{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:17:52Z","timestamp":1771949872608,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585945","type":"print"},{"value":"9783030585952","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58595-2_6","type":"book-chapter","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T03:29:28Z","timestamp":1605842968000},"page":"85-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["An End-to-End OCR Text Re-organization Sequence Learning for Rich-Text Detail Image Comprehension"],"prefix":"10.1007","author":[{"given":"Liangcheng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Bu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongpan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"6_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"issue":"6","key":"6_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355610","volume":"52","author":"GM Binmakhashen","year":"2019","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surveys (CSUR) 52(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surveys (CSUR)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: PhotoOCR: reading text in uncontrolled conditions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 785\u2013792 (2013)","DOI":"10.1109\/ICCV.2013.102"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Busta, M., Neumann, L., Matas, J.: Deep TextSpotter: an end-to-end trainable scene text localization and recognition framework. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2204\u20132212 (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chakraborty, A., Paranjape, B., Kakarla, S., Ganguly, N.: Stop clickbait: detecting and preventing clickbaits in online news media. In: 2016 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 9\u201316. IEEE (2016)","DOI":"10.1109\/ASONAM.2016.7752207"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, J., Lapata, M.: Neural summarization by extracting sentences and words. arXiv preprint arXiv:1603.07252 (2016)","DOI":"10.18653\/v1\/P16-1046"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Y., et al.: Fused text segmentation networks for multi-oriented scene text detection. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3604\u20133609. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Eriguchi, A., Hashimoto, K., Tsuruoka, Y.: Tree-to-sequence attentional neural machine translation. arXiv preprint arXiv:1603.06075 (2016)","DOI":"10.18653\/v1\/P16-1078"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Filippova, K., Alfonseca, E., Colmenares, C.A., Kaiser, L., Vinyals, O.: Sentence compression by deletion with LSTMs. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 360\u2013368 (2015)","DOI":"10.18653\/v1\/D15-1042"},{"key":"6_CR11","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1109\/PGEC.1964.263781","volume":"2","author":"H Freeman","year":"1964","unstructured":"Freeman, H., Garder, L.: Apictorial Jigsaw puzzles: the computer solution of a problem in pattern recognition. IEEE Trans. Electron. Comput. 2, 118\u2013127 (1964)","journal-title":"IEEE Trans. Electron. Comput."},{"key":"6_CR12","unstructured":"Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint arXiv:1410.5401 (2014)"},{"issue":"1","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vis. 116(1), 1\u201320 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.patcog.2016.01.008","volume":"54","author":"V Khare","year":"2016","unstructured":"Khare, V., Shivakumara, P., Raveendran, P., Blumenstein, M.: A blind deconvolution model for scene text detection and recognition in video. Pattern Recogn. 54, 128\u2013148 (2016)","journal-title":"Pattern Recogn."},{"key":"6_CR15","unstructured":"Kool, W., van Hoof, H., Welling, M.: Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475 (2018)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint arXiv:1903.11279 (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving Jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Pomeranz, D., Shemesh, M., Ben-Shahar, O.: A fully automated greedy square jigsaw puzzle solver. In: CVPR 2011, pp. 9\u201316. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995331"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Rong, X., Yi, C., Tian, Y.: Unambiguous text localization and retrieval for cluttered scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5494\u20135502 (2017)","DOI":"10.1109\/CVPR.2017.349"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. California Univ San Diego La Jolla Inst for Cognitive Science, Tech. rep. (1985)","DOI":"10.21236\/ADA164453"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Cruz, R.S., Fernando, B., Cherian, A., Gould, S.: DeepPermNet: visual permutation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3949\u20133957 (2017)","DOI":"10.1109\/CVPR.2017.640"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368 (2017)","DOI":"10.18653\/v1\/P17-1099"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Sholomon, D., David, O., Netanyahu, N.S.: A genetic algorithm-based solver for very large Jigsaw puzzles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1767\u20131774 (2013)","DOI":"10.1109\/CVPR.2013.231"},{"issue":"2","key":"6_CR25","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1214\/aoms\/1177703591","volume":"35","author":"R Sinkhorn","year":"1964","unstructured":"Sinkhorn, R.: A relationship between arbitrary positive matrices and doubly stochastic matrices. Ann. Math. Stat. 35(2), 876\u2013879 (1964)","journal-title":"Ann. Math. Stat."},{"issue":"2","key":"6_CR26","doi-asserted-by":"publisher","first-page":"343","DOI":"10.2140\/pjm.1967.21.343","volume":"21","author":"R Sinkhorn","year":"1967","unstructured":"Sinkhorn, R., Knopp, P.: Concerning nonnegative matrices and doubly stochastic matrices. Pac. J. Math. 21(2), 343\u2013348 (1967)","journal-title":"Pac. J. Math."},{"key":"6_CR27","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"6_CR28","unstructured":"Vinyals, O., Bengio, S., Kudlur, M.: Order matters: sequence to sequence for sets. arXiv preprint arXiv:1511.06391 (2015)"},{"key":"6_CR29","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, pp. 2692\u20132700 (2015)"},{"key":"6_CR30","unstructured":"Weston, J., et al.: Towards AI-complete question answering: a set of prerequisite toy tasks. arXiv preprint arXiv:1502.05698 (2015)"},{"key":"6_CR31","unstructured":"Xu, K., Wu, L., Wang, Z., Feng, Y., Witbrock, M., Sheinin, V.: Graph2Seq: graph to sequence learning with attention-based neural networks. arXiv preprint arXiv:1804.00823 (2018)"},{"key":"6_CR32","unstructured":"Yin, F., Wu, Y.C., Zhang, X.Y., Liu, C.L.: Scene text recognition with sliding convolutional character models. arXiv preprint arXiv:1709.01727 (2017)"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"You, Y., Jia, W., Liu, T., Yang, W.: Improving abstractive document summarization with salient information modeling. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2132\u20132141 (2019)","DOI":"10.18653\/v1\/P19-1205"},{"issue":"1","key":"6_CR34","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10(1), 19\u201336 (2016)","journal-title":"Front. Comput. Sci."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58595-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:04:36Z","timestamp":1732061076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58595-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585945","9783030585952"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58595-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","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":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}