{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:29:58Z","timestamp":1742912998279,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031065545"},{"type":"electronic","value":"9783031065552"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-06555-2_44","type":"book-chapter","created":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T09:10:13Z","timestamp":1652778613000},"page":"659-673","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["QAlayout: Question Answering Layout Based on Multimodal Attention for Visual Question Answering on Corporate Document"],"prefix":"10.1007","author":[{"given":"Ibrahim Souleiman","family":"Mahamoud","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aur\u00e9lie","family":"Joseph","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent Poulain","family":"d\u2019Andecy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Marc","family":"Ogier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,18]]},"reference":[{"unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016)","key":"44_CR1"},{"doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: ICDAR 2019 competition on scene text visual question answering (2019)","key":"44_CR2","DOI":"10.1109\/ICCV.2019.00439"},{"unstructured":"Cheng, H., Zhou, J.T., Tay, W.P., Wen, B.: Attentive graph neural networks for few-shot learning (2020)","key":"44_CR3"},{"doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions (2017)","key":"44_CR4","DOI":"10.1109\/CVPR.2017.195"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2019)","key":"44_CR5"},{"key":"44_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/978-3-030-86549-8_34","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"L Garncarek","year":"2021","unstructured":"Garncarek, L., et al.: LAMBERT: layout-aware language modeling for information extraction. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 532\u2013547. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_34"},{"doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in Visual Question Answering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","key":"44_CR7","DOI":"10.1109\/CVPR.2017.670"},{"doi-asserted-by":"crossref","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) (2015)","key":"44_CR8","DOI":"10.1109\/ICDAR.2015.7333910"},{"doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 991\u2013995. IEEE (2015)","key":"44_CR9","DOI":"10.1109\/ICDAR.2015.7333910"},{"doi-asserted-by":"crossref","unstructured":"Lin, W., Gao, Q., Sun, L., Zhong, Z., Hu, K., Ren, Q., Huo, Q.: VIBERTgrid: a jointly trained multi-modal 2D document representation for key information extraction from documents (2021)","key":"44_CR10","DOI":"10.1007\/978-3-030-86549-8_35"},{"unstructured":"Lin, Z., et al.: Medical visual question answering: a survey (2021)","key":"44_CR11"},{"unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019)","key":"44_CR12"},{"doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: a dataset for VQA on document images (2021)","key":"44_CR13","DOI":"10.1109\/WACV48630.2021.00225"},{"doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for squad (2018)","key":"44_CR14","DOI":"10.18653\/v1\/P18-2124"},{"unstructured":"Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension (2018)","key":"44_CR15"},{"unstructured":"TOMSETT, D.: https:\/\/digitalhumans.com","key":"44_CR16"},{"unstructured":"Vaswani, A., et al.: Attention is all you need (2017)","key":"44_CR17"},{"doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, J., Li, Q., Hwang, M.Y., Zong, C., Li, Z.: Incremental learning from scratch for task-oriented dialogue systems (2019)","key":"44_CR18","DOI":"10.18653\/v1\/P19-1361"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Yao, Q., Kwok, J., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning (2020)","key":"44_CR19","DOI":"10.1145\/3386252"},{"doi-asserted-by":"crossref","unstructured":"Wu, J., Lu, J., Sabharwal, A., Mottaghi, R.: Multi-modal answer validation for knowledge-based VQA (2021)","key":"44_CR20","DOI":"10.1609\/aaai.v36i3.20174"},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding (2022)","key":"44_CR21","DOI":"10.18653\/v1\/2021.acl-long.201"},{"doi-asserted-by":"publisher","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: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, July 2020. https:\/\/doi.org\/10.1145\/3394486.3403172, http:\/\/dx.doi.org\/10.1145\/3394486.3403172","key":"44_CR22","DOI":"10.1145\/3394486.3403172"},{"unstructured":"Yu, A.W., et al.: QANet: combining local convolution with global self-attention for reading comprehension (2018)","key":"44_CR23"},{"unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization (2017)","key":"44_CR24"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06555-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:09:23Z","timestamp":1710259763000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06555-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031065545","9783031065552"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06555-2_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"18 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Document Analysis Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"La Rochelle","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"22 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"das2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/das2022.univ-lr.fr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"94","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":"52","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":"16","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":"55% - 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":"2.85","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)"}}]}}