{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:09:27Z","timestamp":1780776567080,"version":"3.54.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T00:00:00Z","timestamp":1693008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T00:00:00Z","timestamp":1693008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0100104"],"award-info":[{"award-number":["2018AAA0100104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2018AAA0100100"],"award-info":[{"award-number":["2018AAA0100100"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20211164"],"award-info":[{"award-number":["BK20211164"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s00530-023-01162-2","type":"journal-article","created":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T14:01:58Z","timestamp":1693058518000},"page":"3805-3818","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Asymmetric bi-encoder for image\u2013text retrieval"],"prefix":"10.1007","volume":"29","author":[{"given":"Wei","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siya","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,26]]},"reference":[{"key":"1162_CR1","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-VL: A universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, NY, pp. 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"1162_CR2","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.neucom.2018.10.059","volume":"330","author":"A Yuan","year":"2019","unstructured":"Yuan, A., Li, X., Lu, X.: 3g structure for image caption generation. Neurocomputing 330, 17\u201328 (2019)","journal-title":"Neurocomputing"},{"key":"1162_CR3","doi-asserted-by":"crossref","unstructured":"Lee, K., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany, pp. 212\u2013228 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"1162_CR4","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"1162_CR5","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."},{"issue":"8","key":"1162_CR6","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1109\/TMM.2019.2951226","volume":"22","author":"L Guo","year":"2019","unstructured":"Guo, L., Liu, J., Lu, S., Lu, H.: Show, tell, and polish: ruminant decoding for image captioning. IEEE Trans. Multimedia 22(8), 2149\u20132162 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"1162_CR7","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Y., Zhao, D.: Layer-wise enhanced transformer with multi-modal fusion for image caption. Multimedia Systems 29, 1\u201314 (2022)","DOI":"10.1007\/s00530-022-01036-z"},{"key":"1162_CR8","doi-asserted-by":"crossref","unstructured":"do Carmo Nogueira, T., Vinhal, C.D.N., da Cruz J\u00fanior, G., Ullmann, M.R.D., Marques, T.C.: A reference-based model using deep learning for image captioning. Multimedia Systems 29, 1\u201317 (2022)","DOI":"10.1007\/s00530-022-00937-3"},{"key":"1162_CR9","doi-asserted-by":"crossref","unstructured":"Dou, Z.-Y., Xu, Y., Gan, Z., Wang, J., Wang, S., Wang, L., Zhu, C., Zhang, P., Yuan, L., Peng, N., et al.: An empirical study of training end-to-end vision-and-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"1162_CR10","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems (NIPS), pp. 13 (2019)"},{"key":"1162_CR11","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., et al.: Oscar: Object-semantics aligned pre-training for vision-language tasks. In: Proceedings of the 16th European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"1162_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, B., Hu, H., Jain, V., Ie, E., Sha, F.: Learning to represent image and text with denotation graph. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 823\u2013839 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.60"},{"key":"1162_CR13","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 394 (2018)","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"1162_CR14","doi-asserted-by":"crossref","unstructured":"Dong, J., Li, X., Xu, C., Ji, S., He, Y., Yang, G., Wang, X.: Dual encoding for zero-example video retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"1162_CR15","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Huang, W., Dong, D., Scott, M.R.: Multi-similarity loss with general pair weighting for deep metric learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00516"},{"key":"1162_CR16","doi-asserted-by":"crossref","unstructured":"Sun, Y., Cheng, C., Zhang, Y., Zhang, C., Zheng, L., Wang, Z., Wei, Y.: Circle loss: A unified perspective of pair similarity optimization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"1162_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Proceedings of the 13th European Conference on Computer Vision (ECCV), Zurich, Switzerland, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1162_CR18","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"1162_CR19","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: NIPS, pp. 5998 (2017)"},{"key":"1162_CR20","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019)"},{"key":"1162_CR21","first-page":"1","volume":"29","author":"C Zhang","year":"2022","unstructured":"Zhang, C., Yang, Y., Guo, J., Jin, G., Song, D., Liu, A.A.: Improving text-image cross-modal retrieval with contrastive loss. Multimedia Syst. 29, 1\u20137 (2022)","journal-title":"Multimedia Syst."},{"key":"1162_CR22","doi-asserted-by":"crossref","unstructured":"Sun, H., Qin, X., Liu, X.: Image-text matching using multi-subspace joint representation. Multimedia Systems 29, 1\u201315 (2023)","DOI":"10.1007\/s00530-022-01038-x"},{"key":"1162_CR23","doi-asserted-by":"crossref","unstructured":"Lu, H., Fei, N., Huo, Y., Gao, Y., Lu, Z., Wen, J.-R.: 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 (2022)","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"1162_CR24","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, L., Yu, L., Kholy, A.E., Ahmed, F., Gan, Z., Cheng, Y., Liu, J.: UNITER: universal image-text representation learning. In: Proceedings of the 16th European Conference on Computer Vision (ECCV), Glasgow, UK, pp. 104\u2013120 (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"1162_CR25","doi-asserted-by":"crossref","unstructured":"Lu, X., Zhao, T., Lee, K.: Visualsparta: an embarrassingly simple approach to large-scale text-to-image search with weighted bag-of-words. In: ACL (2021)","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"1162_CR26","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 4171\u20134186 (2019)"},{"key":"1162_CR27","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: Vse++: Improving visual-semantic embeddings with hard negatives. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)"},{"key":"1162_CR28","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1162\/tacl_a_00473","volume":"10","author":"G Geigle","year":"2022","unstructured":"Geigle, G., Pfeiffer, J., Reimers, N., Vuli\u0107, I., Gurevych, I.: Retrieve fast, rerank smart: cooperative and joint approaches for improved cross-modal retrieval. Trans. Assoc. Computat. Linguist. 