{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:40:00Z","timestamp":1756852800844,"version":"3.44.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863364"},{"type":"electronic","value":"9783030863371"}],"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\/978-3-030-86337-1_5","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"64-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Heterogeneous Network Based Semi-supervised Learning for Scene Text\u00a0Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6006-9929","authenticated-orcid":false,"given":"Qianyi","family":"Jiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9748-5942","authenticated-orcid":false,"given":"Qi","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7592-8722","authenticated-orcid":false,"given":"Nan","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7386-2694","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3983-047X","authenticated-orcid":false,"given":"Xiaolin","family":"Wei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Baskar$$\\varphi $$, M.K., Watanabe, S., Astudillo$$\\pi $$, R., HoriY, T.: Semi-supervised sequence-to-sequence ASR using unpaired speech and text. arXiv preprint arXiv:1905.01152 (2019)","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"5_CR2","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":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D.D., Wang, W., Gao, W., ZhiHua, Z.: Tri-net for semi-supervised deep learning. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/278"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, W., Wang, C.: Semi-supervised ASR by end-to-end self-training. arXiv preprint arXiv:2001.09128 (2020)","DOI":"10.21437\/Interspeech.2020-1280"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"5_CR7","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":"5_CR8","doi-asserted-by":"crossref","unstructured":"Hady, M.F.A., Schwenker, F.: Co-training by committee: a new semi-supervised learning framework. In: 2008 IEEE International Conference on Data Mining Workshops (2008)","DOI":"10.1109\/ICDMW.2008.27"},{"key":"5_CR9","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. CoRR (2014)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Kahn, J., Lee, A., Hannun, A.: Self-training for end-to-end speech recognition. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"5_CR11","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":"5_CR12","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: Star-Net: a spatial attention residue network for scene text recognition. In: BMVC (2016)","DOI":"10.5244\/C.30.43"},{"key":"5_CR15","unstructured":"Liu, X., et al.: ICDAR 2019 robust reading challenge on reading Chinese text on signboard. arXiv preprint arXiv:1912.09641 (2019)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Lucas, S., et al.: ICDAR 2003 Robust Reading Competitions: Entries, Results and Future Directions. ICDAR (2005)","DOI":"10.1007\/s10032-004-0134-3"},{"key":"5_CR17","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":"5_CR18","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":"5_CR19","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":"5_CR20","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: Seed: semantics enhanced encoder-decoder framework for scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13528\u201313537 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"5_CR21","doi-asserted-by":"crossref","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 (2017)","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. TPAMI (2018)","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR 2017 competition on reading Chinese text in the wild (RCTW-17). In: ICDAR (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"5_CR24","unstructured":"Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence (2020)"},{"key":"5_CR25","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV (2011)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"5_CR28","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Liu, W.: A unified framework for multioriented text detection and recognition. TIP (2014)","DOI":"10.1109\/TIP.2014.2353813"},{"key":"5_CR30","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: CVPR (2012)"},{"key":"5_CR31","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":"5_CR32","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":"5_CR33","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2018)"}],"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\/978-3-030-86337-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:13:17Z","timestamp":1756851197000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}