{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:05:32Z","timestamp":1778079932508,"version":"3.51.4"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198144","type":"print"},{"value":"9783031198151","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19815-1_23","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"392-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["CoMER: Modeling Coverage for\u00a0Transformer-Based Handwritten Mathematical Expression Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2952-0531","authenticated-orcid":false,"given":"Wenqi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.patrec.2012.09.023","volume":"35","author":"F Alvaro","year":"2014","unstructured":"Alvaro, F., S\u00e1nchez, J.A., Bened\u00ed, J.M.: Recognition of on-line handwritten mathematical expressions using 2d stochastic context-free grammars and hidden markov models. Pattern Recogn. Lett. 35, 58\u201367 (2014)","journal-title":"Pattern Recogn. Lett."},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, R.H.: Syntax-directed recognition of hand-printed two-dimensional mathematics. In: Symposium on Interactive Systems for Experimental Applied Mathematics: Proceedings of the Association for Computing Machinery Inc., Symposium, pp. 436\u2013459 (1967)","DOI":"10.1016\/B978-0-12-395608-8.50048-7"},{"key":"23_CR3","unstructured":"Bengio, Y., Frasconi, P., Simard, P.: The problem of learning long-term dependencies in recurrent networks. In: IEEE International Conference on Neural Networks, pp. 1183\u20131188. IEEE (1993)"},{"key":"23_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"issue":"1","key":"23_CR5","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/PL00013549","volume":"3","author":"KF Chan","year":"2000","unstructured":"Chan, K.F., Yeung, D.Y.: Mathematical expression recognition: a survey. Int. J. Doc. Anal. Recogn. 3(1), 3\u201315 (2000)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5076\u20135084 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"23_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2018)"},{"key":"23_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1007\/978-3-030-86331-9_39","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"H Ding","year":"2021","unstructured":"Ding, H., Chen, K., Huo, Q.: An encoder-decoder approach to handwritten mathematical expression recognition with multi-head attention and stacked decoder. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 602\u2013616. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_39"},{"key":"23_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"23_CR11","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: International Conference on Artificial Intelligence and Statistics (2011)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"23_CR13","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv: Learning (2015)"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Lavirotte, S., Pottier, L.: Mathematical formula recognition using graph grammar. In: Document Recognition V, vol. 3305, pp. 44\u201352. International Society for Optics and Photonics (1998)","DOI":"10.1117\/12.304644"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Jin, L., Lai, S., Zhu, Y.: Improving attention-based handwritten mathematical expression recognition with scale augmentation and drop attention. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 175\u2013180. IEEE (2020)","DOI":"10.1109\/ICFHR2020.2020.00041"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Liu, L., Utiyama, M., Finch, A., Sumita, E.: Agreement on target-bidirectional neural machine translation. In: North American Chapter of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/N16-1046"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2\u20139 February 2021, pp. 2286\u20132293. AAAI Press (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16328","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Empirical Methods in Natural Language Processing (2015)","DOI":"10.18653\/v1\/D15-1166"},{"issue":"2","key":"23_CR19","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s10032-012-0184-x","volume":"16","author":"S MacLean","year":"2013","unstructured":"MacLean, S., Labahn, G.: A new approach for recognizing handwritten mathematics using relational grammars and fuzzy sets. Int. J. Doc. Anal. Recogn. (IJDAR) 16(2), 139\u2013163 (2013)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Mahdavi, M., Zanibbi, R., Mouchere, H., Viard-Gaudin, C., Garain, U.: Icdar 2019 crohme+ tfd: competition on recognition of handwritten mathematical expressions and typeset formula detection. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1533\u20131538. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00247"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Mouchere, H., Viard-Gaudin, C., Zanibbi, R., Garain, U.: Icfhr 2014 competition on recognition of on-line handwritten mathematical expressions (crohme 2014). In: 2014 14th International Conference on Frontiers in Handwriting Recognition, pp. 791\u2013796. IEEE (2014)","DOI":"10.1109\/ICFHR.2014.138"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Mouch\u00e8re, H., Viard-Gaudin, C., Zanibbi, R., Garain, U.: Icfhr 2016 crohme: competition on recognition of online handwritten mathematical expressions. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 607\u2013612. IEEE (2016)","DOI":"10.1109\/ICFHR.2016.0116"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13\u201319 June 2020, pp. 10968\u201310977. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01098. https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/html\/Pan_X-Linear_Attention_Networks_for_Image_Captioning_CVPR_2020_paper.html","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"23_CR24","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Neural Information Processing Systems (2019)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Rosendahl, J., Herold, C., Petrick, F., Ney, H.: Recurrent attention for the transformer. In: Proceedings of the Second Workshop on Insights from Negative Results in NLP, pp. 62\u201366 (2021)","DOI":"10.18653\/v1\/2021.insights-1.10"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Truong, T.N., Nguyen, C.T., Phan, K.M., Nakagawa, M.: Improvement of end-to-end offline handwritten mathematical expression recognition by weakly supervised learning. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 181\u2013186. IEEE (2020)","DOI":"10.1109\/ICFHR2020.2020.00042"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Tu, Z., Lu, Z., Liu, Y., Liu, X., Li, H.: Modeling coverage for neural machine translation. In: Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1008"},{"key":"23_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (2017)"},{"key":"23_CR29","unstructured":"Wu, J.W., Yin, F., Zhang, Y.M., Zhang, X.Y., Liu, C.L.: Handwritten mathematical expression recognition via paired adversarial learning. Int. J. Comput. Vis., 1\u201316 (2020)"},{"key":"23_CR30","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Zanibbi, R., Mouch\u00e8re, H., Viard-Gaudin, C.: Evaluating structural pattern recognition for handwritten math via primitive label graphs. In: Document Recognition and Retrieval (2013)","DOI":"10.1117\/12.2008409"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, J., Du, J., Dai, L.: Multi-scale attention with dense encoder for handwritten mathematical expression recognition. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2245\u20132250. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546031"},{"key":"23_CR33","unstructured":"Zhang, J., Du, J., Yang, Y., Song, Y.Z., Wei, S., Dai, L.: A tree-structured decoder for image-to-markup generation. In: ICML. p. In Press (2020)"},{"key":"23_CR34","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.patcog.2017.06.017","volume":"71","author":"J Zhang","year":"2017","unstructured":"Zhang, J., Du, J., Zhang, S., Liu, D., Hu, Y., Hu, J., Wei, S., Dai, L.: Watch, attend and parse: An end-to-end neural network based approach to handwritten mathematical expression recognition. Pattern Recogn. 71, 196\u2013206 (2017)","journal-title":"Pattern Recogn."},{"key":"23_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1007\/978-3-030-86331-9_37","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"W Zhao","year":"2021","unstructured":"Zhao, W., Gao, L., Yan, Z., Peng, S., Du, L., Zhang, Z.: Handwritten mathematical expression recognition with bidirectionally trained transformer. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 570\u2013584. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_37"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19815-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:27:07Z","timestamp":1666394827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19815-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198144","9783031198151"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19815-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}