{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:39:34Z","timestamp":1781584774070,"version":"3.54.5"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T00:00:00Z","timestamp":1708128000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T00:00:00Z","timestamp":1708128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0900701"],"award-info":[{"award-number":["2021YFF0900701"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0900701"],"award-info":[{"award-number":["2021YFF0900701"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0900701"],"award-info":[{"award-number":["2021YFF0900701"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801441"],"award-info":[{"award-number":["61801441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801441"],"award-info":[{"award-number":["61801441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801441"],"award-info":[{"award-number":["61801441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Construction Project of \u201cBeijing top notch\u201dDiscipline"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In the text-video retrieval task, the objective is to calculate the similarity between a text and a video, and rank the relevant candidates higher. Most existing methods only consider the text-video semantic alignment in the global view. But using mean-pooling to obtain global semantics and simply aligning text and video in the global view may lead to semantic bias. In addition, some methods utilize offline object detectors or sentence parsers to obtain entity-level information in text and video and achieve local alignment. However, inaccurate detection introduces possible errors and such approaches prevent models from being trained end-to-end for retrieval. To overcome these limitations, we propose multi-grained and semantic-guided alignment for text-video retrieval in this paper, which can achieve fine-grained alignment based on video frames and text words, local alignment based on semantic centers, and global alignment. Specially, we explore summary semantics of text and video to guide the local alignment based on semantic centers for we believe that the importance of each semantic center is determined by summary semantics. We evaluate our approach on four benchmark datasets of MSRVTT, MSVD, ActivityNet Captions, and DiDeMo, achieving better performance than most existing methods.<\/jats:p>","DOI":"10.1007\/s11063-024-11468-5","type":"journal-article","created":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T05:02:11Z","timestamp":1708146131000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MGSGA: Multi-grained and Semantic-Guided Alignment for Text-Video Retrieval"],"prefix":"10.1007","volume":"56","author":[{"given":"Xiaoyu","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayao","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,17]]},"reference":[{"key":"11468_CR1","unstructured":"Miech A, Laptev I, Sivic J (2018) Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516"},{"key":"11468_CR2","unstructured":"Liu Y, Albanie S, Nagrani A, Zisserman A (2019) Use what you have: video retrieval using representations from collaborative experts. In: 30th British machine vision conference, p 279"},{"key":"11468_CR3","doi-asserted-by":"crossref","unstructured":"Gabeur V, Sun C, Alahari K, Schmid C (2020) Multi-modal transformer for video retrieval. In: European conference on computer vision, pp 214\u2013229","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"11468_CR4","doi-asserted-by":"crossref","unstructured":"Dzabraev M, Kalashnikov M, Komkov S, Petiushko A (2021) Mdmmt: multidomain multimodal transformer for video retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3354\u20133363","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"11468_CR5","unstructured":"Kunitsyn A, Kalashnikov M, Dzabraev M, Ivaniuta A (2022) Mdmmt-2: multidomain multimodal transformer for video retrieval, one more step towards generalization. arXiv preprint arXiv:2203.07086"},{"key":"11468_CR6","doi-asserted-by":"crossref","unstructured":"Wang X, Zhu L, Yang Y (2021) T2vlad: global-local sequence alignment for text-video retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5079\u20135088","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"11468_CR7","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"},{"key":"11468_CR8","doi-asserted-by":"crossref","unstructured":"Gemmeke