135"},{"key":"2634_CR42","unstructured":"Banerjee S, Lavie A (2005) Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: IEEvaluation@ACL. https:\/\/api.semanticscholar.org\/CorpusID:7164502"},{"key":"2634_CR43","unstructured":"Lin C-Y (2004) Rouge: a package for automatic evaluation of summaries. In: Annual meeting of the association for computational linguistics. https:\/\/api.semanticscholar.org\/CorpusID:964287"},{"key":"2634_CR44","doi-asserted-by":"crossref","unstructured":"Vedantam R, Zitnick CL, Parikh D (2014) Cider: consensus-based image description evaluation. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2634_CR45","doi-asserted-by":"crossref","unstructured":"Anderson P, Fernando B, Johnson M, Gould S (2016) Spice: semantic propositional image caption evaluation. arXiv:1607.08822","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"2634_CR46","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, K\u00f6pf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) Pytorch: an imperative style, high-performance deep learning library. arXiv:1912.01703"},{"key":"2634_CR62","doi-asserted-by":"crossref","unstructured":"Jiang W, Ma L, Jiang YG, Liu W, Zhang T (2018) Recurrent fusion network for image captioning [A]. European Conference on Computer Vision[C]","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"2634_CR47","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. CoRR. arXiv:1412.6980"},{"key":"2634_CR48","doi-asserted-by":"crossref","unstructured":"Yang X, Tang K, Zhang H, Cai J (2018) Auto-encoding scene graphs for image captioning. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10677\u201310686","DOI":"10.1109\/CVPR.2019.01094"},{"key":"2634_CR49","unstructured":"Herdade S, Kappeler A, Boakye K, Soares J (2019) Image captioning: transforming objects into words. In: Neural information processing systems. https:\/\/api.semanticscholar.org\/CorpusID:189898359"},{"key":"2634_CR50","doi-asserted-by":"crossref","unstructured":"Fan Z, Wei Z, Wang S, Wang R, Li Z, Shan H, Huang X (2021) Tcic: theme concepts learning cross language and vision for image captioning. arXiv:2106.10936","DOI":"10.24963\/ijcai.2021\/91"},{"key":"2634_CR51","first-page":"1","volume":"12","author":"Z Jiang","year":"2023","unstructured":"Jiang Z, Wang X, Zhai Z, Cheng B (2023) Lg-mlformer: local and global mlp for image captioning. Int J Multim Inf Retriev 12:1\u201313","journal-title":"Int J Multim Inf Retriev"},{"key":"2634_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102377","volume":"77","author":"L Chen","year":"2023","unstructured":"Chen L, Yang Y, Hu J, Pan L, Zhai H (2023) Relational-convergent transformer for image captioning. Displays 77:102377","journal-title":"Displays"},{"key":"2634_CR53","doi-asserted-by":"publisher","first-page":"98","DOI":"10.5755\/j01.itc.53.1.35095","volume":"53","author":"H Zhang","year":"2024","unstructured":"Zhang H, Xu C, Xu B, Jian M, Liu H, Li X (2024) Tsic-clip: traffic scene image captioning model based on clip. Inf Technol Control 53:98\u2013114","journal-title":"Inf Technol Control"},{"key":"2634_CR54","doi-asserted-by":"crossref","unstructured":"Cheng Y, Huang F, Zhou L, Jin C, Zhang Y, Zhang T (2017) A hierarchical multimodal attention-based neural network for image captioning. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval","DOI":"10.1145\/3077136.3080671"},{"key":"2634_CR55","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1109\/TMM.2017.2751140","volume":"20","author":"L Li","year":"2018","unstructured":"Li L, Tang S, Zhang Y, Deng L, Tian Q (2018) Gla: global-local attention for image description. IEEE Trans Multim 20:726\u2013737","journal-title":"IEEE Trans Multim"},{"key":"2634_CR56","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-decoder network for image captioning. IEEE Trans Multim 21:2942\u20132956","journal-title":"IEEE Trans Multim"},{"key":"2634_CR57","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.neucom.2019.04.095","volume":"398","author":"S Ding","year":"2020","unstructured":"Ding S, Qu S, Xi Y, Wan S (2020) Stimulus-driven and concept-driven analysis for image caption generation. Neurocomputing 398:520\u2013530","journal-title":"Neurocomputing"},{"key":"2634_CR58","doi-asserted-by":"publisher","first-page":"6575","DOI":"10.1007\/s10489-021-02734-3","volume":"52","author":"C Wang","year":"2021","unstructured":"Wang C, Gu X (2021) Image captioning with adaptive incremental global context attention. Appl Intell 52:6575\u20136597","journal-title":"Appl Intell"},{"key":"2634_CR59","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"2634_CR60","doi-asserted-by":"crossref","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2016) Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 3242\u20133250","DOI":"10.1109\/CVPR.2017.345"},{"key":"2634_CR61","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TMM.2020.2976552","volume":"23","author":"J Zhang","year":"2021","unstructured":"Zhang J, Mei K, Zheng Y, Fan J (2021) Integrating part of speech guidance for image captioning. IEEE Trans Multim 23:92\u2013104","journal-title":"IEEE Trans Multim"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02634-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02634-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02634-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:01:36Z","timestamp":1757156496000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02634-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,11]]},"references-count":62,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["2634"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02634-9","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,11]]},"assertion":[{"value":"20 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}