{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:58:48Z","timestamp":1743044328336,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705328"},{"type":"electronic","value":"9783031705335"}],"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_20","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"331-345","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End to\u00a0End Table Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6017-258X","authenticated-orcid":false,"given":"Yun Young","family":"Choi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4676-8784","authenticated-orcid":false,"given":"Taehoon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2348-4900","authenticated-orcid":false,"given":"Namwook","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7701-2335","authenticated-orcid":false,"given":"Taehee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1419-9930","authenticated-orcid":false,"given":"Seongho","family":"Joe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: Transfusion: robust lidar-camera fusion for 3d object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"20_CR2","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":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chen, X., Zeng, G., Wang, J.: Group DETR: fast training convergence with decoupled one-to-many label assignment. arXiv preprint arXiv:2207.13085 (2022)","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"20_CR4","unstructured":"Chi, Z., Huang, H., Xu, H.D., Yu, H., Yin, W., Mao, X.L.: Complicated table structure recognition. arXiv preprint arXiv:1908.04729 (2019)"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: A methodology for evaluating algorithms for table understanding in pdf documents. In: Proceedings of the 2012 ACM Symposium on Document Engineering, pp. 45\u201348 (2012)","DOI":"10.1145\/2361354.2361365"},{"issue":"16","key":"20_CR6","doi-asserted-by":"publisher","first-page":"7610","DOI":"10.3390\/app11167610","volume":"11","author":"KA Hashmi","year":"2021","unstructured":"Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Cascade network with deformable composite backbone for formula detection in scanned document images. Appl. Sci. 11(16), 7610 (2021)","journal-title":"Appl. Sci."},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"113521","DOI":"10.1109\/ACCESS.2021.3103413","volume":"9","author":"KA Hashmi","year":"2021","unstructured":"Hashmi, K.A., Stricker, D., Liwicki, M., Afzal, M.N., Afzal, M.Z.: Guided table structure recognition through anchor optimization. IEEE Access 9, 113521\u2013113534 (2021)","journal-title":"IEEE Access"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Hosang, J., Benenson, R., Schiele, B.: Learning non-maximum suppression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4507\u20134515 (2017)","DOI":"10.1109\/CVPR.2017.685"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Improving table structure recognition with visual-alignment sequential coordinate modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11134\u201311143 (2023)","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Jia, D., et al.: DETRS with hybrid matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"20_CR12","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: Tablebank: table benchmark for image-based table detection and recognition. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1918\u20131925 (2020)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Docbank: A benchmark dataset for document layout analysis. arXiv preprint arXiv:2006.01038 (2020)","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"20_CR14","unstructured":"Liu, S., et al.: Dab-DETR: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., Bissacco, A., Fujii, Y., Raptis, M.: Towards end-to-end unified scene text detection and layout analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131059 (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"issue":"18","key":"20_CR16","doi-asserted-by":"publisher","first-page":"8969","DOI":"10.3390\/app12188969","volume":"12","author":"M Minouei","year":"2022","unstructured":"Minouei, M., Hashmi, K.A., Soheili, M.R., Afzal, M.Z., Stricker, D.: Continual learning for table detection in document images. Appl. Sci. 12(18), 8969 (2022)","journal-title":"Appl. Sci."},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Paliwal, S.S., Vishwanath, D., Rahul, R., Sharma, M., Vig, L.: Tablenet: deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 128\u2013133. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., Visave, M., Sultanpure, K.: Cascadetabnet: an approach for end to end table detection and structure recognition from image-based documents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 572\u2013573 (2020)","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Qasim, S.R., Mahmood, H., Shafait, F.: Rethinking table recognition using graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 142\u2013147. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"20_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: Deepdesrt: deep learning for detection and structure recognition of tables in document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a01, pp. 1162\u20131167. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"20_CR22","doi-asserted-by":"publisher","unstructured":"Shehzadi, T., Azeem\u00a0Hashmi, K., Stricker, D., Liwicki, M., Zeshan\u00a0Afzal, M.: Towards end-to-end semi-supervised table detection with deformable transformer. In: International Conference on Document Analysis and Recognition, pp. 51\u201376. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_4","DOI":"10.1007\/978-3-031-41679-8_4"},{"issue":"20","key":"20_CR23","doi-asserted-by":"publisher","first-page":"10578","DOI":"10.3390\/app122010578","volume":"12","author":"S Sinha","year":"2022","unstructured":"Sinha, S., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Rethinking learnable proposals for graphical object detection in scanned document images. Appl. Sci. 12(20), 10578 (2022)","journal-title":"Appl. Sci."},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: Pubtables-1m: towards comprehensive table extraction from unstructured documents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4634\u20134642 (2022)","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"20_CR25","doi-asserted-by":"publisher","unstructured":"Smock, B., Pesala, R., Abraham, R.: Grits: grid table similarity metric for table structure recognition. In: International Conference on Document Analysis and Recognition, pp. 535\u2013549. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_33","DOI":"10.1007\/978-3-031-41734-4_33"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Wang, J., Hu, K., Zhong, Z., Sun, L., Huo, Q.: Detect-order-construct: A tree construction based approach for hierarchical document structure analysis. arXiv preprint arXiv:2401.11874 (2024)","DOI":"10.1016\/j.patcog.2024.110836"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Zheng, X., Burdick, D., Popa, L., Zhong, X., Wang, N.X.R.: Global table extractor (GTE): a framework for joint table identification and cell structure recognition using visual context. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 697\u2013706 (2021)","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"20_CR28","doi-asserted-by":"crossref","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 (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"20_CR29","doi-asserted-by":"publisher","unstructured":"Zhong, Z., et al.: A hybrid approach to document layout analysis for heterogeneous document images. In: International Conference on Document Analysis and Recognition, pp. 189\u2013206. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_12","DOI":"10.1007\/978-3-031-41734-4_12"},{"key":"20_CR30","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"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_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:07:49Z","timestamp":1725685669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_20","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":"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"}}]}}