JF, Ellis DP, Freedman D, Jansen A, Lawrence W, Moore RC, Plakal M, Ritter M (2017) Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE international conference on acoustics, speech and signal processing, pp 776\u2013780","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"11468_CR9","doi-asserted-by":"crossref","unstructured":"Xie S, Sun C, Huang J, Tu Z, Murphy K (2018) Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision, pp 305\u2013321","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"11468_CR10","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning, pp 8748\u20138763"},{"key":"11468_CR11","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo H, Ji L, Zhong M, Chen Y, Lei W, Duan N, Li T (2022) Clip4clip: an empirical study of CLIP for end to end video clip retrieval and captioning. Neurocomputing 508:293\u2013304","journal-title":"Neurocomputing"},{"key":"11468_CR12","unstructured":"Fang H, Xiong P, Xu L, Chen Y (2021) Clip2video: mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097"},{"key":"11468_CR13","unstructured":"Gao Z, Liu J, Chen S, Chang D, Zhang H, Yuan J (2021) Clip2tv: an empirical study on transformer-based methods for video-text retrieval. arXiv preprint arXiv:2111.05610"},{"key":"11468_CR14","unstructured":"Cheng X, Lin H, Wu X, Yang F, Shen D (2021) Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv preprint arXiv:2109.04290"},{"key":"11468_CR15","doi-asserted-by":"crossref","unstructured":"Wu P, He X, Tang M, Lv Y, Liu J (2021) Hanet: hierarchical alignment networks for video-text retrieval. In: Proceedings of the 29th ACM international conference on multimedia, pp 3518\u20133527","DOI":"10.1145\/3474085.3475515"},{"key":"11468_CR16","doi-asserted-by":"crossref","unstructured":"Satar B, Hongyuan Z, Bresson X, Lim JH (2021) Semantic role aware correlation transformer for text to video retrieval. In: 2021 IEEE international conference on image processing, pp 1334\u20131338","DOI":"10.1109\/ICIP42928.2021.9506267"},{"key":"11468_CR17","doi-asserted-by":"crossref","unstructured":"Chen S, Zhao Y, Jin Q, Wu Q (2020) Fine-grained video-text retrieval with hierarchical graph reasoning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10638\u201310647","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"11468_CR18","doi-asserted-by":"crossref","unstructured":"Madasu A, Aflalo E, Stan GBM, Tseng S, Bertasius G, Lal V (2023) Improving video retrieval using multilingual knowledge transfer. In: Advances in information retrieval-45th European conference on information retrieval, pp 669\u2013684","DOI":"10.1007\/978-3-031-28244-7_42"},{"key":"11468_CR19","doi-asserted-by":"crossref","unstructured":"Gorti SK, Vouitsis N, Ma J, Golestan K, Volkovs M, Garg A, Yu G (2022) X-pool: cross-modal language-video attention for text-video retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5006\u20135015","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"11468_CR20","doi-asserted-by":"crossref","unstructured":"Zhao S, Zhu L, Wang X, Yang Y (2022) Centerclip: token clustering for efficient text-video retrieval. In: The 45th international ACM SIGIR conference on research and development in information retrieval, pp 970\u2013981","DOI":"10.1145\/3477495.3531950"},{"key":"11468_CR21","doi-asserted-by":"crossref","unstructured":"Liu Y, Xiong P, Xu L, Cao S, Jin Q (2022) Ts2-net: token shift and selection transformer for text-video retrieval. In: European conference on computer vision, pp 319\u2013335","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"11468_CR22","unstructured":"Zhang B, Jin X, Gong W, Xu K, Zhang Z, Wang P, Shen X, Feng J (2023) Multimodal video adapter for parameter efficient video text retrieval. arXiv preprint arXiv:2301.07868"},{"key":"11468_CR23","unstructured":"Jiang H, Zhang J, Huang R, Ge C, Ni Z, Lu J, Zhou J, Song S, Huang G (2022) Cross-modal adapter for text-video retrieval. arXiv preprint arXiv:2211.09623"},{"key":"11468_CR24","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30, Annual conference on neural information processing systems, pp 5998\u20136008"},{"key":"11468_CR25","doi-asserted-by":"crossref","unstructured":"Chen Y, Li L, Yu L, Kholy AE, Ahmed F, Gan Z, Cheng Y, Liu J (2020) UNITER: universal image-text representation learning. In: European conference on computer vision, pp 