{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:21Z","timestamp":1783439841813,"version":"3.54.6"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031417306","type":"print"},{"value":"9783031417313","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41731-3_3","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T06:02:26Z","timestamp":1692338546000},"page":"36-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Visual Information Extraction in\u00a0the\u00a0Wild: Practical Dataset and\u00a0End-to-End Solution"],"prefix":"10.1007","author":[{"given":"Jianfeng","family":"Kuang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingkun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deqiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15302\u201315312 (2021)","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: Query-driven generative network for document information extraction in the wild. In: ACM MM, pp. 4261\u20134271 (2022)","DOI":"10.1145\/3503161.3547877"},{"key":"3_CR3","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":"3_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR6","first-page":"3635","volume":"34","author":"J Huang","year":"2021","unstructured":"Huang, J., Guan, D., Xiao, A., Lu, S.: Model adaptation: historical contrastive learning for unsupervised domain adaptation without source data. Adv. Neural. Inf. Process. Syst. 34, 3635\u20133649 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR 2019 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":"3_CR8","unstructured":"Hwang, W., et al.: Post-OCR parsing: building simple and robust parser via bio tagging (2019)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, X., Long, R., Xue, N., Yang, Z., Yao, C., Xia, G.S.: Revisiting document image dewarping by grid regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4543\u20134552 (2022)","DOI":"10.1109\/CVPR52688.2022.00450"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Kahraman, H.T., Sagiroglu, S., Colak, I.: Development of adaptive and intelligent web-based educational systems. In: 2010 4th International Conference on Application of Information and Communication Technologies, pp. 1\u20135. IEEE (2010)","DOI":"10.1109\/ICAICT.2010.5612054"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1476"},{"key":"3_CR12","unstructured":"Khosla, P., et al.: Supervised contrastive learning, vol. 33, pp. 18661\u201318673 (2020)"},{"key":"3_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"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":"3_CR14","doi-asserted-by":"crossref","unstructured":"Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. In: Proceedings of NAACL-HLT, pp. 260\u2013270 (2016)","DOI":"10.18653\/v1\/N16-1030"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Unimo: towards unified-modal understanding and generation via cross-modal contrastive learning. 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. 2592\u20132607 (2021)","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"3_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108946","volume":"132","author":"XH Li","year":"2022","unstructured":"Li, X.H., Yin, F., Dai, H.S., Liu, C.L.: Table structure recognition and form parsing by end-to-end object detection and relation parsing. Pattern Recogn. 132, 108946 (2022)","journal-title":"Pattern Recogn."},{"key":"3_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/978-3-030-58621-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Liao","year":"2020","unstructured":"Liao, M., Pang, G., Huang, J., Hassner, T., Bai, X.: Mask TextSpotter v3: segmentation proposal network for robust scene text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 706\u2013722. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_41"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pp. 32\u201339 (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"3_CR21","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-OCR parsing (2019)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: Styleclip: text-driven manipulation of stylegan imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2085\u20132094 (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Qian, Y., Santus, E., Jin, Z., Guo, J., Barzilay, R.: Graphie: a graph-based framework for information extraction. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 751\u2013761 (2019)","DOI":"10.18653\/v1\/N19-1082"},{"key":"3_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: Denseclip: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"3_CR26","unstructured":"Sun, H., Kuang, Z., Yue, X., Lin, C., Zhang, W.: Spatial dual-modality graph reasoning for key information extraction. arXiv preprint arXiv:2103.14470 (2021)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Tang, G., et al.: Matchvie: exploiting match relevancy between entities for visual information extraction (2021)","DOI":"10.24963\/ijcai.2021\/144"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Wang, H., Bai, X., Yang, M., Zhu, S., Wang, J., Liu, W.: Scene text retrieval via joint text detection and similarity learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4558\u20134567 (2021)","DOI":"10.1109\/CVPR46437.2021.00453"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Knowledge mining with scene text for fine-grained recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4624\u20134633 (2022)","DOI":"10.1109\/CVPR52688.2022.00458"},{"key":"3_CR30","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. 35, pp. 2738\u20132745 (2021)","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: mmlayout: multi-grained multimodal transformer for document understanding. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4877\u20134886 (2022)","DOI":"10.1145\/3503161.3548406"},{"issue":"6","key":"3_CR32","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1147\/rd.266.0647","volume":"26","author":"KY Wong","year":"1982","unstructured":"Wong, K.Y., Casey, R.G., Wahl, F.M.: Document analysis system. IBM J. Res. Dev. 26(6), 647\u2013656 (1982)","journal-title":"IBM J. Res. Dev."},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Layoutlmv2: multi-modal pre-training for visually-rich document 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. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"3_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: ACMSIGKDD, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Reading and writing: Discriminative and generative modeling for self-supervised text recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4214\u20134223 (2022)","DOI":"10.1145\/3503161.3547784"},{"key":"3_CR36","unstructured":"You, Y., Chen, T., Sui, Y., Chen, T., Wang, Z., Shen, Y.: Graph contrastive learning with augmentations, vol. 33, pp. 5812\u20135823 (2020)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Yu, W., Liu, Y., Hua, W., Jiang, D., Ren, B., Bai, X.: Turning a clip model into a scene text detector. arXiv preprint arXiv:2302.14338 (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: Pick: processing key information extraction from documents using improved graph learning-convolutional networks. In: ICPR, pp. 4363\u20134370. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"3_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109337","volume":"138","author":"G Zeng","year":"2023","unstructured":"Zeng, G., et al.: Beyond OCR+ VQA: towards end-to-end reading and reasoning for robust and accurate TextVQA. Pattern Recognit. 138, 109337 (2023)","journal-title":"Pattern Recognit."},{"key":"3_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"},{"issue":"9","key":"3_CR41","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV 130(9), 2337\u20132348 (2022)","journal-title":"IJCV"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, F., Lei, W., Feng, F., Wang, C., Zhang, H., Chua, T.S.: Towards complex document understanding by discrete reasoning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4857\u20134866 (2022)","DOI":"10.1145\/3503161.3548422"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41731-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:31:36Z","timestamp":1729935096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41731-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417306","9783031417313"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41731-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}