10, 503\u2013521 (2022)","journal-title":"Trans. Assoc. Computat. Linguist."},{"key":"1162_CR29","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"1","key":"1162_CR30","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L., Shamma, D.A., Bernstein, M.S., Fei-Fei, L.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"issue":"9","key":"1162_CR31","doi-asserted-by":"publisher","first-page":"6437","DOI":"10.1109\/TCSVT.2022.3164230","volume":"32","author":"X Dong","year":"2022","unstructured":"Dong, X., Zhang, H., Zhu, L., Nie, L., Liu, L.: Hierarchical feature aggregation based on transformer for image-text matching. IEEE Trans. Circuits Syst. Video Tech. 32(9), 6437\u20136447 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Tech."},{"key":"1162_CR32","doi-asserted-by":"publisher","first-page":"103067","DOI":"10.1016\/j.scs.2021.103067","volume":"73","author":"Q Liu","year":"2021","unstructured":"Liu, Q., Li, W., Chen, Z., Hua, B.: Deep metric learning for image retrieval in smart city development. Sustain. Cities Soc. 73, 103067 (2021)","journal-title":"Sustain. Cities Soc."},{"key":"1162_CR33","doi-asserted-by":"crossref","unstructured":"Wu, C.-Y., Manmatha, R., Smola, A.J., Krahenbuhl, P.: Sampling matters in deep embedding learning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.309"},{"key":"1162_CR34","doi-asserted-by":"crossref","unstructured":"Suh, Y., Han, B., Kim, W., Lee, K.M.: Stochastic class-based hard example mining for deep metric learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00742"},{"key":"1162_CR35","doi-asserted-by":"crossref","unstructured":"Harwood, B., Kumar BG, V., Carneiro, G., Reid, I., Drummond, T.: Smart mining for deep metric learning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.307"},{"key":"1162_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, H., Huang, W., Scott, M.R.: Cross-batch memory for embedding learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"1162_CR37","doi-asserted-by":"crossref","unstructured":"Lu, H., Huo, Y., Ding, M., Fei, N., Lu, Z.: Cross-modal contrastive learning for generalizable and efficient image-text retrieval. Machine Intelligence Research 20, 1\u201314 (2023)","DOI":"10.1007\/s11633-022-1386-4"},{"key":"1162_CR38","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: Multi-task vision and language representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"1162_CR39","unstructured":"Gan, Z., Chen, Y., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. In: Advances in Neural Information Processing Systems (NeurIPS), virtual (2020)"},{"key":"1162_CR40","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"1162_CR41","doi-asserted-by":"crossref","unstructured":"Sun, S., Chen, Y.-C., Li, L., Wang, S., Fang, Y., Liu, J.: Lightningdot: Pre-training visual-semantic embeddings for real-time image-text retrieval. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (2021)","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"1162_CR42","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Wang, L.: Instance-aware image and sentence matching with selective multimodal lstm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2310\u20132318 (2017)","DOI":"10.1109\/CVPR.2017.767"},{"key":"1162_CR43","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"1162_CR44","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., Wang, L.: Learning semantic concepts and order for image and sentence matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6163\u20136171 (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"1162_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, X., Li, H., Sheng, L., Yan, J., Wang, X., Shao, J.: Camp: Cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision (CVPR), pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"1162_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yang, H., Qian, X., Ma, L., Lu, J., Li, B., Fan, X.: Position focused attention network for image-text matching. In: International Joint Conference on Artificial Intelligence (IJCAI) (2019)","DOI":"10.24963\/ijcai.2019\/526"},{"key":"1162_CR47","doi-asserted-by":"crossref","unstructured":"Hu, Z., Luo, Y., Lin, J., Yan, Y., Chen, J.: Multi-level visual-semantic alignments with relation-wise dual attention network for image and text matching. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 789\u2013795 (2019)","DOI":"10.24963\/ijcai.2019\/111"},{"key":"1162_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, Y., Ji, Z., Pang, Y., Ma, L.: Consensus-aware visual-semantic embedding for image-text matching. In: European Conference on Computer Vision (ECCV), pp. 18\u201334 (2020). Springer","DOI":"10.1007\/978-3-030-58586-0_2"},{"issue":"1","key":"1162_CR49","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1109\/TCSVT.2021.3060713","volume":"32","author":"J Wu","year":"2022","unstructured":"Wu, J., Wu, C., Lu, J., Wang, L., Cui, X.: Region reinforcement network with topic constraint for image-text matching. IEEE Trans. Circuits Syst. Video Tech. 32(1), 388\u2013397 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Tech."},{"key":"1162_CR50","doi-asserted-by":"crossref","unstructured":"Ge, X., Chen, F., Jose, J.M., Ji, Z., Wu, Z., Liu, X.: Structured multi-modal feature embedding and alignment for image-sentence retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5185\u20135193 (2021)","DOI":"10.1145\/3474085.3475634"},{"issue":"1","key":"1162_CR51","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/TPAMI.2022.3148470","volume":"45","author":"K Li","year":"2022","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Image-text embedding learning via visual and textual semantic reasoning. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 641\u2013656 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1162_CR52","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1218\u20131226 (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"1162_CR53","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1162_CR54","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (2015)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01162-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01162-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01162-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T11:09:37Z","timestamp":1700132977000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01162-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,26]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1162"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01162-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,26]]},"assertion":[{"value":"4 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}