{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:10:41Z","timestamp":1758089441660,"version":"3.44.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046239"},{"type":"electronic","value":"9783032046246"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04624-6_22","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:33:51Z","timestamp":1758000831000},"page":"375-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mask CoMER: Enhancing Handwritten Mathematical Expression Recognition with\u00a0Masked Language Pretraining and\u00a0Regularization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2588-5235","authenticated-orcid":false,"given":"Nam Van Hai","family":"Phan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1042-8260","authenticated-orcid":false,"given":"Khoa Minh","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7553-4848","authenticated-orcid":false,"given":"Trung Thanh","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9063-3577","authenticated-orcid":false,"given":"Trung Thanh","family":"Pham","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6551-9106","authenticated-orcid":false,"given":"Phuong-Nam","family":"Tran","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9302-3129","authenticated-orcid":false,"given":"Duc Ngoc Minh","family":"Dang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"issue":"6","key":"22_CR1","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1080\/02564602.2021.2008277","volume":"39","author":"R Aggarwal","year":"2022","unstructured":"Aggarwal, R., Pandey, S., Tiwari, A.K., Harit, G.: Survey of mathematical expression recognition for printed and handwritten documents. IETE Tech. Rev. 39(6), 1245\u20131253 (2022)","journal-title":"IETE Tech. Rev."},{"key":"22_CR2","unstructured":"Deng, Y., Kanervisto, A., Ling, J., Rush, A.M.: Image-to-markup generation with coarse-to-fine attention. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a070, pp. 980\u2013989. PMLR (2017). https:\/\/proceedings.mlr.press\/v70\/deng17a.html"},{"key":"22_CR3","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., 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, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"22_CR4","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, pp. 1050\u20131059. ICML 2016, JMLR.org (2016)"},{"key":"22_CR5","doi-asserted-by":"publisher","unstructured":"Gong, Z., Zhou, K., Zhao, X., Sha, J., Wang, S., Wen, J.R.: Continual pre-training of language models for math problem understanding with syntax-aware memory network. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5923\u20135933. Association for Computational Linguistics, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.408, https:\/\/aclanthology.org\/2022.acl-long.408\/","DOI":"10.18653\/v1\/2022.acl-long.408"},{"key":"22_CR6","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. The MIT Press (2016)"},{"key":"22_CR7","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/978-3-031-72670-5_8","volume-title":"Computer Vision - ECCV 2024","author":"T Guan","year":"2025","unstructured":"Guan, T., Lin, C., Shen, W., Yang, X.: PosFormer: recognizing complex handwritten mathematical expression with position forest transformer. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision - ECCV 2024, pp. 130\u2013147. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72670-5_8"},{"key":"22_CR8","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261\u20132269 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"22_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"22_CR10","unstructured":"Kwon, G., Cai, Z., Ravichandran, A., Bas, E., Bhotika, R., Soatto, S.: Masked vision and language modeling for multi-modal representation learning. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=ZhuXksSJYWn"},{"key":"22_CR11","first-page":"197","volume-title":"Computer Vision - ECCV 2022","author":"B Li","year":"2022","unstructured":"Li, B., et al.: When counting meets HMER: counting-aware network for handwritten mathematical expression recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 197\u2013214. Springer Nature Switzerland, Cham (2022)"},{"key":"22_CR12","doi-asserted-by":"publisher","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 (2020). https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00041","DOI":"10.1109\/ICFHR2020.2020.00041"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Li, Z., Yang, W., Qi, H., Jin, L., Huang, Y., Ding, K.: A tree-based model with branch parallel decoding for handwritten mathematical expression recognition. Pattern Recogn. 149, 110220 (2024). https:\/\/doi.org\/10.1016\/j.patcog.2023.110220, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320323009172","DOI":"10.1016\/j.patcog.2023.110220"},{"key":"22_CR14","doi-asserted-by":"publisher","unstructured":"Liao, Y., Jiang, X., Liu, Q.: Probabilistically masked language model capable of autoregressive generation in arbitrary word order. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 263\u2013274. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.24, https:\/\/aclanthology.org\/2020.acl-main.24","DOI":"10.18653\/v1\/2020.acl-main.24"},{"key":"22_CR15","doi-asserted-by":"publisher","unstructured":"Lin, Z., Li, J., Dai, G., Chen, T., Huang, S., Lin, J.: Contrastive representation enhancement and learning for handwritten mathematical expression recognition. Pattern Recogn. Lett. 186, 14\u201320 (2024). https:\/\/doi.org\/10.1016\/j.patrec.2024.08.021, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167865524002538","DOI":"10.1016\/j.patrec.2024.08.021"},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-031-72998-0_16","volume-title":"Computer Vision - ECCV 2024","author":"C Liu","year":"2025","unstructured":"Liu, C., et al.: NAMER: non-autoregressive modeling for handwritten mathematical expression recognition. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision - ECCV 2024, pp. 273\u2013291. Springer Nature Switzerland, Cham (2025)"},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Liu, J., et al.: Valor: Vision-audio-language omni-perception pretraining model and dataset. IEEE Trans. Pattern Anal. Mach. Intell., 1\u201318 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3479776","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"22_CR18","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"22_CR19","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=Skq89Scxx"},{"key":"22_CR20","doi-asserted-by":"publisher","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 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00247","DOI":"10.1109\/ICDAR.2019.00247"},{"key":"22_CR21","doi-asserted-by":"publisher","unstructured":"Mouch\u00e8re, 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 (2014). https:\/\/doi.org\/10.1109\/ICFHR.2014.138","DOI":"10.1109\/ICFHR.2014.138"},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Mouch\u00e8re, H., Viard-Gaudin, C., Zanibbi, R., Garain, U.: Icfhr2016 CROHME: competition on recognition of online handwritten mathematical expressions. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 607\u2013612 (2016). https:\/\/doi.org\/10.1109\/ICFHR.2016.0116","DOI":"10.1109\/ICFHR.2016.0116"},{"key":"22_CR23","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, pp. 807\u2013814. ICML 2010, Omnipress, Madison, WI, USA (2010)"},{"key":"22_CR24","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018). https:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMert: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"22_CR26","doi-asserted-by":"publisher","unstructured":"Tang, J.M., Guo, H.Y., Wu, J.W., Yin, F., Huang, L.L.: Offline handwritten mathematical expression recognition with graph encoder and transformer decoder. Pattern Recogn. 148, 110155 (2024). https:\/\/doi.org\/10.1016\/j.patcog.2023.110155, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S003132032300852X","DOI":"10.1016\/j.patcog.2023.110155"},{"key":"22_CR27","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.procs.2024.04.025","volume":"235","author":"BN Van","year":"2024","unstructured":"Van, B.N., Hoang, V.T.: A short review for handwritten math expression recognition techniques. Procedia Comput. Sci. 235, 231\u2013239 (2024)","journal-title":"Procedia Comput. Sci."},{"key":"22_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"22_CR29","doi-asserted-by":"publisher","unstructured":"Wettig, A., Gao, T., Zhong, Z., Chen, D.: Should you mask 15% in masked language modeling? In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2985\u20133000. Association for Computational Linguistics, Dubrovnik, Croatia (2023). https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.217, https:\/\/aclanthology.org\/2023.eacl-main.217\/","DOI":"10.18653\/v1\/2023.eacl-main.217"},{"key":"22_CR30","doi-asserted-by":"publisher","unstructured":"Yang, W., Li, Z., Peng, D., Jin, L., He, M., Yao, C.: Read ten lines at one glance: Line-aware semi-autoregressive transformer for multi-line handwritten mathematical expression recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2066\u20132077. MM 2023, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3581783.3612499","DOI":"10.1145\/3581783.3612499"},{"key":"22_CR31","doi-asserted-by":"publisher","unstructured":"Yuan, Y., et al.: Syntax-aware network for handwritten mathematical expression recognition. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4543\u20134552 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00451","DOI":"10.1109\/CVPR52688.2022.00451"},{"key":"22_CR32","doi-asserted-by":"publisher","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 (2018). https:\/\/doi.org\/10.1109\/ICPR.2018.8546031","DOI":"10.1109\/ICPR.2018.8546031"},{"key":"22_CR33","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1016\/j.patcog.2017.06.017, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320317302376","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"22_CR34","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-031-19815-1_23","volume-title":"Computer Vision - ECCV 2022","author":"W Zhao","year":"2022","unstructured":"Zhao, W., Gao, L.: Comer: Modeling coverage for transformer-based handwritten mathematical expression recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 392\u2013408. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_23"},{"key":"22_CR35","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-031-70549-6_2","volume-title":"Document Analysis and Recognition - ICDAR 2024","author":"J Zhu","year":"2024","unstructured":"Zhu, J., Gao, L., Zhao, W.: ICAL: implicit character-aided learning for enhanced handwritten mathematical expression recognition. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) Document Analysis and Recognition - ICDAR 2024, pp. 21\u201337. Springer Nature Switzerland, Cham (2024)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04624-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:33:56Z","timestamp":1758000836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04624-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032046239","9783032046246"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04624-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}