{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:07:22Z","timestamp":1776888442987,"version":"3.51.2"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705519","type":"print"},{"value":"9783031705526","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70552-6_13","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"219-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-page Document Visual Question Answering Using Self-attention Scoring Mechanism"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-3916","authenticated-orcid":false,"given":"Lei","family":"Kang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5657-9790","authenticated-orcid":false,"given":"Rub\u00e8n","family":"Tito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0368-9697","authenticated-orcid":false,"given":"Ernest","family":"Valveny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-4454","authenticated-orcid":false,"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"13_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":"13_CR2","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"13_CR3","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":"13_CR4","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"issue":"7","key":"13_CR5","doi-asserted-by":"publisher","first-page":"8227","DOI":"10.1109\/TPAMI.2023.3235826","volume":"45","author":"D Coquenet","year":"2023","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: Dan: a segmentation-free document attention network for handwritten document recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8227\u20138243 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR6","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-25069-9_19","volume-title":"European Conference on Computer Vision","author":"B Davis","year":"2022","unstructured":"Davis, B., Morse, B., Price, B., Tensmeyer, C., Wigington, C., Morariu, V.: End-to-end document recognition and understanding with dessurt. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13804, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19"},{"key":"13_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"13_CR8","unstructured":"Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. In: Advances in Neural Information Processing Systems, vol. 34, pp. 39\u201350 (2021)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: Layoutlmv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"13_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/978-3-031-41676-7_25","volume-title":"International Conference on Document Analysis and Recognition","author":"C Jian","year":"2023","unstructured":"Jian, C., Jin, L., Liang, L., Liu, C.: HisDoc R-CNN: robust Chinese historical document text line detection with dynamic rotational proposal network and iterative attention head. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14187, pp. 428\u2013445. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_25"},{"key":"13_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108766","volume":"129","author":"L Kang","year":"2022","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Pay attention to what you read: non-recurrent handwritten text-line recognition. Pattern Recogn. 129, 108766 (2022)","journal-title":"Pattern Recogn."},{"key":"13_CR12","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"European Conference on Computer Vision","author":"G Kim","year":"2022","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29"},{"key":"13_CR13","unstructured":"Lee, K., et al.: Pix2struct: screenshot parsing as pretraining for visual language understanding. In: International Conference on Machine Learning, pp. 18893\u201318912. PMLR (2023)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., Cui, L., Zhang, C., Wei, F.: DIT: self-supervised pre-training for document image transformer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3530\u20133539 (2022)","DOI":"10.1145\/3503161.3547911"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Selfdoc: self-supervised document representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652\u20135660 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"13_CR16","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 Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"13_CR17","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-031-41685-9_16","volume-title":"International Conference on Document Analysis and Recognition","author":"D Parres","year":"2023","unstructured":"Parres, D., Paredes, R.: Fine-tuning vision encoder-decoder transformers for handwriting text recognition on historical documents. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14190, pp. 253\u2013268. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41685-9_16"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Peng, Q., et al.: Ernie-layout: layout knowledge enhanced pre-training for visually-rich document understanding. arXiv preprint arXiv:2210.06155 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"13_CR19","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":"13_CR20","unstructured":"Rae, J.W., et al.: Scaling language models: methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)"},{"issue":"1","key":"13_CR21","first-page":"5485","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(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"13_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834","volume":"144","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multipage DocVQA. Pattern Recogn. 144, 109834 (2023)","journal-title":"Pattern Recogn."},{"key":"13_CR23","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17283\u201317297 (2020)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70552-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:17Z","timestamp":1749996437000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}