104\u2013120","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"11468_CR26","doi-asserted-by":"crossref","unstructured":"Li X, Yin X, Li C, Zhang P, Hu X, Zhang L, Wang L, Hu H, Dong L, Wei F, Choi Y, Gao J (2020) Oscar: object-semantics aligned pre-training for vision-language tasks. In: European conference on computer vision, pp 121\u2013137","DOI":"10.1007\/978-3-030-58577-8_8"},{"issue":"4","key":"11468_CR27","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1145\/3451390","volume":"17","author":"N Messina","year":"2021","unstructured":"Messina N, Amato G, Esuli A, Falchi F, Gennaro C, Marchand-Maillet S (2021) Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. ACM Trans Multimed Comput Commun Appl 17(4):128\u2013112823","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"11468_CR28","unstructured":"Ren S, He K, Girshick RB, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems 28: annual conference on neural information processing systems 2015, pp 91\u201399"},{"key":"11468_CR29","doi-asserted-by":"publisher","first-page":"9189","DOI":"10.1109\/TMM.2023.3248160","volume":"25","author":"J Guo","year":"2023","unstructured":"Guo J, Wang M, Zhou Y, Song B, Chi Y, Fan W, Chang J (2023) HGAN: hierarchical graph alignment network for image-text retrieval. IEEE Trans Multimed 25:9189\u20139202","journal-title":"IEEE Trans Multimed"},{"key":"11468_CR30","doi-asserted-by":"crossref","unstructured":"Dong J, Li X, Xu C, Ji S, He Y, Yang G, Wang X (2019) Dual encoding for zero-example video retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9346\u20139355","DOI":"10.1109\/CVPR.2019.00957"},{"key":"11468_CR31","doi-asserted-by":"crossref","unstructured":"Feng Z, Zeng Z, Guo C, Li Z (2020) Exploiting visual semantic reasoning for video-text retrieval. In: Proceedings of the twenty-ninth international joint conference on artificial intelligence, pp 1005\u20131011","DOI":"10.24963\/ijcai.2020\/140"},{"key":"11468_CR32","doi-asserted-by":"crossref","unstructured":"Ge Y, Ge Y, Liu X, Li D, Shan Y, Qie X, Luo P (2022) Bridging video-text retrieval with multiple choice questions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16167\u201316176","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"11468_CR33","doi-asserted-by":"crossref","unstructured":"Wang H, Xu D, He D, Li F, Ji Z, Han J, Ding E (2022) Boosting video-text retrieval with explicit high-level semantics. In: Proceedings of the 30th ACM international conference on multimedia, pp 4887\u20134898","DOI":"10.1145\/3503161.3548010"},{"key":"11468_CR34","doi-asserted-by":"crossref","unstructured":"Arandjelovic R, Gronat P, Torii A, Pajdla T, Sivic J (2016) NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5297\u20135307","DOI":"10.1109\/CVPR.2016.572"},{"key":"11468_CR35","unstructured":"Oord Avd, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"11468_CR36","doi-asserted-by":"crossref","unstructured":"Xu J, Mei T, Yao T, Rui Y (2016) 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\u20135296","DOI":"10.1109\/CVPR.2016.571"},{"key":"11468_CR37","unstructured":"Chen D, Dolan WB (2011) 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\u2013200"},{"key":"11468_CR38","doi-asserted-by":"crossref","unstructured":"Krishna R, Hata K, Ren F, Fei-Fei L, Carlos\u00a0Niebles J (2017) Dense-captioning events in videos. In: Proceedings of the IEEE international conference on computer vision, pp 706\u2013715","DOI":"10.1109\/ICCV.2017.83"},{"key":"11468_CR39","doi-asserted-by":"crossref","unstructured":"Anne\u00a0Hendricks L, Wang O, Shechtman E, Sivic J, Darrell T, Russell B (2017) Localizing moments in video with natural language. In: Proceedings of the IEEE international conference on computer vision, pp 5803\u20135812","DOI":"10.1109\/ICCV.2017.618"},{"key":"11468_CR40","doi-asserted-by":"crossref","unstructured":"Bain M, Nagrani A, Varol G, Zisserman A (2021) Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1728\u20131738","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"11468_CR41","doi-asserted-by":"crossref","unstructured":"Lei J, Li L, Zhou L, Gan Z, Berg TL, Bansal M, Liu J (2021) Less is more: Clipbert for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7331\u20137341","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"11468_CR42","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR 2015"},{"key":"11468_CR43","doi-asserted-by":"crossref","unstructured":"Bogolin S, Croitoru I, Jin H, Liu Y, Albanie S (2022) Cross modal retrieval with querybank normalisation. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 5184\u20135195","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"11468_CR44","unstructured":"Bai J, Liu C, Ni F, Wang H, Hu M, Guo X, Cheng L (2022) Lat: latent translation with cycle-consistency for video-text retrieval. arXiv preprint arXiv:2207.04858"},{"key":"11468_CR45","doi-asserted-by":"crossref","unstructured":"Ge Y, Ge Y, Liu X, Wang J, Wu J, Shan Y, Qie X, Luo P (2022) Miles: visual bert pre-training with injected language semantics for video-text retrieval. In: European conference on computer vision, pp 691\u2013708","DOI":"10.1007\/978-3-031-19833-5_40"},{"key":"11468_CR46","doi-asserted-by":"crossref","unstructured":"Wu X, Gao C, Lin Z, Wang Z, Han J, Hu S (2022) Rap: redundancy-aware video-language pre-training for text-video retrieval. In: Findings of the Association for computational linguistics, pp 3036\u20133047","DOI":"10.18653\/v1\/2022.findings-emnlp.221"},{"key":"11468_CR47","doi-asserted-by":"crossref","unstructured":"Lu H, Fei N, Huo Y, Gao Y, Lu Z, Wen J-R (2022) Cots: Collaborative two-stream vision-language pre-training model for cross-modal retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15692\u201315701","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"11468_CR48","doi-asserted-by":"crossref","unstructured":"Hu F, Chen A, Wang Z, Zhou F, Dong J, Li X (2022) Lightweight attentional feature fusion: a new baseline for text-to-video retrieval. In: European conference on computer vision, pp 444\u2013461","DOI":"10.1007\/978-3-031-19781-9_26"},{"key":"11468_CR49","unstructured":"Zou X, Wu C, Cheng L, Wang Z (2022) Tokenflow: rethinking fine-grained cross-modal alignment in vision-language retrieval. arXiv preprint arXiv:2209.13822"},{"key":"11468_CR50","unstructured":"Jin P, Huang J, Liu F, Wu X, Ge S, Song G, Clifton DA, Chen J (2022) Expectation-maximization contrastive learning for compact video-and-language representations. In: Advances in neural information processing systems, vol 35, pp 30291\u201330306"},{"key":"11468_CR51","doi-asserted-by":"crossref","unstructured":"Chen Y, Wang J, Lin L, Qi Z, Ma J, Shan Y (2023) Tagging before alignment: integrating multi-modal tags for video-text retrieval. In: Thirty-Fifth conference on innovative applications of artificial intelligence, pp 396\u2013404","DOI":"10.1609\/aaai.v37i1.25113"},{"key":"11468_CR52","doi-asserted-by":"publisher","unstructured":"Jin P, Li H, Cheng Z, Li K, Ji X, Liu C, Yuan L, Chen J (2023) Diffusionret: generative text-video retrieval with diffusion model. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2470\u20132481. https:\/\/doi.org\/10.48550\/arXiv.2303.09867","DOI":"10.48550\/arXiv.2303.09867"},{"key":"11468_CR53","doi-asserted-by":"crossref","unstructured":"Jin P, Li H, Cheng Z, Huang J, Wang Z, Yuan L, Liu C, Chen J (2023) Text-video retrieval with disentangled conceptualization and set-to-set alignment. In: Proceedings of the thirty-second international joint conference on artificial intelligence, pp 938\u2013946","DOI":"10.24963\/ijcai.2023\/104"},{"key":"11468_CR54","doi-asserted-by":"crossref","unstructured":"Jin P, Huang J, Xiong P, Tian S, Liu C, Ji X, Yuan L, Chen J (2023) Video-text as game players: hierarchical banzhaf interaction for cross-modal representation learning. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 2472\u20132482","DOI":"10.1109\/CVPR52729.2023.00244"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11468-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11468-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11468-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T20:22:33Z","timestamp":1715890953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11468-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,17]]},"references-count":54,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["11468"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11468-5","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,17]]},"assertion":[{"value":"27 November 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2024","order":2,"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 there is no conflict of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"54"}}