{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:54:27Z","timestamp":1772906067558,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416750","type":"print"},{"value":"9783031416767","type":"electronic"}],"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\/978-3-031-41676-7_28","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"484-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-teacher Knowledge Distillation for\u00a0End-to-End Text Image Machine Translation"],"prefix":"10.1007","author":[{"given":"Cong","family":"Ma","sequence":"first","affiliation":[]},{"given":"Yaping","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Mei","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"28_CR1","unstructured":"Afli, H., Way, A.: Integrating optical character recognition and machine translation of historical documents. In: Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities, LT4DH@COLING, pp. 109\u2013116 (2016)"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, pp. 4714\u20134722 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"issue":"9","key":"28_CR3","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., Yang, J.: An image-based automatic Arabic translation system. Pattern Recognit. 42(9), 2127\u20132134 (2009)","journal-title":"Pattern Recognit."},{"issue":"3","key":"28_CR4","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s10032-015-0247-x","volume":"18","author":"J Chen","year":"2015","unstructured":"Chen, J., Cao, H., Natarajan, P.: Integrating natural language processing with image document analysis: what we learned from two real-world applications. Int. J. Document Anal. Recognit. 18(3), 235\u2013247 (2015)","journal-title":"Int. J. Document Anal. Recognit."},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yin, F., Yang, Q., Liu, C.L.: Cross-lingual text image recognition via multi-hierarchy cross-modal mimic. IEEE Trans. Multimedia (TMM), pp. 1\u201313 (2022)","DOI":"10.1109\/TMM.2022.3183386"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yin, F., Zhang, X., Yang, Q., Liu, C.: Cross-lingual text image recognition via multi-task sequence to sequence learning. In: 25th International Conference on Pattern Recognition (ICPR), pp. 3122\u20133129 (2020)","DOI":"10.1109\/ICPR48806.2021.9412281"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Du, J., Huo, Q., Sun, L., Sun, J.: Snap and translate using windows phone. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 809\u2013813. IEEE Computer Society (2011)","DOI":"10.1109\/ICDAR.2011.166"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Hinami, R., Ishiwatari, S., Yasuda, K., Matsui, Y.: Towards fully automated manga translation. In: The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI) (2021)","DOI":"10.1609\/aaai.v35i14.17537"},{"key":"28_CR10","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. CoRR abs\/1503.02531 (2015)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, 1\u20134 November 2016, pp. 1317\u20131327. The Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/D16-1139"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: End-to-end speech translation with knowledge distillation. In: Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15\u201319 September 2019, pp. 1128\u20131132. ISCA (2019)","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Ma, C., et al.: Improving end-to-end text image translation from the auxiliary text translation task. In: 26th International Conference on Pattern Recognition, ICPR 2022, Montreal, QC, Canada, 21\u201325 August 2022, pp. 1664\u20131670. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956695"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Mansimov, E., Stern, M., Chen, M., Firat, O., Uszkoreit, J., Jain, P.: Towards end-to-end in-image neural machine translation. In: Proceedings of the First International Workshop on Natural Language Processing Beyond Text, pp. 70\u201374. Association for Computational Linguistics, Online (Nov 2020)","DOI":"10.18653\/v1\/2020.nlpbt-1.8"},{"key":"28_CR15","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-981-33-4543-0_30","volume-title":"Innovations in Computer Science and Engineering","author":"KC Shekar","year":"2021","unstructured":"Shekar, K.C., Cross, M.A., Vasudevan, V.: Optical character recognition and neural machine translation using deep learning techniques. In: Saini, H.S., Sayal, R., Govardhan, A., Buyya, R. (eds.) Innovations in Computer Science and Engineering. LNNS, vol. 171, pp. 277\u2013283. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-33-4543-0_30"},{"issue":"11","key":"28_CR16","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. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 4168\u20134176. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"28_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-030-86331-9_7","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"T Su","year":"2021","unstructured":"Su, T., Liu, S., Zhou, S.: RTNet: an end-to-end method for handwritten text image translation. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 99\u2013113. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_7"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Sun, H., Wang, R., Chen, K., Utiyama, M., Sumita, E., Zhao, T.: Knowledge distillation for multilingual unsupervised neural machine translation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5\u201310 July 2020, pp. 3525\u20133535 (2020)","DOI":"10.18653\/v1\/2020.acl-main.324"},{"key":"28_CR20","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 8\u201313 December 2014, Montreal, Quebec, Canada, pp. 3104\u20133112 (2014)"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Tan, X., Ren, Y., He, D., Qin, T., Zhao, Z., Liu, T.: Multilingual neural machine translation with knowledge distillation. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019","DOI":"10.18653\/v1\/D19-1089"},{"key":"28_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"28_CR23","unstructured":"Watanabe, Y., Okada, Y., Kim, Y., Takeda, T.: Translation camera. In: Fourteenth International Conference on Pattern Recognition, ICPR 1998, Brisbane, Australia, 16\u201320 August 1998, pp. 613\u2013617 (1998)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Br\u00e9gier, R., Combaluzier, H., Leroy, V., Rogez, G.: DOPE: distillation of part experts for whole-body 3D pose estimation in the wild. In: Computer Vision - ECCV 2020\u201316th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XXVI. vol. 12371, pp. 380\u2013397 (2020)","DOI":"10.1007\/978-3-030-58574-7_23"},{"issue":"9","key":"28_CR25","doi-asserted-by":"publisher","first-page":"1664","DOI":"10.4304\/jsw.6.9.1664-1671","volume":"6","author":"F Wong","year":"2011","unstructured":"Wong, F., Chao, S., Chan, W.K.: Cyclops - snapshot translation system based on mobile device. J. Softw. 6(9), 1664\u20131671 (2011)","journal-title":"J. Softw."},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Yang, J., Chen, X., Zhang, J., Zhang, Y., Waibel, A.: Automatic detection and translation of text from natural scenes. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2002, 13\u201317 May 2002, Orlando, Florida, USA, pp. 2101\u20132104 (2002)","DOI":"10.1109\/ICASSP.2002.5745049"},{"key":"28_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/978-3-030-31726-3_16","volume-title":"Pattern Recognition and Computer Vision","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Nie, S., Liang, S., Liu, W.: Bidirectional adversarial domain adaptation with semantic consistency. In: Lin, Z. (ed.) PRCV 2019. LNCS, vol. 11859, pp. 184\u2013198. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31726-3_16"},{"key":"28_CR28","doi-asserted-by":"publisher","first-page":"3922","DOI":"10.1109\/TIP.2021.3066903","volume":"30","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Nie, S., Liang, S., Liu, W.: Robust text image recognition via adversarial sequence-to-sequence domain adaptation. IEEE Trans. Image Process. 30, 3922\u20133933 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiang, L., Zhu, J., Zhang, J., Zhou, Y., Zong, C.: Knowledge graph enhanced neural machine translation via multi-task learning on sub-entity granularity. In: Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, 8\u201313 December 2020, pp. 4495\u20134505 (2020)","DOI":"10.18653\/v1\/2020.coling-main.397"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhang, J., Zhou, Y., Zong, C.: Knowledge graphs enhanced neural machine translation. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pp. 4039\u20134045 (2020)","DOI":"10.24963\/ijcai.2020\/559"}],"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\/978-3-031-41676-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:38:00Z","timestamp":1729935480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41676-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416750","9783031416767"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41676-7_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}