{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T21:27:30Z","timestamp":1773091650279,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61877031"],"award-info":[{"award-number":["61877031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012135","name":"Jiangxi Normal University","doi-asserted-by":"publisher","award":["YJS2022029"],"award-info":[{"award-number":["YJS2022029"]}],"id":[{"id":"10.13039\/501100012135","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00530-023-01130-w","type":"journal-article","created":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T12:01:31Z","timestamp":1689422491000},"page":"2469-2482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal-enhanced hierarchical attention network for video captioning"],"prefix":"10.1007","volume":"29","author":[{"given":"Maosheng","family":"Zhong","sequence":"first","affiliation":[]},{"given":"Youde","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Zhixiang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,15]]},"reference":[{"key":"1130_CR1","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2625-2634) (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1130_CR2","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729 (2014)","DOI":"10.3115\/v1\/N15-1173"},{"key":"1130_CR3","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In Proceedings of the IEEE international conference on computer vision (pp. 4507-4515) (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"1130_CR4","doi-asserted-by":"crossref","unstructured":"Xu, J., Yao, T., Zhang, Y., Mei, T.: Learning multimodal attention LSTM networks for video captioning. In Proceedings of the 25th ACM international conference on Multimedia (pp. 537-545) (2017, October)","DOI":"10.1145\/3123266.3123448"},{"issue":"1","key":"1130_CR5","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/s00530-021-00816-3","volume":"28","author":"A Singh","year":"2022","unstructured":"Singh, A., Singh, T.D., Bandyopadhyay, S.: Attention based video captioning framework for hindi. Multimedia Syst. 28(1), 195\u2013207 (2022)","journal-title":"Multimedia Syst."},{"key":"1130_CR6","unstructured":"Zhong, M., Zhang, H., Xiong, H., Chen, Y., Wang, M., Zhou, X.: Kgvideo: A Video Captioning Method Based on Object Detection and Knowledge Graph. Available at SSRN 4017055"},{"issue":"5","key":"1130_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-022-01329-3","volume":"33","author":"M Zhong","year":"2022","unstructured":"Zhong, M., Zhang, H., Wang, Y., Xiong, H.: BiTransformer: augmenting semantic context in video captioning via bidirectional decoder. Mach. Vis. Appl. 33(5), 1\u20139 (2022)","journal-title":"Mach. Vis. Appl."},{"key":"1130_CR8","doi-asserted-by":"crossref","unstructured":"Yang, B., Zhang, T., Zou, Y.: (2022) CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter. In: Pattern Recognition and Computer Vision: 5th Chinese Conference. PRCV,: Shenzhen, China, November 4?7, 2022, Proceedings, Part I, pp. 368\u2013381. Springer International Publishing, Cham (2022)","DOI":"10.1007\/978-3-031-18907-4_29"},{"key":"1130_CR9","doi-asserted-by":"crossref","unstructured":"Hori, C., Hori, T., Lee, T. Y., Zhang, Z., Harsham, B., Hershey, J. R., ... Sumi, K.: Attention-based multimodal fusion for video description. In Proceedings of the IEEE international conference on computer vision (pp. 4193-4202) (2017)","DOI":"10.1109\/ICCV.2017.450"},{"issue":"1","key":"1130_CR10","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1130_CR11","doi-asserted-by":"crossref","unstructured":"Aafaq, N., Akhtar, N., Liu, W., Gilani, S. Z., & Mian, A.: Spatio-temporal dynamics and semantic attribute enriched visual encoding for video captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 12487-12496) (2019)","DOI":"10.1109\/CVPR.2019.01277"},{"key":"1130_CR12","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: 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. 6077-6086) (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"issue":"22","key":"1130_CR13","doi-asserted-by":"publisher","first-page":"31793","DOI":"10.1007\/s11042-019-08011-3","volume":"78","author":"JY Lee","year":"2019","unstructured":"Lee, J.Y.: Deep multimodal embedding for video captioning. Multimedia Tools Appl. 78(22), 31793\u201331805 (2019)","journal-title":"Multimedia Tools Appl."},{"key":"1130_CR14","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.cviu.2017.04.013","volume":"163","author":"AA Liu","year":"2017","unstructured":"Liu, A.A., Xu, N., Wong, Y., Li, J., Su, Y.T., Kankanhalli, M.: Hierarchical & multimodal video captioning: Discovering and transferring multimodal knowledge for vision to language. Comput. Vis. Image Underst. 163, 113\u2013125 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"1130_CR15","doi-asserted-by":"crossref","unstructured":"Jin, Q., Chen, J., Chen, S., Xiong, Y., & Hauptmann, A.: Describing videos using multi-modal fusion. In Proceedings of the 24th ACM international conference on Multimedia (pp. 1087-1091) (2016, October)","DOI":"10.1145\/2964284.2984065"},{"issue":"48","key":"1130_CR16","first-page":"975","volume":"181","author":"Y Jiang","year":"2019","unstructured":"Jiang, Y.: Multi-feature fusion for video captioning. Int. J. Comput. Appl. 181(48), 975\u20138887 (2019)","journal-title":"Int. J. Comput. Appl."