{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:26:14Z","timestamp":1758126374473,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705458"},{"type":"electronic","value":"9783031705465"}],"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\/978-3-031-70546-5_1","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:02:47Z","timestamp":1725944567000},"page":"3-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["CREPE: Coordinate-Aware End-to-End Document Parser"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2153-3782","authenticated-orcid":false,"given":"Yamato","family":"Okamoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7001-4641","authenticated-orcid":false,"given":"Youngmin","family":"Baek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6713-3858","authenticated-orcid":false,"given":"Geewook","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6692-6952","authenticated-orcid":false,"given":"Ryota","family":"Nakao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9033-5231","authenticated-orcid":false,"given":"DongHyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7272-2198","authenticated-orcid":false,"given":"Moon Bin","family":"Yim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8509-9163","authenticated-orcid":false,"given":"Seunghyun","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4962-8977","authenticated-orcid":false,"given":"Bado","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"1_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 (ICCV), pp. 993\u20131003 (October 2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., et al.: Cleval: character-level evaluation for text detection and recognition tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 564\u2013565 (2020)","DOI":"10.1109\/CVPRW50498.2020.00290"},{"issue":"3","key":"1_CR3","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s10032-021-00378-0","volume":"24","author":"S Bakkali","year":"2021","unstructured":"Bakkali, S., Ming, Z., Coustaty, M., Rusi\u00f1ol, M.: Eaml: ensemble self-attention-based mutual learning network for document image classification. Int. J. Doc. Anal. Recogn. (IJDAR) 24(3), 251\u2013268 (2021)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: Attention where it matters: rethinking visual document understanding with selective region concentration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19517\u201319527 (October 2023)","DOI":"10.1109\/ICCV51070.2023.01788"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"1_CR6","unstructured":"Chen, T., Saxena, S., Li, L., Fleet, D.J., Hinton, G.: Pix2seq: a language modeling framework for object detection. arXiv preprint arXiv:2109.10852 (2021)"},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Clausner, C., Antonacopoulos, A., Pletschacher, S.: Icdar2019 competition on recognition of documents with complex layouts - rdcl2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1521\u20131526 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00245","DOI":"10.1109\/ICDAR.2019.00245"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: Vision grid transformer for document layout analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19462\u201319472 (October 2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1_CR10","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. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00049"},{"key":"1_CR11","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)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"1_CR12","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":"1_CR13","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":"1_CR14","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":"1_CR15","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":"1_CR16","doi-asserted-by":"crossref","unstructured":"Kil, T., Kim, S., Seo, S., Kim, Y., Kim, D.: Towards unified scene text spotting based on sequence generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15223\u201315232 (2023)","DOI":"10.1109\/CVPR52729.2023.01461"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"1_CR18","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-031-41498-5_16","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2023 Workshops: San Jos\u00e9, CA, USA, August 24\u201326, 2023, Proceedings, Part I","author":"G Kim","year":"2023","unstructured":"Kim, G., Yokoo, S., Seo, S., Osanai, A., Okamoto, Y., Baek, Y.: On text localization in\u00a0end-to-end OCR-free document understanding transformer without text localization supervision. In: Coustaty, M., Forn\u00e9s, A. (eds.) Document Analysis and Recognition \u2013 ICDAR 2023 Workshops: San Jos\u00e9, CA, USA, August 24\u201326, 2023, Proceedings, Part I, pp. 215\u2013232. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41498-5_16"},{"key":"1_CR19","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-031-41731-3_3","volume-title":"Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part VI","author":"J Kuang","year":"2023","unstructured":"Kuang, J., et al.: Visual information extraction in\u00a0the\u00a0wild: practical dataset and\u00a0end-to-end solution. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part VI, pp. 36\u201353. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41731-3_3"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Docbank: a benchmark dataset for document layout analysis (2020)","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Liao, H., et al.: Doctr: document transformer for structured information extraction in documents. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19584\u201319594 (October 2023)","DOI":"10.1109\/ICCV51070.2023.01794"},{"key":"1_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR23","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: Spts v2: single-point scene text spotting. arXiv preprint arXiv:2301.01635 (2023)","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022 (October 2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR26","doi-asserted-by":"publisher","unstructured":"Ly, N.T., Takasu, A.: An end-to-end multi-task learning model for image-based table recognition, pp. 626\u2013634 (2023). https:\/\/doi.org\/10.5220\/0011685000003417","DOI":"10.5220\/0011685000003417"},{"key":"1_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":"1_CR28","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-ocr parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"1_CR29","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: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part II","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.) Document Analysis and Recognition \u2013 ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part II, pp. 732\u2013747. Springer International Publishing, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_47"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Iki, T., Nishida, K., Saito, K., Suzuki, J.: Instructdoc: a dataset for zero-shot generalization of visual document understanding with instructions. arXiv preprint arXiv:2401.13313 (2024)","DOI":"10.1609\/aaai.v38i17.29874"},{"key":"1_CR31","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Towards robust visual information extraction in real world: new dataset and novel solution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 2738\u20132745 (2021)","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"1_CR34","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 and Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Unitab: unifying text and box outputs for grounded vision-language modeling. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"1_CR36","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-030-86337-1_8","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part IV","author":"M Yim","year":"2021","unstructured":"Yim, M., Kim, Y., Cho, H.-C., Park, S.: SynthTIGER: synthetic text image GEneratoR towards better text recognition models. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition \u2013 ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part IV, pp. 109\u2013124. Springer International Publishing, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_8"},{"key":"1_CR37","unstructured":"Yu, Y., et al.: Structextv2: masked visual-textual prediction for document image pre-training. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=HE_75XY5Ljh"},{"key":"1_CR38","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 (2020). https:\/\/api.semanticscholar.org\/CorpusID:218900797","DOI":"10.1145\/3394171.3413900"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1_CR40","doi-asserted-by":"publisher","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (Sep 2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00166","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"1_CR41","unstructured":"Zhu, F., Wang, C., Lei, W., Liu, Z., Chua, T.S.: Rdu: a region-based approach to form-style document understanding. arXiv preprint arXiv:2206.06890 (2022)"},{"key":"1_CR42","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comp. Sci. 10, 19\u201336 (2016)","journal-title":"Front. Comp. Sci."},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. In: Proceedings of the IEEE (2023)","DOI":"10.1109\/JPROC.2023.3238524"}],"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\/978-3-031-70546-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T23:05:44Z","timestamp":1732748744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70546-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705458","9783031705465"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70546-5_1","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"}}]}}