{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:02:45Z","timestamp":1780081365109,"version":"3.54.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863302","type":"print"},{"value":"9783030863319","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86331-9_50","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"778-792","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Document Collection Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Rub\u00e8n","family":"Tito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ernest","family":"Valveny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"issue":"12","key":"50_CR1","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2552\u20132566 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50_CR2","unstructured":"Amazon: Amazon textract (2021). https:\/\/aws.amazon.com\/es\/textract\/. Accessed 11 Jan 2021"},{"key":"50_CR3","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":"50_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/978-3-030-58589-1_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Bansal","year":"2020","unstructured":"Bansal, A., Zhang, Y., Chellappa, R.: Visual question answering on image sets. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXI. LNCS, vol. 12366, pp. 51\u201367. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_4"},{"key":"50_CR5","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":"50_CR6","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, pp. 4291\u20134301 (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"50_CR7","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"50_CR8","doi-asserted-by":"crossref","unstructured":"Co\u00fcasnon, B., Lemaitre, A.: Recognition of tables and forms (2014)","DOI":"10.1007\/978-0-85729-859-1_20"},{"key":"50_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/3-540-45869-7_47","volume-title":"Document Analysis Systems V","author":"AR Dengel","year":"2002","unstructured":"Dengel, A.R., Klein, B.: smartFIX: a requirements-driven system for document analysis and understanding. In: Lopresti, D., Hu, J., Kashi, R. (eds.) DAS 2002. LNCS, vol. 2423, pp. 433\u2013444. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45869-7_47"},{"key":"50_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. ACL (2019)"},{"key":"50_CR11","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., Zhang, S., Wang, W., Zhang, C., Huang, H.: Heterogeneous memory enhanced multimodal attention model for video question answering. In: Proceedings of the IEEE\/CVF Conference on CVPR, pp. 1999\u20132007 (2019)","DOI":"10.1109\/CVPR.2019.00210"},{"key":"50_CR12","unstructured":"Google: Google OCR (2020). https:\/\/cloud.google.com\/solutions\/document-ai. Accessed 10 Dec 2020"},{"key":"50_CR13","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for TextVQA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01001"},{"issue":"5","key":"50_CR14","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/34.291440","volume":"16","author":"JJ Hull","year":"1994","unstructured":"Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 550\u2013554 (1994)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50_CR15","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B., Cohen, S., Kanan, C.: DVQA: understanding data visualizations via question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5648\u20135656 (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"50_CR16","unstructured":"Kahou, S.E., Michalski, V., Atkinson, A., K\u00e1d\u00e1r, \u00c1., Trischler, A., Bengio, Y.: FigureQA: an annotated figure dataset for visual reasoning. arXiv preprint arXiv:1710.07300 (2017)"},{"key":"50_CR17","doi-asserted-by":"crossref","unstructured":"Krishnan, P., Dutta, K., Jawahar, C.V.: Word spotting and recognition using deep embedding. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 1\u20136 (2018)","DOI":"10.1109\/DAS.2018.70"},{"key":"50_CR18","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet Physics doklady, pp. 707\u2013710. Soviet Union (1966)"},{"issue":"3","key":"50_CR19","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1561\/1500000016","volume":"3","author":"TY Liu","year":"2009","unstructured":"Liu, T.Y.: Learning to rank for information retrieval. Found. Trends Inf. Retr. 3(3), 225\u2013331 (2009)","journal-title":"Found. Trends Inf. Retr."},{"key":"50_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: Proceedings of the 2019 Conference of the North American Chapter on Computational Linguistics, pp. 32\u201339 (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"50_CR21","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. arXiv preprint arXiv:1410.0210 (2014)"},{"key":"50_CR22","unstructured":"Manmatha, R., Croft, W.: Word spotting: indexing handwritten archives. In: Intelligent Multimedia Information Retrieval Collection, pp. 43\u201364 (1997)"},{"key":"50_CR23","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF WACV, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"50_CR24","unstructured":"Mathew, M., Tito, R., Karatzas, D., Manmatha, R., Jawahar, C.: Document visual question answering challenge 2020. arXiv e-prints, pp. arXiv-2008 (2020)"},{"key":"50_CR25","doi-asserted-by":"crossref","unstructured":"Mouch\u00e8re, H., Viard-Gaudin, C., Zanibbi, R., Garain, U.: ICFHR 2016 CROHME: competition on recognition of online handwritten mathematical expressions. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) (2016)","DOI":"10.1109\/ICFHR.2016.0116"},{"key":"50_CR26","doi-asserted-by":"crossref","unstructured":"Palm, R.B., Winther, O., Laws, F.: Cloudscan - a configuration-free invoice analysis system using recurrent neural networks. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 406\u2013413 (2017)","DOI":"10.1109\/ICDAR.2017.74"},{"key":"50_CR27","doi-asserted-by":"crossref","unstructured":"Rath, T.M., Manmatha, R.: Word image matching using dynamic time warping. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings, vol. 2, pp. II-II. IEEE (2003)","DOI":"10.1109\/CVPR.2003.1211511"},{"key":"50_CR28","unstructured":"Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. arXiv preprint arXiv:1505.02074 (2015)"},{"key":"50_CR29","doi-asserted-by":"crossref","unstructured":"Schuster, D., et al.: Intellix - end-user trained information extraction for document archiving. In: 2013 12th ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.28"},{"key":"50_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-319-46478-7_41","volume-title":"Computer Vision \u2013 ECCV 2016","author":"N Siegel","year":"2016","unstructured":"Siegel, N., Horvitz, Z., Levin, R., Divvala, S., Farhadi, A.: FigureSeer: parsing result-figures in research papers. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VII. LNCS, vol. 9911, pp. 664\u2013680. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_41"},{"key":"50_CR31","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"50_CR32","doi-asserted-by":"crossref","unstructured":"Sudholt, S., Fink, G.A.: Evaluating word string embeddings and loss functions for CNN-based word spotting. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 493\u2013498 (2017)","DOI":"10.1109\/ICDAR.2017.87"},{"key":"50_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"50_CR34","doi-asserted-by":"crossref","unstructured":"Wilkinson, T., Lindstr\u00f6m, J., Brun, A.: Neural ctrl-f: segmentation-free query-by-string word spotting in handwritten manuscript collections. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4443\u20134452 (2017)","DOI":"10.1109\/ICCV.2017.475"},{"key":"50_CR35","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics (2020)"},{"key":"50_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: KDD 2020, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"50_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: TRIE: end-to-end text reading and information extraction for document understanding, pp. 1413\u20131422 (2020)","DOI":"10.1145\/3394171.3413900"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86331-9_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:06:14Z","timestamp":1756937174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","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":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","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":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"Additionally, 13 competition reports are included.","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)"}}]}}