{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T18:51:56Z","timestamp":1769799116188,"version":"3.49.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863302","type":"print"},{"value":"9783030863319","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86331-9_42","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"648-663","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Image to LaTeX with Graph Neural Network for Mathematical Formula Recognition"],"prefix":"10.1007","author":[{"given":"Shuai","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Yuan, K.: Multi-dimensional formula feature modeling for mathematical information retrieval. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, p. 1381 (2017)","DOI":"10.1145\/3077136.3084158"},{"key":"42_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1007\/978-3-030-45442-5_60","volume-title":"Advances in Information Retrieval","author":"G Nishizawa","year":"2020","unstructured":"Nishizawa, G., Liu, J., Diaz, Y., Dmello, A., Zhong, W., Zanibbi, R.: MathSeer: a math-aware search interface with intuitive formula editing, reuse, and lookup. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12036, pp. 470\u2013475. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45442-5_60"},{"key":"42_CR3","unstructured":"Peng, S., Yuan. K., Gao, L., et al.: MathBERT: a pre-trained model for mathematical formula understanding. arXiv e-prints (2021). arXiv: 2105.00377"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Yuan, K., Gao, L., Wang, Y., et al.: A mathematical information retrieval system based on RankBoost. In: Proceedings of the 16th ACM\/IEEE-CS on Joint Conference on Digital Libraries, pp. 259\u2013260 (2016)","DOI":"10.1145\/2910896.2925460"},{"key":"42_CR5","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. ACM (1967)","DOI":"10.1145\/2402536.2402585"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Suzuki, M., Tamari, F., Fukuda, R., Uchida, S., Kanahori, T.: Infty: an integrated OCR system for mathematical documents. In: Proceedings of the 2003 ACM Symposium on Document Engineering, pp. 95\u2013104. ACM (2003)","DOI":"10.1145\/958220.958239"},{"key":"42_CR7","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"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Sharif Razavian, A., Azizpour, H., Sullivan, J., et al.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806\u2013813 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Yuan, K., He, D., Yang, X., et al.: Follow the curve: arbitrarily oriented scene text detection using key points spotting and curve prediction. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/ICME46284.2020.9102770"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Yuan, K., He, D., Jiang, Z., et al.: Automatic generation of headlines for online math questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. (05), pp. 9490\u20139497 (2020)","DOI":"10.1609\/aaai.v34i05.6493"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"4","key":"42_CR13","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10032-011-0174-4","volume":"15","author":"R Zanibbi","year":"2012","unstructured":"Zanibbi, R., Blostein, D.: Recognition and retrieval of mathematical expressions. Int. J. Doc. Anal. Recogn. (IJDAR) 15(4), 331\u2013357 (2012)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Yan, Z., Zhang, X., Gao, L., et al.: ConvMath: a convolutional sequence network for mathematical expression recognition. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 4566\u20134572. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412913"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, X., Gao, L., Yuan, K., et al.: A symbol dominance based formulae recognition approach for pdf documents. 2In: 017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1144\u20131149. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.189"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Twaakyondo, H.M., Okamoto, M.: Structure analysis and recognition of mathematical expressions. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 1, pp. 430\u2013437. IEEE (1995)","DOI":"10.1109\/ICDAR.1995.599029"},{"issue":"11","key":"42_CR17","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/TPAMI.2002.1046157","volume":"24","author":"R Zanibbi","year":"2002","unstructured":"Zanibbi, R., Blostein, D., Cordy, J.R.: Recognizing mathematical expressions using tree transformation. IEEE Trans. Pattern Anal. Mach. Intell. 24(11), 1455\u20131467 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR18","unstructured":"Yamamoto, R., Sako, S., Nishimoto, T., Sagayama, S.: On-line recognition of handwritten mathematical expressions based on stroke-based stochastic context-free grammar. In: tenth International Workshop on Frontiers in Handwriting (2006)"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Prusa, D., Hlav\u00e1c, V.: Mathematical formulae recognition using 2D grammars. In: Ninth International Conference on Document Analysis and Recognition, ICDAR 2007, vol. 2, pp. 849\u2013853. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4377035"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Alvaro, F., Benedi, J.M., et al.: Recognition of printed mathematical expressions using two-dimensional stochastic context-free grammars. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 1225\u20131229. IEEE (2011)","DOI":"10.1109\/ICDAR.2011.247"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Ciresan, D.C., et al.: Deep, big, simple neural nets for handwritten digit recognition. Neural Comput. 22(12), 3207\u20133220 (2010)","DOI":"10.1162\/NECO_a_00052"},{"key":"42_CR22","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Deep structured output learning for unconstrained text recognition. In: ICLR (2015)"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, J., Du, J., Dai, L.: A GRU-based encoder-decoder approach with attention for online handwritten mathematical expression recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition, vol. 1, pp. 902\u2013907. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.152"},{"key":"42_CR25","unstructured":"Deng, Y., Kanervisto, A., Rush, A.M.: What you get is what you see: a visual markup decompiler. arXiv preprint arXiv:1609.04938, vol. 10, pp. 32\u201337 (2016)"},{"key":"42_CR26","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.procs.2019.01.246","volume":"147","author":"J Wang","year":"2019","unstructured":"Wang, J., Sun, Y., Wang, S.: Image to Latex with DenseNet encoder and joint attention. Procedia Comput. Sci. 147, 374\u2013380 (2019)","journal-title":"Procedia Comput. Sci."},{"key":"42_CR27","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Mahdavi, M., Condon, M., Davila, K., Zanibbi, R.: LPGA: line-of-sight parsing with graph-based attention for math formula recognition. In: Proceedings of the International Conference on Document Analysis and Recognition (2019)","DOI":"10.1109\/ICDAR.2019.00109"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. arXiv preprint arXiv:1801.07698 (2018)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"42_CR31","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)"},{"key":"42_CR32","unstructured":"Levy, O., Goldberg, Y.: Neural word embedding as implicit matrix factorization. In: Advances in Neural Information Processing Systems, pp. 2177\u20132185 (2014)"},{"key":"42_CR33","doi-asserted-by":"crossref","unstructured":"Luong, M., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv: 1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks. arXiv preprint arXiv:1211.3711 (2012)","DOI":"10.1007\/978-3-642-24797-2"},{"key":"42_CR35","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 on Association for Computational Linguistics. Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"42_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, W., Bai, Z., Zhu, Y.: An improved approach based on CNN-RNNs for mathematical expression recognition. In: Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing, pp. 57\u201361. ACM (2019)","DOI":"10.1145\/3330393.3330410"},{"key":"42_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Watch, attend and parse: an end-to-end neural network based approach to handwritten mathematical expression recognition. Pattern Recogn. 71, 196\u2013206 (2017)","DOI":"10.1016\/j.patcog.2017.06.017"},{"issue":"1","key":"42_CR38","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TMM.2018.2844689","volume":"21","author":"J Zhang","year":"2018","unstructured":"Zhang, J., Jun, D., Dai, L.: Track, attend, and parse (tap): an end-to-end framework for online handwritten mathematical expression recognition. IEEE Trans. Multimedia 21(1), 221\u2013233 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"42_CR39","unstructured":"Zhang, J., et al.: A tree-structured decoder for image-to-markup generation. In: International Conference on Machine Learning. PMLR (2020)"},{"key":"42_CR40","unstructured":"Yan, Z., Ma, T., Gao, L., et al.: Persistence homology for link prediction: an interactive view. arXiv preprint arXiv:2102.10255 (2021)"},{"key":"42_CR41","doi-asserted-by":"crossref","unstructured":"Wu, J., Yin, F., et al.: Graph-to-graph: towards accurate and interpretable online handwritten mathematical expression recognition. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16399"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86331-9_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:06:01Z","timestamp":1756937161000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}