{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T10:11:28Z","timestamp":1772532688184,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC, Zhuhai Industry Core and Key Technology Research Project","award":["61936003"],"award-info":[{"award-number":["61936003"]}]},{"name":"Science and Technology Foundation of Guangzhou Huangpu Development District","award":["2020GH17"],"award-info":[{"award-number":["2020GH17"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612499","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"2066-2077","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8738-0648","authenticated-orcid":false,"given":"Wentao","family":"Yang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0372-8895","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3263-3449","authenticated-orcid":false,"given":"Dezhi","family":"Peng","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-0957","authenticated-orcid":false,"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3759-4727","authenticated-orcid":false,"given":"Mengchao","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-4796","authenticated-orcid":false,"given":"Cong","family":"Yao","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.09.013"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2402536.2402585"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3043802.3043941"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01468"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19885"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/PL00013549"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3144899"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR, 980--989","author":"Deng Yuntian","year":"2017","unstructured":"Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, and Alexander M Rush. 2017. Image-to-markup generation with coarse-to-fine attention. In International Conference on Machine Learning. PMLR, 980--989."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16219"},{"key":"e_1_3_2_1_14_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Gu Jiatao","year":"2018","unstructured":"Jiatao Gu, James Bradbury, Caiming Xiong, Victor O. K. Li, and Richard Socher. 2018. Non-Autoregressive Neural Machine Translation. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=B1l8BtlCb"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013723"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/107"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1141"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.98"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_20_1","unstructured":"Kazuya Kawakami. 2008. Supervised sequence labelling with recurrent neural networks. Ph.D. Dissertation. Technical University of Munich."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4377037"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1999.791736"},{"key":"e_1_3_2_1_24_1","volume-title":"Document Recognition V","author":"Lavirotte St\u00e9phane","unstructured":"St\u00e9phane Lavirotte and Loic Pottier. 1998. Mathematical formula recognition using graph grammar. In Document Recognition V, Vol. 3305. SPIE, 44--52."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00291"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.09.002"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"e_1_3_2_1_28_1","volume-title":"Tel Aviv","author":"Li Bohan","year":"2022","unstructured":"Bohan Li, Ye Yuan, Dingkang Liang, Xiao Liu, Zhilong Ji, Jinfeng Bai, Wenyu Liu, and Xiang Bai. 2022. When counting meets HMER: counting-aware network for handwritten mathematical expression recognition. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVIII. Springer, 197--214."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475578"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR2020.2020.00041"},{"key":"e_1_3_2_1_31_1","volume-title":"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)","author":"Mahdavi Mahshad","unstructured":"Mahshad Mahdavi, Richard Zanibbi, Harold Mouchere, Christian Viard-Gaudin, and Utpal Garain. 2019. 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). IEEE, 1533--1538."},{"key":"e_1_3_2_1_32_1","volume-title":"ICFHR 2014 competition on recognition of on-line handwritten mathematical expressions (CROHME 2014). In 2014 14th International Conference on Frontiers in Handwriting Recognition. IEEE, 791--796","author":"Mouchere Harold","year":"2014","unstructured":"Harold Mouchere, Christian Viard-Gaudin, Richard Zanibbi, and Utpal Garain. 2014. ICFHR 2014 competition on recognition of on-line handwritten mathematical expressions (CROHME 2014). In 2014 14th International Conference on Frontiers in Handwriting Recognition. IEEE, 791--796."},{"key":"e_1_3_2_1_33_1","volume-title":"ICFHR2016 CROHME: Competition on recognition of online handwritten mathematical expressions. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE, 607--612","author":"Mouch\u00e8re Harold","year":"2016","unstructured":"Harold Mouch\u00e8re, Christian Viard-Gaudin, Richard Zanibbi, and Utpal Garain. 2016. ICFHR2016 CROHME: Competition on recognition of online handwritten mathematical expressions. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE, 607--612."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86159-9_8"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.155"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475238"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.277"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR2020.2020.00042"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86198-8_1"},{"key":"e_1_3_2_1_42_1","volume-title":"Modeling coverage for neural machine translation. arXiv preprint arXiv:1601.04811","author":"Tu Zhaopeng","year":"2016","unstructured":"Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, and Hang Li. 2016. Modeling coverage for neural machine translation. arXiv preprint arXiv:1601.04811 (2016)."},{"key":"e_1_3_2_1_43_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. attention is all you need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1509"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00591"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20172"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10925-7_2"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01291-5"},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International Conference on Machine Learning. PMLR, 2048--2057."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475179"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108910"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00451"},{"key":"e_1_3_2_1_53_1","volume-title":"Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701","author":"Zeiler Matthew D","year":"2012","unstructured":"Matthew D Zeiler. 2012. Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546031"},{"key":"e_1_3_2_1_55_1","volume-title":"International Conference on Machine Learning. PMLR, 11076--11085","author":"Zhang Jianshu","year":"2020","unstructured":"Jianshu Zhang, Jun Du, Yongxin Yang, Yi-Zhe Song, Si Wei, and Lirong Dai. 2020. A tree-structured decoder for image-to-markup generation. In International Conference on Machine Learning. PMLR, 11076--11085."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"e_1_3_2_1_57_1","volume-title":"ICDAR 2019 robust reading challenge on reading chinese text on signboard. In 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, 1577--1581","author":"Zhang Rui","year":"2019","unstructured":"Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, Lei Wang, Dong Wang, Minghui Liao, Mingkun Yang, et al. 2019. ICDAR 2019 robust reading challenge on reading chinese text on signboard. In 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, 1577--1581."},{"key":"e_1_3_2_1_58_1","volume-title":"Tel Aviv","author":"Zhao Wenqi","year":"2022","unstructured":"Wenqi Zhao and Liangcai Gao. 2022. CoMER: Modeling coverage for Transformer-based handwritten mathematical expression recognition. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVIII. Springer, 392--408."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_37"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548424"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612499","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:52Z","timestamp":1755820852000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":61,"alternative-id":["10.1145\/3581783.3612499","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612499","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}