{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:20:10Z","timestamp":1743110410176,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463105"},{"type":"electronic","value":"9783031463112"}],"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\/978-3-031-46311-2_10","type":"book-chapter","created":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T19:01:50Z","timestamp":1698519710000},"page":"116-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Text Block Segmentation Framework for\u00a0Photo Translation"],"prefix":"10.1007","author":[{"given":"Jiajia","family":"Wu","sequence":"first","affiliation":[]},{"given":"Anni","family":"Li","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zhengyan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Allahyari, M., et al.: Text summarization techniques: a brief survey. arXiv preprint arXiv:1707.02268 (2017)","DOI":"10.14569\/IJACSA.2017.081052"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"10_CR3","unstructured":"Bahdanau, D., Cho, K.H., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Caglayan, O., et al.: Cross-lingual visual pre-training for multimodal machine translation. In: arXiv preprint arXiv:2101.10044 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.112"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"10_CR6","unstructured":"D\u2019Informatique, D.E., Ese, N., Esent, P., Au, E., Frasconi, P.P.: Long short-term memory in recurrent neural networks. EPFL (2001)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"10_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-030-58595-2_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Li","year":"2020","unstructured":"Li, L., Gao, F., Bu, J., Wang, Y., Yu, Z., Zheng, Q.: An end-to-end OCR Text Re-organization sequence learning for Rich-Text detail image comprehension. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 85\u2013100. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_6"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: TextSnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"10_CR14","unstructured":"Mikolov, T., Karafi\u00cd\u0107t, M., Burget, L., Cernock, J., Khudanpur, S.: Recurrent neural network based language model. In: Interspeech, Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September (2015)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR 2006). vol. 3, pp. 850\u2013855. IEEE (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"10_CR18","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"issue":"11","key":"10_CR19","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":"10_CR20","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"10_CR21","first-page":"369","volume":"11006","author":"LN Smith","year":"2019","unstructured":"Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. Artif. Intell. Mach. Learn. Multi-Domain Oper. Appl. 11006, 369\u2013386 (2019)","journal-title":"Artif. Intell. Mach. Learn. Multi-Domain Oper. Appl."},{"key":"10_CR22","unstructured":"St$$\\acute{{\\rm l}}$$\u017an, A., Berard, A., Besacier, L., Gall$$\\acute{{\\rm l}}$$\u0119, M.: Multilingual unsupervised neural machine translation with denoising adapters. In: Empirical Methods in Natural Language Processing (2021)"},{"key":"10_CR23","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS (2014)"},{"key":"10_CR24","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"10_CR25","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, pp. 2692\u20132700 (2015)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"10_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108214","volume":"122","author":"J Wu","year":"2022","unstructured":"Wu, J., et al.: A multimodal attention fusion network with a dynamic vocabulary for textVQA. Pattern Recogn. 122, 108214 (2022)","journal-title":"Pattern Recogn."},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., Xie, L.: Aggregation cross-entropy for sequence recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6538\u20136547 (2019)","DOI":"10.1109\/CVPR.2019.00670"},{"key":"10_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Yan, R., Peng, L., Xiao, S., Yao, G.: Primitive representation learning for scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2021)","DOI":"10.1109\/CVPR46437.2021.00035"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., Liang, L., Kuang, Z., Jin, L., Zhang, W.: Fourier contour embedding for arbitrary-shaped text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3123\u20133131 (2021)","DOI":"10.1109\/CVPR46437.2021.00314"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Du, J.: TextMountain: accurate scene text detection via instance segmentation. Pattern Recogn. 110, 107336 (2020)","DOI":"10.1016\/j.patcog.2020.107336"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46311-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T19:03:09Z","timestamp":1698519789000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46311-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463105","9783031463112"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46311-2_10","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":"29 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","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":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","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":"166","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":"41% - 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":"3","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}