{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:32:27Z","timestamp":1742945547523,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416842"},{"type":"electronic","value":"9783031416859"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41685-9_18","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T14:04:59Z","timestamp":1692367499000},"page":"287-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incremental Teacher Model with Mixed Augmentations and Scheduled Pseudo-label Loss for Handwritten Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7138-9645","authenticated-orcid":false,"given":"Masayuki","family":"Honda","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4751-1302","authenticated-orcid":false,"given":"Hung Tuan","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2556-9191","authenticated-orcid":false,"given":"Cuong Tuan","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2760-8724","authenticated-orcid":false,"given":"Cong Kha","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9467-2275","authenticated-orcid":false,"given":"Ryosuke","family":"Odate","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5714-5305","authenticated-orcid":false,"given":"Takashi","family":"Kanemaru","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7872-156X","authenticated-orcid":false,"given":"Masaki","family":"Nakagawa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: The 25th Neural Information Processing Systems, pp. 1106\u20131114 (2012). https:\/\/doi.org\/10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"18_CR2","doi-asserted-by":"publisher","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. In: The 9th ISCA Speech Synthesis Workshop, p. 125 (2016). https:\/\/doi.org\/10.1109\/ICASSP.2009.4960364","DOI":"10.1109\/ICASSP.2009.4960364"},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39, 652\u2013663 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2587640","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR4","doi-asserted-by":"publisher","unstructured":"Graves, A., Schmidhuber, J.J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: The 21st International Conference on Neural Information Processing Systems, pp. 545\u2013552 (2008). https:\/\/doi.org\/10.1007\/978-1-4471-4072-6","DOI":"10.1007\/978-1-4471-4072-6"},{"key":"18_CR5","doi-asserted-by":"publisher","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: The 14th International Conference on Document Analysis and Recognition, pp. 67\u201372 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.20","DOI":"10.1109\/ICDAR.2017.20"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In: The 30th International Conference on Neural Information Processing Systems, pp. 838\u2013846 (2016). https:\/\/doi.org\/10.5555\/3157096.3157190","DOI":"10.5555\/3157096.3157190"},{"key":"18_CR7","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s100320200071","volume":"5","author":"UV Marti","year":"2003","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recognit. 5, 39\u201346 (2003). https:\/\/doi.org\/10.1007\/s100320200071","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Shivram, A., Ramaiah, C., Setlur, S., Govindaraju, V.: IBM-UB-1: a dual mode unconstrained english handwriting dataset. In: The 12th International Conference on Document Analysis and Recognition, pp. 13\u201317 (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.12","DOI":"10.1109\/ICDAR.2013.12"},{"key":"18_CR9","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1016\/j.patcog.2013.08.009","volume":"47","author":"SA Mahmoud","year":"2014","unstructured":"Mahmoud, S.A., et al.: KHATT: an open Arabic offline handwritten text database. Pattern Recognit. 47, 1096\u20131112 (2014). https:\/\/doi.org\/10.1016\/j.patcog.2013.08.009","journal-title":"Pattern Recognit."},{"key":"18_CR10","doi-asserted-by":"publisher","unstructured":"Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: CASIA online and offline Chinese handwriting databases. In: The 11th International Conference on Document Analysis and Recognition, pp. 37\u201341 (2011). https:\/\/doi.org\/10.1109\/ICDAR.2011.17","DOI":"10.1109\/ICDAR.2011.17"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Kumar Bhunia, A., et al.: Handwriting trajectory recovery using end-to-end deep encoder-decoder network. In: The 24th International Conference on Pattern Recognition, pp. 3639\u20133644 (2018). https:\/\/doi.org\/10.1109\/ICPR.2018.8546093","DOI":"10.1109\/ICPR.2018.8546093"},{"key":"18_CR12","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR13","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: The 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261\u20132269 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"18_CR14","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/ACCESS.2018.2885398","volume":"7","author":"Y Zhu","year":"2019","unstructured":"Zhu, Y., Xie, Z., Jin, L., Chen, X., Huang, Y., Zhang, M.: SCUT-EPT: new dataset and benchmark for offline Chinese text recognition in examination paper. IEEE Access. 7, 370\u2013382 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2018.2885398","journal-title":"IEEE Access."},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Nguyen, H.T., Nguyen, C.T., Oka, H., Ishioka, T., Nakagawa, M.: Handwriting recognition and automatic scoring for descriptive answers in Japanese language tests. In: Porwal, U., Forn\u00e9s, A., Shafait, F. (eds.) ICFHR 2022. LNCS, vol. 13639, pp. 274\u2013284. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-21648-0_19","DOI":"10.1007\/978-3-031-21648-0_19"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: The 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15297\u201315307 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01505","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Kang, L., Rusi\u00f1ol, M., Forn\u00e9s, A., Riba, P., Villegas, M.: Unsupervised adaptation for synthetic-to-real handwritten word recognition. In: The IEEE\/CVF Winter Conference on Applications of Computer Vision (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093392","DOI":"10.1109\/WACV45572.2020.9093392"},{"key":"18_CR18","unstructured":"Lee, D.