{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:44:51Z","timestamp":1762325091491,"version":"3.44.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863302"},{"type":"electronic","value":"9783030863319"}],"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\/978-3-030-86331-9_7","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"99-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["RTNet: An End-to-End Method for Handwritten Text Image Translation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8869-1664","authenticated-orcid":false,"given":"Tonghua","family":"Su","sequence":"first","affiliation":[]},{"given":"Shuchen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shengjie","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.esp.2014.09.001","volume":"37","author":"M Groves","year":"2015","unstructured":"Groves, M., Mundt, K.: Friend or foe? Google Translate in language for academic purposes. Engl. Specif. Purp. 37, 112\u2013121 (2015)","journal-title":"Engl. Specif. Purp."},{"key":"7_CR2","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., et al.: Universal transformers.\u00a0In: ICLR (2019)"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Weng, R., Wei, H., Huang, S., et al.: GRET: Global Representation Enhanced Transformer. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6464"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Tang, G., M\u00fcller, M., Rios, A., et al.: Why self-attention? a targeted evaluation of neural machine translation architectures. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1458"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Voita, E., Sennric, R., Titov, I.: The bottom-up evolution of representations in the transformer: a study with machine translation and language modeling objectives. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)","DOI":"10.18653\/v1\/D19-1448"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., et al.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,pp. 19\u20131580. ACL, Italy (2019)","DOI":"10.18653\/v1\/P19-1580"},{"key":"7_CR7","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one?\u00a0In: Advances in Neural Information Processing Systems (2019)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Raganato, A., Scherrer, Y., Tiedemann, J.: Fixed encoder self-attention patterns in transformer-based machine translation.\u00a0arXiv preprint (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.49"},{"key":"7_CR9","unstructured":"Poulos, J., Rafael, V.: \u201cAttention networks for image-to-text\u201d.\u00a0arXiv preprint, arXiv: 1712.04046 (2017)"},{"key":"7_CR10","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., et al.: Attention-based models for speech recognition.\u00a0In: Advances in Neural Information Processing Systems (2015)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Michael, J., Labahn, R., Gr\u00fcning, T., et al.: Evaluating sequence-to-sequence models for handwritten text recognition. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00208"},{"issue":"11","key":"7_CR12","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. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wei, H., Bao, F., et al.: Segmentation-free printed traditional Mongolian OCR using sequence to sequence with attention model. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE Computer Society (2017)","DOI":"10.1109\/ICDAR.2017.101"},{"key":"7_CR14","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":"7_CR15","unstructured":"Gehring, J., Auli, M., Grangier, D., et al.: Convolutional sequence to sequence learning. In: ICML, pp.1243\u20131252 (2017)"},{"issue":"9","key":"7_CR16","doi-asserted-by":"publisher","first-page":"2127","DOI":"10.1016\/j.patcog.2008.10.031","volume":"42","author":"Y Chang","year":"2009","unstructured":"Chang, Y., Chen, D., Zhang, Y., et al.: An image-based automatic Arabic translation system. Pattern Recogn. 42(9), 2127\u20132134 (2009)","journal-title":"Pattern Recogn."},{"key":"7_CR17","unstructured":"Cao, H., Chen, J., Devlin, J.: Document recognition and translation system for uncon-strained Arabic documents. In: International Conference on Pattern Recognition (2012)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Bender, O., Matusov, E., Hahn, S.: The RWTH Arabic-to-English spoken language trans-la-tion system. In: IEEE Workshop on Automatic Speech Recognition & Understanding (2008)","DOI":"10.1109\/ASRU.2007.4430145"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Jia, Y.: Direct speech-to-speech translation with a sequence-to-sequence model. In: Inters-peech (2019)","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"7_CR20","unstructured":"Morillot, O.: The UOB-Tele-com ParisTech Arabic Handwriting Recognition and Translation Systems for the OpenHart 2013 Competition (2013)"},{"key":"7_CR21","unstructured":"Alkhoury, I.: Arabic Text Recognition and Machine Translation. PhD Thesis (2015)"},{"key":"7_CR22","unstructured":"Yang, J., Gao, J., Zhang, Y.: Towards automatic sign translation. In: International Confe-rence on Human Language Technology Research (2003)"},{"issue":"10","key":"7_CR23","first-page":"50","volume":"55","author":"C Patel","year":"2012","unstructured":"Patel, C., Patel, A., Patel, D.: Optical character recognition by open source OCR tool tesse-ract: a case study. Int. J. Comput. Appl. 55(10), 50\u201356 (2012)","journal-title":"Int. J. Comput. Appl."},{"key":"7_CR24","unstructured":"Ling, W., Trancoso, I., Dyer, C.: Character-based neural machine translation. In: ACL (2016)"},{"key":"7_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"7_CR26","unstructured":"Yonghui, W.: Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint (2016)"},{"key":"7_CR27","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural Machine Translation by Jointly Learning to Align and Translate. arXiv preprint (2015)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yin, F., Zhang, X.Y., et al.: Cross-lingual text image recognition via multi-task sequence to sequence learning. In: International Conference on Pattern Recognition, pp. 3122\u20133129 (2020)","DOI":"10.1109\/ICPR48806.2021.9412281"}],"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\/978-3-030-86331-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:02:13Z","timestamp":1756936933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_7","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)"}}]}}