{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T12:14:58Z","timestamp":1769256898936,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557639","type":"print"},{"value":"9789819557646","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5764-6_20","type":"book-chapter","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T06:08:34Z","timestamp":1769148514000},"page":"288-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Trustworthy Document Information Extraction with\u00a0Self-evaluation Mechanism"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3789-9705","authenticated-orcid":false,"given":"Haoyu","family":"Cao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9863-7689","authenticated-orcid":false,"given":"Anqi","family":"Gou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5731-6869","authenticated-orcid":false,"given":"Rui","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1895-7799","authenticated-orcid":false,"given":"Haobin","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,24]]},"reference":[{"key":"20_CR1","unstructured":"Hwang, W., et al.: Post-OCR parsing: building simple and robust parser via bio tagging. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision. LNCS, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"20_CR3","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":"20_CR4","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":"20_CR5","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: 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":"20_CR6","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":"20_CR7","unstructured":"Cui, L., Xu, Y., Lv, T., Wei, F.: Document AI: benchmarks, models and applications. arXiv preprint arXiv:2111.08609 (2021)"},{"key":"20_CR8","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vis. 129, 161\u2013184 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"20_CR9","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":"20_CR10","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, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Kim, D., Kim, Y., Kim, D., Lim, Y., Kim, G., Kil, T.: SCOB: universal text understanding via character-wise supervised contrastive learning with online text rendering for bridging domain gap. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19562\u201319573 (2023)","DOI":"10.1109\/ICCV51070.2023.01792"},{"key":"20_CR12","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, pp. 19517\u201319527 (2023)","DOI":"10.1109\/ICCV51070.2023.01788"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Wan, J., et al.: OmniParser: a unified framework for text spotting, key information extraction and table recognition. arXiv preprint arXiv:2403.19128 (2024)","DOI":"10.1109\/CVPR52733.2024.01481"},{"key":"20_CR14","doi-asserted-by":"publisher","unstructured":"Dhouib, M., Bettaieb, G., Shabou, A.: DocParser: end-to-end OCR-free information extraction from visually rich documents. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) International Conference on Document Analysis and Recognition, vol. 14191, pp. 155\u2013172. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_10","DOI":"10.1007\/978-3-031-41734-4_10"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Shilman, M., Liang, P., Viola, P.: Learning nongenerative grammatical models for document analysis. In: Tenth IEEE International Conference on Computer Vision, ICCV\u201905, Volume 1, vol.\u00a02, pp. 962\u2013969. IEEE (2005)","DOI":"10.1109\/ICCV.2005.140"},{"key":"20_CR16","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.) European Conference on Computer Vision, ECCV 2022. LNCS, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"20_CR17","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"},{"key":"20_CR18","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, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR19","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"20_CR20","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 2019, 20\u201325 September 2019, Sydney, Australia, pp. 254\u2013259. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00049"},{"key":"20_CR21","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction. CoRR abs\/2103.10213 (2021)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Hwang, W., Yim, J., Park, S., Yang, S., Seo, M.: Spatial dependency parsing for semi-structured document information extraction. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics, ACL\/IJCNLP 2021, Online Event, 1\u20136 August 2021, vol. ACL\/IJCNLP 2021, pp. 330\u2013343. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.findings-acl.28"},{"key":"20_CR23","unstructured":"Hwang, A., Frey, W.R., McKeown, K.R.: Towards augmenting lexical resources for slang and African American English. In: Zampieri, M., Nakov, P., Ljubesic, N., Tiedemann, J., Scherrer, Y. (eds.) Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial@COLING 2020, Barcelona, Spain (Online), 13 December 2020, pp. 160\u2013172. International Committee on Computational Linguistics (ICCL) (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5764-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T06:08:39Z","timestamp":1769148519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5764-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557639","9789819557646"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5764-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"24 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}