{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:05:06Z","timestamp":1761897906987,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416781"},{"type":"electronic","value":"9783031416798"}],"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\/978-3-031-41679-8_24","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"420-434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["ICDAR 2023 Competition on\u00a0Document UnderstanDing of\u00a0Everything (DUDE)"],"prefix":"10.1007","author":[{"given":"Jordy","family":"Van Landeghem","sequence":"first","affiliation":[]},{"given":"Rub\u00e8n","family":"Tito","sequence":"additional","affiliation":[]},{"given":"\u0141ukasz","family":"Borchmann","sequence":"additional","affiliation":[]},{"given":"Micha\u0142","family":"Pietruszka","sequence":"additional","affiliation":[]},{"given":"Dawid","family":"Jurkiewicz","sequence":"additional","affiliation":[]},{"given":"Rafa\u0142","family":"Powalski","sequence":"additional","affiliation":[]},{"given":"Pawe\u0142","family":"J\u00f3ziak","sequence":"additional","affiliation":[]},{"given":"Sanket","family":"Biswas","sequence":"additional","affiliation":[]},{"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[]},{"given":"Tomasz","family":"Stanis\u0142awek","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"24_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: ICDAR 2019 competition on scene text visual question answering. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1563\u20131570. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00251"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Scene text visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"24_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"24_CR5","doi-asserted-by":"publisher","unstructured":"Dhuliawala, S., Adolphs, L., Das, R., Sachan, M.: Calibration of machine reading systems at scale. In: Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland, pp. 1682\u20131693 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.133, https:\/\/aclanthology.org\/2022.findings-acl.133","DOI":"10.18653\/v1\/2022.findings-acl.133"},{"key":"24_CR6","unstructured":"D\u00eddac, S., Menon, S., Vondrick, C.: ViperGPT: visual inference via python execution for reasoning. arXiv preprint: arXiv:2303.08128 (2023)"},{"key":"24_CR7","unstructured":"Geifman, Y., El-Yaniv, R.: Selective classification for deep neural networks. In: Advances in neural information processing systems, vol. 30 (2017)"},{"key":"24_CR8","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning, ICML\u201917, vol. 70, pp. 1321\u20131330 (2017)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. arXiv preprint: arXiv:2211.11559 (2022)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"24_CR10","doi-asserted-by":"publisher","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking, MM \u201922, pp. 4083\u20134091. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"24_CR11","unstructured":"Jaeger, P.F., L\u00fcth, C.T., Klein, L., Bungert, T.J.: A call to reflect on evaluation practices for failure detection in image classification. In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=YnkGMIh0gvX"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 2, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"24_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-86337-1_40","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"A Jimeno Yepes","year":"2021","unstructured":"Jimeno Yepes, A., Zhong, P., Burdick, D.: ICDAR 2021 competition on scientific literature parsing. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 605\u2013617. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_40"},{"key":"24_CR14","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2020","unstructured":"Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: SpanBERT: improving pre-training by representing and predicting spans. Trans. Assoc. Comput. Linguist. 8, 64\u201377 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Kamath, A., Jia, R., Liang, P.: Selective question answering under domain shift. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5684\u20135696 (2020)","DOI":"10.18653\/v1\/2020.acl-main.503"},{"key":"24_CR16","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint: arXiv:2301.12597 (2023)"},{"key":"24_CR17","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"24_CR18","unstructured":"Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: International Conference on Learning Representations (2018). https:\/\/openreview.net\/forum?id=H1VGkIxRZ"},{"key":"24_CR19","unstructured":"Lin, S., Hilton, J., Evans, O.: Teaching models to express their uncertainty in words. Trans. Mach. Learn. Res. (2022). https:\/\/openreview.net\/forum?id=8s8K2UZGTZ"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: InfographicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"24_CR21","unstructured":"Mathew, M., Tito, R., Karatzas, D., Manmatha, R., Jawahar, C.: Document visual question answering challenge 2020. arXiv preprint: arXiv:2008.08899 (2020)"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Naeini, M.P., Cooper, G., Hauskrecht, M.: Obtaining well calibrated probabilities using Bayesian binning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29 (2015)","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"24_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-030-86331-9_47","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Powalski","year":"2021","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: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 732\u2013747. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_47"},{"key":"24_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-030-86549-8_7","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"L Qiao","year":"2021","unstructured":"Qiao, L., et al.: LGPMA: complicated table structure recognition with local and global pyramid mask alignment. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 99\u2013114. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_7"},{"issue":"140","key":"24_CR25","first-page":"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\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Raja, S., Mondal, A., Jawahar, C.: ICDAR 2023 competition on visual question answering on business document images (2023)","DOI":"10.1007\/978-3-031-41679-8_26"},{"issue":"3","key":"24_CR27","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s00799-022-00329-y","volume":"23","author":"T Saikh","year":"2022","unstructured":"Saikh, T., Ghosal, T., Mittal, A., Ekbal, A., Bhattacharyya, P.: ScienceQA: a novel resource for question answering on scholarly articles. Int. J. Digit. Libr. 23(3), 289\u2013301 (2022)","journal-title":"Int. J. Digit. Libr."},{"key":"24_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-86549-8_36","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"T Stanis\u0142awek","year":"2021","unstructured":"Stanis\u0142awek, T., et al.: Kleister: key information extraction datasets involving long documents with complex layouts. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 564\u2013579. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_36"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. arXiv preprint: arXiv:2212.02623 (2022)","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"24_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1007\/978-3-030-86331-9_50","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Tito","year":"2021","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Document collection visual question answering. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 778\u2013792. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_50"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multi-page DocVQA. arXiv preprint: arXiv:2212.05935 (2022)","DOI":"10.2139\/ssrn.4466918"},{"key":"24_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1007\/978-3-030-86337-1_42","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Tito","year":"2021","unstructured":"Tito, R., Mathew, M., Jawahar, C.V., Valveny, E., Karatzas, D.: ICDAR 2021 competition on document visual question answering. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 635\u2013649. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_42"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Van Landeghem, J., et al.: Document understanding dataset and evaluation (DUDE). In: International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"24_CR34","doi-asserted-by":"publisher","unstructured":"Yang, Y., Wang, H., Katabi, D.: On multi-domain long-tailed recognition, imbalanced domain generalization and beyond. In: Computer Vision - ECCV 2022: 17th European Conference, Proceedings, Part XX, Tel Aviv, Israel, 23\u201327 October 2022, pp. 57\u201375. Springer-Verlag, Berlin, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_4","DOI":"10.1007\/978-3-031-20044-1_4"},{"key":"24_CR35","doi-asserted-by":"publisher","unstructured":"Yang, Z., Qi, P., et al.: HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2369\u20132380. Association for Computational Linguistics, Brussels (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1259, https:\/\/aclanthology.org\/D18-1259","DOI":"10.18653\/v1\/D18-1259"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"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\/978-3-031-41679-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:42:56Z","timestamp":1729935776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_24","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)"}}]}}