{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T02:48:06Z","timestamp":1788749286306,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":35,"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_18","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"294-310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["GeoContrastNet: Contrastive Key-Value Edge Learning for\u00a0Language-Agnostic Document Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3722-4329","authenticated-orcid":false,"given":"Nil","family":"Biescas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6041-0931","authenticated-orcid":false,"given":"Carlos","family":"Boned","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4533-4739","authenticated-orcid":false,"given":"Josep","family":"Llad\u00f3s","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6648-8270","authenticated-orcid":false,"given":"Sanket","family":"Biswas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"18_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":"18_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv preprint arXiv:1409.0473"},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Banerjee, A., Biswas, S., Llad\u00f3s, J., Pal, U.: SwinDocSegmenter: an end-to-end unified domain adaptive transformer for document instance segmentation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. LNCS, vol. 14187. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_18","DOI":"10.1007\/978-3-031-41676-7_18"},{"key":"18_CR4","unstructured":"Biswas, S., Banerjee, A., Llad\u00f3s, J., Pal, U.: DocSegTr: An instance-level end-to-end document image segmentation transformer (2022). arXiv preprint arXiv:2201.11438"},{"issue":"3","key":"18_CR5","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","volume":"24","author":"S Biswas","year":"2021","unstructured":"Biswas, S., Riba, P., Llad\u00f3s, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recogn. (IJDAR) 24(3), 269\u2013281 (2021)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Carbonell, M., Riba, P., Villegas, M., Forn\u00e9s, A., Llad\u00f3s, J.: Named entity recognition and relation extraction with graph neural networks in semi structured documents. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9622\u20139627. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412669"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 134\u2013141. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00030"},{"key":"18_CR8","doi-asserted-by":"publisher","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.) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. LNCS, vol. 13804. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"18_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-030-86549-8_27","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"B Davis","year":"2021","unstructured":"Davis, B., Morse, B., Price, B., Tensmeyer, C., Wiginton, C.: Visual FUDGE: form understanding via dynamic graph editing. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 416\u2013431. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_27"},{"key":"18_CR10","doi-asserted-by":"publisher","unstructured":"Gemelli, A., Biswas, S., Civitelli, E., Llad\u00f3s, J., Marinai, S.: Doc2Graph: a task agnostic document understanding framework based on graph neural networks. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. LNCS, vol. 13804. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_22","DOI":"10.1007\/978-3-031-25069-9_22"},{"key":"18_CR11","first-page":"39","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu, J., et al.: UniDoc: unified pretraining framework for document understanding. Adv. Neural. Inf. Process. Syst. 34, 39\u201350 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR12","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)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: BROS: a pre-trained language model focusing on text and layout for better key information extraction from documents. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"18_CR14","unstructured":"Howard, A.G., et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint arXiv:1704.04861"},{"key":"18_CR15","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":"18_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1516\u20131520. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW). vol.\u00a02, pp.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"18_CR18","unstructured":"Jocher, G., et al.: ultralytics\/yolov5: v6. 1-TensorRT, TensorFlow edge TPU and OpenVINO export and inference. Zenodo, Feb 22 (2022)"},{"key":"18_CR19","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2016). arXiv preprint arXiv:1609.02907"},{"key":"18_CR20","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":"18_CR21","doi-asserted-by":"crossref","unstructured":"Luo, C., Cheng, C., Zheng, Q., Yao, C.: GeoLayoutLM: geometric pre-training for visual information extraction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7092\u20137101 (2023)","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Maity, S.: et al.: SelfDocSeg: a self-supervised vision-based approach towards document segmentation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. LNCS, vol. 14187. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_20","DOI":"10.1007\/978-3-031-41676-7_20"},{"key":"18_CR23","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":"18_CR24","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":"18_CR25","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":"18_CR26","doi-asserted-by":"crossref","unstructured":"Riba, P., Dutta, A., Goldmann, L., Forn\u00e9s, A., Ramos, O., Llad\u00f3s, J.: Table detection in invoice documents by graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 122\u2013127. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"18_CR27","unstructured":"Tito, R., et\u00a0al.: Privacy-aware document visual question answering (2023). arXiv preprint arXiv:2312.10108"},{"key":"18_CR28","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks (2017). arXiv preprint arXiv:1710.10903"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Voutharoja, B.P., Qu, L., Shiri, F.: Language independent neuro-symbolic semantic parsing for form understanding (2023). arXiv preprint arXiv:2305.04460","DOI":"10.1007\/978-3-031-41679-8_8"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Wang, D., Ma, Z., Nourbakhsh, A., Gu, K., Shah, S.: DocGraphLM: documental graph language model for information extraction. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1944\u20131948 (2023)","DOI":"10.1145\/3539618.3591975"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: A simple yet effective language-independent layout transformer for structured document understanding (2022). arXiv preprint arXiv:2202.13669","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding (2020). arXiv preprint arXiv:2012.14740","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"18_CR33","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":"18_CR34","unstructured":"Xu, Y., et al.: LayoutXLM: Multimodal pre-training for multilingual visually-rich document understanding (2021). arXiv preprint arXiv:2104.08836"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: XFUND: a benchmark dataset for multilingual visually rich form understanding. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 3214\u20133224 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.253"}],"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_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:06:47Z","timestamp":1725685607000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_18","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"}}]}}