{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:40:04Z","timestamp":1749998404055,"version":"3.41.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"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_9","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"146-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Federated Document Visual Question Answering: A Pilot Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3353-0473","authenticated-orcid":false,"given":"Khanh","family":"Nguyen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-4454","authenticated-orcid":false,"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"9_CR1","unstructured":"Borchmann, \u0141., et al.: DUE: end-to-end document understanding benchmark. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021). https:\/\/openreview.net\/forum?id=rNs2FvJGDK"},{"issue":"15","key":"9_CR2","doi-asserted-by":"publisher","first-page":"6986","DOI":"10.3390\/s23156986","volume":"23","author":"L Che","year":"2023","unstructured":"Che, L., Wang, J., Zhou, Y., Ma, F.: Multimodal federated learning: a survey. Sensors 23(15), 6986 (2023)","journal-title":"Sensors"},{"key":"9_CR3","unstructured":"Chen, W., et al.: Tabfact: a large-scale dataset for table-based fact verification. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=rkeJRhNYDH"},{"issue":"10","key":"9_CR4","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1038\/s41591-021-01506-3","volume":"27","author":"I Dayan","year":"2021","unstructured":"Dayan, I., et al.: Federated learning for predicting clinical outcomes in patients with covid-19. Nat. Med. 27(10), 1735\u20131743 (2021)","journal-title":"Nat. Med."},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"9_CR7","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., Grave, E.: Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740 (2021)"},{"key":"9_CR8","unstructured":"Ghazi, B., Pagh, R., Velingker, A.: Scalable and differentially private distributed aggregation in the shuffled model. arXiv preprint arXiv:1906.08320 (2019)"},{"key":"9_CR9","unstructured":"Girgis, A., Data, D., Diggavi, S., Kairouz, P., Theertha\u00a0Suresh, A.: Shuffled model of differential privacy in federated learning. In: Banerjee, A., Fukumizu, K. (eds.) Proceedings of the 24th International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol.\u00a0130, pp. 2521\u20132529. PMLR (2021). https:\/\/proceedings.mlr.press\/v130\/girgis21a.html"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964 (2020)","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"9_CR11","unstructured":"Hamer, J., Mohri, M., Suresh, A.T.: Fedboost: a communication-efficient algorithm for federated learning. In: International Conference on Machine Learning, pp. 3973\u20133983. PMLR (2020)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"9_CR13","unstructured":"Hsu, T.M.H., Qi, H., Brown, M.: Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335 (2019)"},{"key":"9_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, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"issue":"21","key":"9_CR15","doi-asserted-by":"publisher","first-page":"6230","DOI":"10.3390\/s20216230","volume":"20","author":"JC Jiang","year":"2020","unstructured":"Jiang, J.C., Kantarci, B., Oktug, S., Soyata, T.: Federated learning in smart city sensing: challenges and opportunities. Sensors 20(21), 6230 (2020)","journal-title":"Sensors"},{"key":"9_CR16","unstructured":"Kairouz, P., et al.: Advances and open problems in federated learning. Found. Trends\u00ae Mach. Learn. 14(1\u20132), 1\u2013210 (2021)"},{"key":"9_CR17","unstructured":"Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., Suresh, A.T.: Scaffold: stochastic controlled averaging for federated learning. In: International Conference on Machine Learning, pp. 5132\u20135143. PMLR (2020)"},{"key":"9_CR18","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"Computer Vision - ECCV 2022","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":"9_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Krishna, K., Garg, S., Bigham, J.P., Lipton, Z.C.: Downstream datasets make surprisingly good pretraining corpora. arXiv preprint arXiv:2209.14389 (2022)","DOI":"10.18653\/v1\/2023.acl-long.682"},{"key":"9_CR21","unstructured":"Lee, K., et al.: Pix2struct: screenshot parsing as pretraining for visual language understanding. In: Proceedings of the 40th International Conference on Machine Learning, ICML 2023. JMLR.org (2023)"},{"key":"9_CR22","doi-asserted-by":"publisher","unstructured":"Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a test collection for complex document information processing. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2006, pp. 665\u2013666. Association for Computing Machinery, New York (2006). https:\/\/doi.org\/10.1145\/1148170.1148307","DOI":"10.1145\/1148170.1148307"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Li, Q., He, B., Song, D.: Model-contrastive federated learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10713\u201310722 (2021)","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"9_CR24","first-page":"429","volume":"2","author":"T Li","year":"2020","unstructured":"Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. Proc. Mach. Learn. Syst. 2, 429\u2013450 (2020)","journal-title":"Proc. Mach. Learn. Syst."},{"issue":"5","key":"9_CR25","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MIS.2020.3017205","volume":"36","author":"G Lin","year":"2020","unstructured":"Lin, G., Liang, F., Pan, W., Ming, Z.: Fedrec: federated recommendation with explicit feedback. IEEE Intell. Syst. 36(5), 21\u201330 (2020)","journal-title":"IEEE Intell. Syst."},{"key":"9_CR26","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":"9_CR27","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":"9_CR28","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., y\u00a0Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273\u20131282. PMLR (2017)"},{"key":"9_CR29","unstructured":"Nguyen, J., Malik, K., Sanjabi, M., Rabbat, M.: Where to begin? Exploring the impact of pre-training and initialization in federated learning. arXiv preprint arXiv:2206.15387 (2022)"},{"key":"9_CR30","doi-asserted-by":"publisher","unstructured":"Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. In: Zong, C., Strube, M. (eds.) Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Beijing, China, pp. 1470\u20131480. Association for Computational Linguistics (2015). https:\/\/doi.org\/10.3115\/v1\/P15-1142. https:\/\/aclanthology.org\/P15-1142","DOI":"10.3115\/v1\/P15-1142"},{"key":"9_CR31","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"},{"issue":"1","key":"9_CR32","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":"9_CR33","unstructured":"Reddi, S., et al.: Adaptive federated optimization. arXiv preprint arXiv:2003.00295 (2020)"},{"issue":"9","key":"9_CR34","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.1109\/TNNLS.2019.2944481","volume":"31","author":"F Sattler","year":"2019","unstructured":"Sattler, F., Wiedemann, S., M\u00fcller, K.R., Samek, W.: Robust and communication-efficient federated learning from non-IID data. IEEE Trans. Neural Netw. Learn. Syst. 31(9), 3400\u20133413 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"9_CR35","unstructured":"Tang, H., Yu, C., Lian, X., Zhang, T., Liu, J.: Doublesqueeze: parallel stochastic gradient descent with double-pass error-compensated compression. In: International Conference on Machine Learning, pp. 6155\u20136165. PMLR (2019)"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19254\u201319264 (2023)","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"9_CR37","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":"9_CR38","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":"9_CR39","unstructured":"Tito, R., et al.: Privacy-aware document visual question answering. arXiv preprint arXiv:2312.10108 (2023)"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Van\u00a0Landeghem, J., et al.: Document understanding dataset and evaluation (dude). In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19528\u201319540 (2023)","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"9_CR41","unstructured":"Vogels, T., Karimireddy, S.P., Jaggi, M.: Powersgd: practical low-rank gradient compression for distributed optimization. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"9_CR42","doi-asserted-by":"publisher","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Liu, Q., Schlangen, D. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6. https:\/\/aclanthology.org\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"9_CR43","unstructured":"Wu, Y., Li, F., Liang, P.S.: Insights into pre-training via simpler synthetic tasks. In: Advances in Neural Information Processing Systems, vol. 35, pp. 21844\u201321857 (2022)"},{"issue":"2","key":"9_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3298981","volume":"10","author":"Q Yang","year":"2019","unstructured":"Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning: concept and applications. ACM Trans. Intell. Syst. Technol. (TIST) 10(2), 1\u201319 (2019)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"}],"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_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:26Z","timestamp":1749996446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}