{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:33:09Z","timestamp":1763202789099,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031417306"},{"type":"electronic","value":"9783031417313"}],"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\/978-3-031-41731-3_5","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T06:02:26Z","timestamp":1692338546000},"page":"70-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["E2TIMT: Efficient and\u00a0Effective Modal Adapter for\u00a0Text 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":"5_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H., Way, A.: Integrating optical character recognition and machine translation of historical documents.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, Osaka, Japan, December 2016, pp. 109\u2013116 (2016)"},{"key":"5_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, 2019, pp. 4714\u20134722 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"issue":"3","key":"5_CR3","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. Doc. Anal. Recogn. (IJDAR) 18(3), 235\u2013247 (2015). https:\/\/doi.org\/10.1007\/s10032-015-0247-x","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"5_CR4","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. Multimed. (TMM), 1\u201313 (2022)","DOI":"10.1109\/TMM.2022.3183386"},{"key":"5_CR5","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 2020, Virtual Event\/Milan, Italy, 10\u201315 January 2021, pp. 3122\u20133129 (2020)","DOI":"10.1109\/ICPR48806.2021.9412281"},{"key":"5_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"5_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 2011, Beijing, China, 18\u201321 September 2011, pp. 809\u2013813. IEEE Computer Society (2011)","DOI":"10.1109\/ICDAR.2011.166"},{"key":"5_CR8","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, May 13\u201315, 2010. JMLR Proceedings, vol. 9, pp. 249\u2013256. JMLR.org (2010)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27\u201330 June 2016, pp. 2315\u20132324. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"5_CR10","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, 2\u20139 February 2021 (2021)"},{"key":"5_CR11","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)"},{"key":"5_CR12","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. CoRR abs\/1406.2227 (2014)"},{"issue":"6","key":"5_CR13","doi-asserted-by":"publisher","first-page":"4451","DOI":"10.1007\/s00500-020-05455-w","volume":"25","author":"H Kaur","year":"2021","unstructured":"Kaur, H., Kumar, M.: Offline handwritten Gurumukhi word recognition using extreme gradient boosting methodology. Soft. Comput. 25(6), 4451\u20134464 (2021)","journal-title":"Soft. Comput."},{"issue":"7","key":"5_CR14","doi-asserted-by":"publisher","first-page":"11155","DOI":"10.1007\/s11042-020-10297-7","volume":"80","author":"H Kaur","year":"2021","unstructured":"Kaur, H., Kumar, M.: On the recognition of offline handwritten word using holistic approach and AdaBoost methodology. Multim. Tools Appl. 80(7), 11155\u201311175 (2021)","journal-title":"Multim. Tools Appl."},{"key":"5_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Le, H., Pino, J.M., Wang, C., Gu, J., Schwab, D., Besacier, L.: Lightweight adapter tuning for multilingual speech translation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 2: Short Papers), Virtual Event, 1\u20136 August 2021, pp. 817\u2013824. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-short.103"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5\u201310 July 2020, pp. 7871\u20137880. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 4582\u20134597. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"5_CR19","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":"5_CR20","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. Association for Computational Linguistics, November 2020","DOI":"10.18653\/v1\/2020.nlpbt-1.8"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 6\u201312 July 2002, Philadelphia, PA, USA, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"5_CR22","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training. Open AI Blog (2018)"},{"key":"5_CR23","first-page":"140:1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1-140:67 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR24","unstructured":"Rebuffi, S., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4\u20139 December 2017, Long Beach, CA, USA, pp. 506\u2013516 (2017)"},{"key":"5_CR25","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1162\/tacl_a_00313","volume":"8","author":"S Rothe","year":"2020","unstructured":"Rothe, S., Narayan, S., Severyn, A.: Leveraging pre-trained checkpoints for sequence generation tasks. Trans. Assoc. Comput. Linguist. 8, 264\u2013280 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"5_CR26","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":"5_CR27","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":"5_CR28","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":"5_CR29","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":"5_CR30","doi-asserted-by":"crossref","unstructured":"Sun, Z., Wang, M., Li, L.: Multilingual translation via grafting pre-trained language models. In: Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event\/Punta Cana, Dominican Republic, 16\u201320 November 2021. ,p. 2735\u20132747. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.233"},{"key":"5_CR31","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":"5_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4\u20139 December 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017)"},{"key":"5_CR33","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2022, Dublin, Ireland, 22\u201327 May 2022, pp. 1\u20139. Association for Computational Linguistics (2022)"},{"key":"5_CR34","unstructured":"Zhang, H., Li, G., Li, J., Zhang, Z., Zhu, Y., Jin, Z.: Fine-tuning pre-trained language models effectively by optimizing subnetworks adaptively. CoRR abs\/2211.01642 (2022)"},{"key":"5_CR35","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., et al. (eds.) PRCV 2019. LNCS, vol. 11859, pp. 184\u2013198. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31726-3_16"},{"key":"5_CR36","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":"5_CR37","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, Barcelona, Spain (Online), 8\u201313 December 2020, pp. 4495\u20134505. International Committee on Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.coling-main.397"},{"key":"5_CR38","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. ijcai.org (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\/978-3-031-41731-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T06:03:33Z","timestamp":1692338613000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41731-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417306","9783031417313"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41731-3_5","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)"}}]}}