},{"key":"1130_CR17","doi-asserted-by":"crossref","unstructured":"Li, L., Zhang, Y., Tang, S., Xie, L., Li, X.,  Tian, Q.: Adaptive spatial location with balanced loss for video captioning. IEEE Trans. Circuits Syst. Video Technol. 32(1), 17\u201330 (2020)","DOI":"10.1109\/TCSVT.2020.3045735"},{"key":"1130_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Y., Cai, Q., Xu, S., Chen, J.: Xlanv model with adaptively multi-modality feature fusing for video captioning. In Proceedings of the 28th ACM International Conference on Multimedia (pp. 4600-4604) (2020, October)","DOI":"10.1145\/3394171.3416290"},{"key":"1130_CR19","doi-asserted-by":"crossref","unstructured":"Yan, Z., Chen, Y., Song, J., Zhu, J.: Multimodal feature fusion based on object relation for video captioning. CAAI Trans. Intell. Technol. 8(1), 247\u2013259 (2023)","DOI":"10.1049\/cit2.12071"},{"key":"1130_CR20","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G. E.: ImageNet classification with deep convolutional neural networks. Commun ACM 60(6), 84\u201390 (2017)","DOI":"10.1145\/3065386"},{"issue":"8","key":"1130_CR21","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1130_CR22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... Polosukhin, I.: Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (pp. 6000\u20136010) (2017)"},{"key":"1130_CR23","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., ... Sutskever, I.: Learning transferable visual models from natural language supervision. In International conference on machine learning (pp. 8748-8763). PMLR (2021, July)"},{"key":"1130_CR24","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A. A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI conference on artificial intelligence (2017, February)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1130_CR25","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6299-6308) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1130_CR26","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., ... Zisserman, A.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"1130_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollr, P., Girshick, R.: Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961\u20132969) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1130_CR28","unstructured":"Bordes, A., Usunier, N., Garcia-Dur\u00e1n, A., Weston, J., & Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2 (pp. 2787\u20132795) (2013)"},{"key":"1130_CR29","doi-asserted-by":"crossref","unstructured":"Han, X., Cao, S., Lv, X., Lin, Y., Liu, Z., Sun, M., Li, J.: Openke: An open toolkit for knowledge embedding. In Proceedings of the 2018 conference on empirical methods in natural language processing: system demonstrations (pp. 139-144) (2018, November)","DOI":"10.18653\/v1\/D18-2024"},{"key":"1130_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., ... Zitnick, C. L.: Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740-755). Springer, Cham (2014, September)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1130_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Dollr, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117-2125) (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1130_CR32","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J.: Faster R-CNN: towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell 39(6), 1137\u20131149 (2017)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1130_CR33","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"1130_CR34","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Liu, W.: Reconstruction network for video captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7622-7631) (2018)","DOI":"10.1109\/CVPR.2018.00795"},{"key":"1130_CR35","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.1109\/TMM.2020.3002669","volume":"23","author":"W Xu","year":"2020","unstructured":"Xu, W., Yu, J., Miao, Z., Wan, L., Tian, Y., Ji, Q.: Deep reinforcement polishing network for video captioning. IEEE Trans. Multimedia 23, 1772\u20131784 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"1130_CR36","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, S., Zhang, W., Huang, Q.: Less is more: Picking informative frames for video captioning. In Proceedings of the European conference on computer vision (ECCV) (pp. 358-373) (2018)","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"1130_CR37","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s00530-018-0598-5","volume":"25","author":"N Xu","year":"2019","unstructured":"Xu, N., Liu, A.A., Nie, W., Su, Y.: Multi-guiding long short-term memory for video captioning. Multimedia Syst. 25, 663\u2013672 (2019)","journal-title":"Multimedia Syst."},{"key":"1130_CR38","doi-asserted-by":"crossref","unstructured":"Chen, J., Pan, Y., Li, Y., Yao, T., Chao, H., Mei, T.: Temporal deformable convolutional encoder-decoder networks for video captioning. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 8167-8174) (2019, July)","DOI":"10.1609\/aaai.v33i01.33018167"},{"issue":"1","key":"1130_CR39","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/TCSVT.2020.3045735","volume":"32","author":"L Li","year":"2022","unstructured":"Li, L., Zhang, Y., Tang, S., Xie, L., Li, X., Tian, Q.: Adaptive spatial location with balanced loss for video captioning. IEEE Trans. Circuits Syst. Video Technol. 