{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T06:29:43Z","timestamp":1769581783241,"version":"3.49.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","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\/978-3-031-70533-5_13","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"208-226","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["GDP: Generic Document Pretraining to\u00a0Improve Document Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6344-8581","authenticated-orcid":false,"given":"Akkshita","family":"Trivedi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6474-4500","authenticated-orcid":false,"given":"Akarsh","family":"Upadhyay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6628-7065","authenticated-orcid":false,"given":"Rudrabha","family":"Mukhopadhyay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5488-7773","authenticated-orcid":false,"given":"Santanu","family":"Chaudhury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"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","doi-asserted-by":"crossref","unstructured":"Arshad, O., Gallo, I., Nawaz, S., Calefati, A.: Aiding intra-text representations with visual context for multimodal named entity recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 337\u2013342 (2019)","DOI":"10.1109\/ICDAR.2019.00061"},{"key":"13_CR3","unstructured":"Bao, H., et\u00a0al.: Unilmv2: pseudo-masked language models for unified language model pre-training. In: International Conference on Machine Learning, pp. 642\u2013652. PMLR (2020)"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Biten, A.F., Tito, R., Gomez, L., Valveny, E., Karatzas, D.: Ocr-idl: Ocr annotations for industry document library dataset. arXiv preprint arXiv:2202.12985 (2022)","DOI":"10.1007\/978-3-031-25069-9_16"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Cho, J., Lu, J., Schwenk, D., Hajishirzi, H., Kembhavi, A.: X-lxmert: aint, caption and answer questions with multi-modal transformers. arXiv preprint arXiv:2009.11278 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"13_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Emanuela\u00a0Boros, E., Toumi, A., Rouchet, E., Abadie, B., Stutzmann, D., Kermorvant, C.: Automatic page classification in a large collection of manuscripts based on the international image interoperability framework. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 756\u2013762 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00126","DOI":"10.1109\/ICDAR.2019.00126"},{"key":"13_CR8","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":"\u0141 Garncarek","year":"2021","unstructured":"Garncarek, \u0141, Powalski, R., Stanis\u0142awek, T., Topolski, B., Halama, P., Turski, M., Grali\u0144ski, F.: 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"},{"key":"13_CR9","unstructured":"Gu, J., et al.: .: Unidoc: unified pretraining framework for document understanding. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol.\u00a034, pp. 39\u201350. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/0084ae4bc24c0795d1e6a4f58444d39b-Paper.pdf"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Xylayoutlm: towards layout-aware multimodal networks for visually-rich document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Guillaume\u00a0Jaume, Hazim Kemal\u00a0Ekenel, J.P.T.: Funsd: a dataset for form understanding in noisy scanned documents. In: Accepted to ICDAR-OST (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Guo, H., Qin, X., Liu, J., Han, J., Liu, J., Ding, E.: Eaten: entity-aware attention for single shot visual text extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 254\u2013259 (2019)","DOI":"10.1109\/ICDAR.2019.00049"},{"key":"13_CR13","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: Bros: a pre-trained language model for understanding texts in document (2021). In: https:\/\/openreview.net\/forum, p.\u00a048"},{"key":"13_CR14","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 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"13_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-86549-8_22","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"S Jahagirdar","year":"2021","unstructured":"Jahagirdar, S., Gangisetty, S., Mishra, A.: Look, read and ask: learning to ask questions by reading text in images. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 335\u2013349. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_22"},{"key":"13_CR16","doi-asserted-by":"publisher","unstructured":"Jain, R., Wigington, C.: Multimodal document image classification. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 71\u201377 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00021","DOI":"10.1109\/ICDAR.2019.00021"},{"key":"13_CR17","doi-asserted-by":"publisher","unstructured":"Kosaraju, S.C., et al.: Dot-net: document layout classification using texture-based cnn. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1029\u20131034 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00168","DOI":"10.1109\/ICDAR.2019.00168"},{"key":"13_CR18","unstructured":"Kumar, J., Ye, P., Doermann, D.: Learning document structure for retrieval and classification. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 1558\u20131561 (2012)"},{"key":"13_CR19","doi-asserted-by":"publisher","unstructured":"Li, C., Bi, B., Yan, M., Wang, W., Huang, S., Huang, F., Si, L.: StructuralLM: Structural pre-training for form understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6309\u20136318. Association for Computational Linguistics, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.493, https:\/\/aclanthology.org\/2021.acl-long.493","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Li, P., Gu, J., Kuen, J., Morariu, V.I., Zhao, H., Jain, R., Manjunatha, V., Liu, H.: 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_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Structext: structured text understanding with multi-modal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1912\u20131920 (2021)","DOI":"10.1145\/3474085.3475345"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: North American Chapter of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"13_CR23","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: Docvqa: a dataset for vqa on document images. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2199\u20132208 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00225","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"13_CR25","unstructured":"Miranda, B., Wang, Y.X., Koyejo, O.: The curse of zero task diversity: on the failure of transfer learning to outperform maml and their empirical equivalence. ArXiv abs\/2208.01545 (2021)"},{"key":"13_CR26","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-ocr parsing (2019)"},{"key":"13_CR27","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. ArXiv abs\/1910.10683 (2019)"},{"key":"13_CR28","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract ocr engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol.\u00a02, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Studer, L., et al.: A comprehensive study of imagenet pre-training for historical document image analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 720\u2013725 (2019)","DOI":"10.1109\/ICDAR.2019.00120"},{"key":"13_CR31","unstructured":"Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=SygXPaEYvH"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: Lilt: a simple yet effective language-independent layout transformer for structured document understanding. In: Annual Meeting of the Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Williams, J., Tadesse, A., Sam, T., Sun, H.M., Monta\u00f1ez, G.D.: Limits of transfer learning. In: International Conference on Machine Learning, Optimization, and Data Science (2020)","DOI":"10.1007\/978-3-030-64580-9_32"},{"key":"13_CR34","unstructured":"Wu, T.L., Li, C., Zhang, M., Chen, T., Hombaiah, S.A., Bendersky, M.: Lampret: layout-aware multimodal pretraining for document understanding. ArXiv abs\/2104.08405 (2021)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. In: ACL-IJCNLP 2021, January 2021","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"13_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: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"13_CR37","unstructured":"Xu, Y., et al.: Layoutxlm: multimodal pre-training for multilingual visually-rich document understanding. CoRR abs\/2104.08836 (2021). https:\/\/arxiv.org\/abs\/2104.08836"},{"key":"13_CR38","unstructured":"Yu, Y., et al.: An empirical study of pre-trained models on out-of-distribution generalization (2022). https:\/\/openreview.net\/forum?id=2RYOwBOFesi"},{"key":"13_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-030-86549-8_8","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"P Zhang","year":"2021","unstructured":"Zhang, P., Li, C., Qiao, L., Cheng, Z., Pu, S., Niu, Y., Wu, F.: VSR: a unified framework for document layout analysis combining vision, semantics and relations. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 115\u2013130. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_8"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Trie: end-to-end text reading and information extraction for document understanding. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1413\u20131422 (2020)","DOI":"10.1145\/3394171.3413900"}],"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\/978-3-031-70533-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:05:38Z","timestamp":1725685538000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_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":"8 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"}}]}}