{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:50:59Z","timestamp":1744181459898,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031417337"},{"type":"electronic","value":"9783031417344"}],"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\/978-3-031-41734-4_11","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"173-188","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MUGS: A Multiple Granularity Semi-supervised Method for\u00a0Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9748-5942","authenticated-orcid":false,"given":"Qi","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6006-9929","authenticated-orcid":false,"given":"Qianyi","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4914-5315","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0889-5692","authenticated-orcid":false,"given":"Lingling","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7386-2694","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"11_CR2","unstructured":"Alex, G., Santiago, F., Faustino, G., J\u00fcrgen, S.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML (2006)"},{"key":"11_CR3","doi-asserted-by":"publisher","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"R Anhar","year":"2014","unstructured":"Anhar, R., Palaiahankote, S., Seng, C.C., Lim, T.C.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41, 8027\u20138048 (2014)","journal-title":"Expert Syst. Appl."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Baek, J., Matsui, Y., Aizawa, K.: What if we only use real datasets for scene text recognition? toward scene text recognition with fewer labels. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"11_CR5","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. TPAMI 41, 2035\u20132048 (2018)","journal-title":"TPAMI"},{"key":"11_CR6","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. TPAMI 39, 2298\u20132304 (2016)","journal-title":"TPAMI"},{"key":"11_CR7","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. TPAMI 39, 2298\u20132304 (2017)","journal-title":"TPAMI"},{"key":"11_CR8","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. In: NIPS (2019)"},{"key":"11_CR9","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"11_CR10","unstructured":"Chen-Yu, L., Simon, O.: Recursive recurrent nets with attention modeling for ocr in the wild. In: CVPR (2016)"},{"key":"11_CR11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10032-019-00334-z","volume":"23","author":"CK Ch\u2019ng","year":"2020","unstructured":"Ch\u2019ng, C.K., Chan, C.S., Liu, C.: Total-text: towards orientation robustness in scene text detection. IJDAR 23, 31\u201352 (2020)","journal-title":"IJDAR"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., Liu, W.: Strokelets: a learned multi-scale representation for scene text recognition. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.515"},{"key":"11_CR13","first-page":"4737","volume":"23","author":"C Yao","year":"2014","unstructured":"Yao, C., Bai, X., Liu, W.: A unified framework for multioriented text detection and recognition. TIP 23, 4737\u20134749 (2014)","journal-title":"TIP"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"11_CR15","unstructured":"Dong-Dong, C., Wei, W., Wei, G., ZhiHua, Z.: Tri-net for semi-supervised deep learning. In: IJCAI (2018)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"11_CR17","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR (2006)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: Icdar 2015 competition on robust reading. In: ICDAR (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: Icdar 2013 robust reading competition. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, D., Cho, M., Kwak, S.: Proxy anchor loss for deep metric learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"11_CR24","unstructured":"Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML (2013)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Litman, R., Anschel, O., Tsiper, S., Litman, R., Mazor, S., Manmatha, R.: Scatter: selective context attentional scene text recognizer. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., et al.: ICDAR 2003 robust reading competitions: entries, results and future directions. In: IJDAR (2005)","DOI":"10.1007\/s10032-004-0134-3"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Luo, C., Jin, L., Chen, J.: Siman: exploring self-supervised representation learning of scene text via similarity-aware normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1039\u20131048 (2022)","DOI":"10.1109\/CVPR52688.2022.00111"},{"key":"11_CR28","unstructured":"Lyu, P., Yang, Z., Leng, X., Wu, X., Li, R., Shen, X.: 2D attentional irregular scene text recognizer (2019). CoRR abs\/1906.05708. http:\/\/arxiv.org\/abs\/1906.05708"},{"key":"11_CR29","unstructured":"Max, J., Karen, S., Andrea, V., Andrew, Z.: Synthetic data and artificial neural networks for natural scene text recognition (2014). CoRR. http:\/\/arxiv.org\/abs\/1406.2227"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC (2012)","DOI":"10.5244\/C.26.127"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"11_CR32","unstructured":"Song, Q., Jiang, Q., Li, N., Zhang, R., Wei, X.: Reads: a rectified attentional double supervised network for scene text recognition. In: ICPR (2020)"},{"key":"11_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-030-86337-1_5","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"Q Jiang","year":"2021","unstructured":"Jiang, Q., Song, Q., Li, N., Zhang, R., Wei, X.: Heterogeneous network based semi-supervised learning for scene text\u00a0recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 64\u201378. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_5"},{"key":"11_CR34","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. In: NIPS (2020)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Qiao, S., Shen, W., Zhang, Z., Wang, B., Yuille, A.: Deep co-training for semi-supervised image recognition. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"11_CR38","unstructured":"Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. In: NIPS (2020)"},{"key":"11_CR39","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10115-013-0706-y","volume":"42","author":"I Triguero","year":"2015","unstructured":"Triguero, I., Garc\u00eda, S., Herrera, F.: Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. Knowl. Inf. Syst. 42, 245\u2013284 (2015)","journal-title":"Knowl. Inf. Syst."},{"key":"11_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"11_CR41","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV (2011)"},{"key":"11_CR42","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification (2019). CoRR abs\/1905.00546, http:\/\/arxiv.org\/abs\/1905.00546"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Reading and writing: discriminative and generative modeling for self-supervised text recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4214\u20134223 (2022)","DOI":"10.1145\/3503161.3547784"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Circle loss: a unified perspective of pair similarity optimization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"11_CR45","first-page":"3005","volume":"30","author":"Y Gao","year":"2021","unstructured":"Gao, Y., Chen, Y., Wang, J., Lu, H.: Semi-supervised scene text recognition. TIP 30, 3005\u20133016 (2021)","journal-title":"TIP"},{"key":"11_CR46","unstructured":"Gao, Y., Huang, Z., Dai, Y., Xu, C., Chen, K., Tuo, J.: Double supervised network with attention mechanism for scene text recognition (2018). CoRR abs\/1808.00677, http:\/\/arxiv.org\/abs\/1808.00677"},{"key":"11_CR47","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. Comput. Sci. (2012)"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhu, B., Yao, X., Sun, Q., Li, R., Yu, B.: Context-based contrastive learning for scene text recognition. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20245"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: Pushing the performance limit of scene text recognizer without human annotation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14116\u201314125 (2022)","DOI":"10.1109\/CVPR52688.2022.01372"}],"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\/978-3-031-41734-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:11:03Z","timestamp":1692342663000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41734-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417337","9783031417344"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41734-4_11","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)"}}]}}