-H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML 2013 Workshop: Challenges in Representation Learning, pp. 1\u20136 (2013)"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Rizve, M.N., Duarte, K., Rawat, Y.S., Shah, M.: In defense of pseudo-labeling: an uncertainty-aware pseudo-label selection framework for semi-supervised learning. In: The 9th International Conference on Learning Representations (2022). https:\/\/doi.org\/10.48550\/arXiv.2101.06329","DOI":"10.48550\/arXiv.2101.06329"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Xie, Z., Sun, Z., Jin, L., Feng, Z., Zhang, S.: Fully convolutional recurrent network for handwritten Chinese text recognition. In: The 23rd International Conference on Pattern Recognition, pp. 4011\u20134016 (2016). https:\/\/doi.org\/10.1109\/ICPR.2016.7900261","DOI":"10.1109\/ICPR.2016.7900261"},{"key":"18_CR21","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/J.NEUCOM.2018.02.008","volume":"289","author":"J Sueiras","year":"2018","unstructured":"Sueiras, J., Ruiz, V., Sanchez, A., Velez, J.F.: Offline continuous handwriting recognition using sequence to sequence neural networks. Neurocomputing 289, 119\u2013128 (2018). https:\/\/doi.org\/10.1016\/J.NEUCOM.2018.02.008","journal-title":"Neurocomputing"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Ly, N.T., Ngo, T.T., Nakagawa, M.: A self-attention based model for offline handwritten text recognition. In: Wallraven, C., Liu, Q., Nagahara, H. (eds.) ACPR 2022. LNCS, vol. 13189, pp. 356\u2013369. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-02444-3_27","DOI":"10.1007\/978-3-031-02444-3_27"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Munkhdalai, T., Yu, H.: Meta networks. In: The 34th International Conference on Machine Learning, pp. 2554\u20132563 (2017). https:\/\/doi.org\/10.48550\/arXiv.1703.00837","DOI":"10.48550\/arXiv.1703.00837"},{"key":"18_CR24","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/J.PATREC.2022.06.003","volume":"160","author":"MA Souibgui","year":"2022","unstructured":"Souibgui, M.A., Forn\u00e9s, A., Kessentini, Y., Megyesi, B.: Few shots are all you need: a progressive learning approach for low resource handwritten text recognition. Pattern Recogn. Lett. 160, 43\u201349 (2022). https:\/\/doi.org\/10.1016\/J.PATREC.2022.06.003","journal-title":"Pattern Recogn. Lett."},{"key":"18_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-41299-9_17","volume-title":"Pattern Recognition","author":"A Chakrapani Gv","year":"2020","unstructured":"Chakrapani Gv, A., Chanda, S., Pal, U., Doermann, D.: One-shot learning-based handwritten word recognition. In: Palaiahnakote, S., Sanniti di Baja, G., Wang, L., Yan, W.Q. (eds.) ACPR 2019. LNCS, vol. 12047, pp. 210\u2013223. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-41299-9_17"},{"key":"18_CR26","doi-asserted-by":"publisher","unstructured":"Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: The 5th International Conference on Learning Representations (2016). https:\/\/doi.org\/10.48550\/arXiv.1610.02242","DOI":"10.48550\/arXiv.1610.02242"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: The 31st International Conference on Neural Information Processing Systems, pp. 1195\u20131204 (2017). https:\/\/doi.org\/10.48550\/arxiv.1703.01780","DOI":"10.48550\/arxiv.1703.01780"},{"key":"18_CR28","doi-asserted-by":"publisher","unstructured":"Miyato, T., Maeda, S.I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1979\u20131993 (2017). https:\/\/doi.org\/10.48550\/arxiv.1704.03976","DOI":"10.48550\/arxiv.1704.03976"},{"key":"18_CR29","doi-asserted-by":"publisher","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Label propagation for deep semi-supervised learning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5065\u20135074 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00521","DOI":"10.1109\/CVPR.2019.00521"},{"key":"18_CR30","doi-asserted-by":"publisher","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Oliver, A., Papernot, N., Raffel, C.: MixMatch: a holistic approach to semi-supervised learning. In: The 33rd International Conference on Neural Information Processing Systems, pp. 5049\u20135059 (2019). https:\/\/doi.org\/10.48550\/arXiv.1905.02249","DOI":"10.48550\/arXiv.1905.02249"},{"key":"18_CR31","doi-asserted-by":"publisher","unstructured":"Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: The 34th International Conference on Neural Information Processing Systems, pp. 596\u2013608 (2020). https:\/\/doi.org\/10.5555\/3495724.3495775","DOI":"10.5555\/3495724.3495775"},{"key":"18_CR32","doi-asserted-by":"publisher","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: The 6th International Conference on Learning Representations (2018). https:\/\/doi.org\/10.48550\/arXiv.1803.07728","DOI":"10.48550\/arXiv.1803.07728"},{"issue":"1","key":"18_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019). https:\/\/doi.org\/10.1186\/s40537-019-0197-0","journal-title":"J. Big Data"},{"key":"18_CR34","doi-asserted-by":"publisher","unstructured":"Bhunia, A.K., Das, A., Bhunia, A.K., Kishore, P.S.R., Roy, P.P.: Handwriting recognition in low-resource scripts using adversarial learning. In: The IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 4762\u20134771 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00490","DOI":"10.1109\/CVPR.2019.00490"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41685-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T14:10:07Z","timestamp":1692367807000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41685-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416842","9783031416859"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41685-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","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":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","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":"316","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":"154","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":"49% - 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":"2.89","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":"1.50","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":"Number and type of other papers accepted : IJDAR track papers","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)"}}]}}