32(1), 17\u201330 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1130_CR40","unstructured":"Wenjie, Pei., Jiyuan, Zhang., Xiangrong, Wang., Lei, Ke., Xi-aoyong, Shen., Yu-Wing, Tai.: Memory-attended recurrentnetwork for video captioning. In CVPR, pages 8347?8356, (2019)"},{"issue":"4","key":"1130_CR41","doi-asserted-by":"publisher","first-page":"3119","DOI":"10.1609\/aaai.v35i4.16421","volume":"35","author":"B Yang","year":"2021","unstructured":"Yang, B., Zou, Y., Liu, F., Zhang, C.: Non-autoregressive coarse-to-fine video captioning. Proc. AAAI Conf. Artif. Intell. 35(4), 3119\u20133127 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i4.16421","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"1130_CR42","doi-asserted-by":"crossref","unstructured":"Chen, S., & Jiang, Y. G.: Motion guided region message passing for video captioning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 1543-1552) (2021)","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"1130_CR43","doi-asserted-by":"crossref","unstructured":"Vaidya, J., Subramaniam, A., Mittal, A.: Co-Segmentation Aided Two-Stream Architecture for Video Captioning. In Proceedings of the IEEE\/CVF Win ter Conference on Applications of Computer Vision (pp. 2774-2784) (2022)","DOI":"10.1109\/WACV51458.2022.00250"},{"issue":"2","key":"1130_CR44","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1109\/TCSVT.2021.3063423","volume":"32","author":"J Deng","year":"2022","unstructured":"Deng, J., Li, L., Zhang, B., Wang, S., Zha, Z., Huang, Q.: Syntax-guided hierarchical attention network for video captioning. IEEE Trans. Circuits Syst. Video Technol. 32(2), 880\u2013892 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3063423","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1130_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Shi, Y., Yuan, C., Li, B., Wang, P., Hu, W., Zha, Z. J.: Object relational graph with teacher-recommended learning for video captioning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13278-13288) (2020)","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"1130_CR46","doi-asserted-by":"crossref","unstructured":"Wu, B., Niu, G., Yu, J., Xiao, X., Zhang, J., Wu, H.: Towards Knowledge-aware Video Captioning via Transitive Visual Relationship Detection. IEEE Transactions on Circuits and Systems for Video Technology. (2022)","DOI":"10.1109\/TCSVT.2022.3169894"},{"key":"1130_CR47","doi-asserted-by":"crossref","unstructured":"Ye, H., Li, G., Qi, Y., Wang, S., Huang, Q., Yang, M.: Hierarchical Modular Network for Video Captioning. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022, 17918\u201317927 (2022)","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"1130_CR48","unstructured":"Chen, D., Dolan, W. B.: Collecting highly parallel data for paraphrase evaluation. In Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies (pp. 190-200) (2011, June)"},{"key":"1130_CR49","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: Msr-vtt: A large video description dataset for bridging video and language. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5288-5296) (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"1130_CR50","doi-asserted-by":"crossref","unstructured":"Pei, W., Zhang, J., Wang, X., Ke, L., Shen, X., Tai, Y. W.: Memory-attended recurrent network for video captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 8347-8356) (2019)","DOI":"10.1109\/CVPR.2019.00854"},{"key":"1130_CR51","doi-asserted-by":"crossref","unstructured":"Pan, B., Cai, H., Huang, D. A., Lee, K. H., Gaidon, A., Adeli, E., Niebles, J.C.: Spatio-temporal graph for video captioning with knowledge distillation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 10870-10879) (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"1130_CR52","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W. J.: Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics (pp. 311-318) (2002, July)","DOI":"10.3115\/1073083.1073135"},{"key":"1130_CR53","unstructured":"Banerjee, S., Lavie, A.: 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. 65-72) (2005, June)"},{"key":"1130_CR54","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4566-4575) (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1130_CR55","unstructured":"Lin, C. Y.: Rouge: a package for automatic evaluation of summaries. In Text summarization branches out (pp. 74\u201381) (2004)"},{"key":"1130_CR56","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C. D.: Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532-1543) (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1130_CR57","doi-asserted-by":"crossref","unstructured":"Novikova, J., Du?ek, O., Curry, A. C., Rieser, V.: Why We Need New Evaluation Metrics for NLG. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (pp. 2241-2252) (2017)","DOI":"10.18653\/v1\/D17-1238"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01130-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01130-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01130-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T13:11:01Z","timestamp":1694783461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01130-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":57,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1130"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01130-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,15]]},"assertion":[{"value":"18 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}