{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T10:07:08Z","timestamp":1743502028346,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250682"},{"type":"electronic","value":"9783031250699"}],"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\/978-3-031-25069-9_19","type":"book-chapter","created":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T00:15:46Z","timestamp":1676333746000},"page":"280-296","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["End-to-End Document Recognition and\u00a0Understanding with\u00a0Dessurt"],"prefix":"10.1007","author":[{"given":"Brian","family":"Davis","sequence":"first","affiliation":[]},{"given":"Bryan","family":"Morse","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Price","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Tensmeyer","sequence":"additional","affiliation":[]},{"given":"Curtis","family":"Wigington","sequence":"additional","affiliation":[]},{"given":"Vlad","family":"Morariu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,14]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"19_CR2","unstructured":"Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. Advances in Neural Information Processing Systems (NIPS) (2016)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chung, J., Delteil, T.: A computationally efficient pipeline approach to full page offline handwritten text recognition. In: International Conference on Document Analysis and Recognition Workshops (ICDARW). IEEE (2019)","DOI":"10.1109\/ICDARW.2019.40078"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3144899"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: International Conference on Document Analysis and Recognition (ICDAR). IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00030"},{"key":"19_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-030-86549-8_27","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"B Davis","year":"2021","unstructured":"Davis, B., Morse, B., Price, B., Tensmeyer, C., Wiginton, C.: Visual FUDGE: form understanding via dynamic graph editing. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 416\u2013431. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_27"},{"key":"19_CR7","unstructured":"Davis, B., Tensmeyer, C., Price, B., Wigington, C., Morse, B., Jain, R.: Text and style conditioned gan for generation of offline handwriting lines (2020)"},{"key":"19_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (2019)"},{"key":"19_CR9","unstructured":"Foundation, W.: Wikimedia downloads. https:\/\/dumps.wikimedia.org"},{"key":"19_CR10","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: International Conference on Document Analysis and Recognition (ICDAR)"},{"key":"19_CR11","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv preprint arXiv:1503.02531 2 (2015)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: Bros: A pre-trained language model focusing on text and layout for better key information extraction from documents. arXiv preprint arXiv:2108.04539 (2021)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Hwang, W., Lee, H., Yim, J., Kim, G., Seo, M.: Cost-effective end-to-end information extraction for semi-structured document images. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.271"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: Funsd: A dataset for form understanding in noisy scanned documents. In: International Conference on Document Analysis and Recognition Workshops (ICDARW). IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"19_CR15","unstructured":"Kim, G., et al.: Donut: document understanding transformer without ocr. arXiv preprint arXiv:2111.15664 (2021)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Klaiman, S., Lehne, M.: Docreader: bounding-box free training of a document information extraction model. In: International Conference on Document Analysis and Recognition (ICDAR) (2021)","DOI":"10.1007\/978-3-030-86549-8_29"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a test collection for complex document information processing. In: ACM SIGIR Conference on Research and Development in Information Retrieval (2006)","DOI":"10.1145\/1148170.1148307"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: 58th Annual Meeting of the Association for Computational Linguistics (ACL) (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"19_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Marti, U.V., Bunke, H.: The iam-database: an English sentence database for offline handwriting recognition. International Journal on Document Analysis and Recognition 5(1) (2002)","DOI":"10.1007\/s100320200071"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Mathew, M., Gomez, L., Karatzas, D., Jawahar, C.: Asking questions on handwritten document collections. Int. J. Document Anal. Recogn. (IJDAR) 24(3) (2021)","DOI":"10.1007\/s10032-021-00383-3"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Powalski, R., Borchmann, \u0141., Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa\u0142ka, G.: Going full-tilt boogie on document understanding with text-image-layout transformer. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 732\u2013747 (2021)","DOI":"10.1007\/978-3-030-86331-9_47"},{"key":"19_CR25","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"19_CR27","unstructured":"Rowtula, V., Krishnan, P., Jawahar, C., CVIT, I.: Pos tagging and named entity recognition on handwritten documents. In: International Conference on Natural Language Processing (ICNLP) (2018)"},{"key":"19_CR28","doi-asserted-by":"publisher","unstructured":"Smith, R.: An overview of the tesseract ocr engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) (2007). https:\/\/doi.org\/10.1109\/ICDAR.2007.4376991","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Toledo, J.I., Carbonell, M., Forn\u00e9s, A., Llad\u00f3s, J.: Information extraction from historical handwritten document images with a context-aware neural model. Pattern Recogn. 86 (2019)","DOI":"10.1016\/j.patcog.2018.08.020"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"T\u00fcselmann, O., M\u00fcller, F., Wolf, F., Fink, G.A.: Recognition-free question answering on handwritten document collections. arXiv preprint arXiv:2202.06080 (2022)","DOI":"10.1007\/978-3-031-21648-0_18"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"T\u00fcselmann, O., Wolf, F., Fink, G.A.: Are end-to-end systems really necessary for ner on handwritten document images? In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) International Conference on Document Analysis and Recognition (ICDAR) (2021)","DOI":"10.1007\/978-3-030-86331-9_52"},{"key":"19_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Wigington, C., Stewart, S., Davis, B., Barrett, B., Price, B., Cohen, S.: Data augmentation for recognition of handwritten words and lines using a cnn-lstm network. In: International Conference on Document Analysis and Recognition (ICDAR) (2017)","DOI":"10.1109\/ICDAR.2017.110"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen, S.: Start, follow, read: End-to-end full-page handwriting recognition. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01231-1_23"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: 59th Annual Meeting of the Association for Computational Linguistics (ACL) (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: International Conference on Knowledge Discovery & Data Mining (KDD) (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Yousef, M., Bishop, T.E.: Origaminet: weakly-supervised, segmentation-free, one-step, full page text recognition by learning to unfold. In: Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01472"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25069-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:51:56Z","timestamp":1709815916000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25069-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250682","9783031250699"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19","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":"14 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}