{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T17:31:59Z","timestamp":1790443919972,"version":"4.1.0"},"publisher-location":"Cham","reference-count":40,"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_25","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"438-452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DTSM: Toward Dense Table Structure Recognition with\u00a0Text Query Encoder and\u00a0Adjacent Feature Aggregator"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3020-5580","authenticated-orcid":false,"given":"Xinhong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6624-6375","authenticated-orcid":false,"given":"Bangdong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0622-4285","authenticated-orcid":false,"given":"Chenfan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3263-3449","authenticated-orcid":false,"given":"Dezhi","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2516-926X","authenticated-orcid":false,"given":"Chongyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-0957","authenticated-orcid":false,"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","unstructured":"Chen, B., Peng, D., Zhang, J., Ren, Y., Jin, L.: Complex table structure recognition in the wild using transformer and identity matrix-based augmentation. In: International Conference on Frontiers in Handwriting Recognition, pp. 545\u2013561. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-21648-0_37","DOI":"10.1007\/978-3-031-21648-0_37"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Huang, C., Zheng, X., Lin, J., Huang, X.J.: TableVLM: multi-modal pre-training for table structure recognition. In: Annual Meeting of the Association for Computational Linguistics, pp. 2437\u20132449 (2023)","DOI":"10.18653\/v1\/2023.acl-long.137"},{"key":"25_CR3","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":"25_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-859-1","volume-title":"Handbook of Document Image Processing and Recognition","year":"2014","unstructured":"Doermann, D., Tombre, K. (eds.): Handbook of Document Image Processing and Recognition. Springer, London (2014). https:\/\/doi.org\/10.1007\/978-0-85729-859-1"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Fischer, P., Smajic, A., Abrami, G., Mehler, A.: Multi-type-td-TSR\u2013extracting tables from document images using a multi-stage pipeline for table detection and table structure recognition: from OCR to structured table representations. In: Advances in Artificial Intelligence, pp. 95\u2013108 (2021)","DOI":"10.1007\/978-3-030-87626-5_8"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Gao, L., et al.: ICDAR 2019 competition on table detection and recognition (cTDaR). In: International Conference on Document Analysis and Recognition, pp. 1510\u20131515 (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: International Conference on Document Analysis and Recognition, pp. 1449\u20131453 (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Improving table structure recognition with visual-alignment sequential coordinate modeling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11134\u201311143 (2023)","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"25_CR11","unstructured":"Itonori, K.: Table structure recognition based on textblock arrangement and ruled line position. In: International Conference on Document Analysis and Recognition, pp. 765\u2013768 (1993)"},{"key":"25_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: Twelfth Language Resources and Evaluation Conference, pp. 1918\u20131925 (2020)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, Z., Yan, J., Zhou, Y., Ye, F., Liu, X.: GFTE: graph-based financial table extraction. In: International Conference on Pattern Recognition, pp. 644\u2013658 (2021)","DOI":"10.1007\/978-3-030-68790-8_50"},{"key":"25_CR14","doi-asserted-by":"publisher","unstructured":"Li, Z., Peng, F., Xue, Y., Hao, N., Jin, L.: Scene table structure recognition with segmentation and key point collaboration. In: International Conference on Document Analysis and Recognition, pp. 295\u2013310. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_17","DOI":"10.1007\/978-3-031-41679-8_17"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"25_CR16","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Lin, W., Sun, Z., Ma, C., Li, M., Wang, J., Sun, L., Huo, Q.: TSRFormer: table structure recognition with transformers. In: ACM International Conference on Multimedia, pp. 6473\u20136482 (2022)","DOI":"10.1145\/3503161.3548038"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, X., Liu, B., Jiang, D., Liu, Y., Ren, B.: Neural collaborative graph machines for table structure recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4533\u20134542 (2022)","DOI":"10.1109\/CVPR52688.2022.00449"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Show, read and reason: table structure recognition with flexible context aggregator. In: ACM International Conference on Multimedia, pp. 1084\u20131092 (2021)","DOI":"10.1145\/3474085.3481534"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Long, R., et al.: Parsing table structures in the wild. In: IEEE International Conference on Computer Vision, pp. 944\u2013952 (2021)","DOI":"10.1109\/ICCV48922.2021.00098"},{"key":"25_CR21","doi-asserted-by":"publisher","unstructured":"Ly, N.T., Takasu, A.: An end-to-end local attention based model for table recognition. In: International Conference on Document Analysis and Recognition, pp. 20\u201336. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_2","DOI":"10.1007\/978-3-031-41679-8_2"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Lyu, P., et al.: GridFormer: towards accurate table structure recognition via grid prediction. In: ACM International Conference on Multimedia, pp. 7747\u20137757 (2023)","DOI":"10.1145\/3581783.3611961"},{"key":"25_CR23","doi-asserted-by":"publisher","first-page":"109006","DOI":"10.1016\/j.patcog.2022.109006","volume":"133","author":"C Ma","year":"2023","unstructured":"Ma, C., Lin, W., Sun, L., Huo, Q.: Robust table detection and structure recognition from heterogeneous document images. Pattern Recogn. 133, 109006 (2023)","journal-title":"Pattern Recogn."},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.: TableFormer: table structure understanding with transformers. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4614\u20134623 (2022)","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"25_CR25","doi-asserted-by":"publisher","unstructured":"Nguyen, N.Q., Le, A.D., Lu, A.K., Mai, X.T., Tran, T.A.: Formerge: recover spanning cells in complex table structure using transformer network. In: International Conference on Document Analysis and Recognition, pp. 522\u2013534. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_32","DOI":"10.1007\/978-3-031-41734-4_32"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Qiao, L., et al.: LGPMA: complicated table structure recognition with local and global pyramid mask alignment. In: International Conference on Document Analysis and Recognition, pp. 99\u2013114 (2021)","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Shen, H., et al.: Divide rows and conquer cells: towards structure recognition for large tables. In: International Joint Conference on Artificial Intelligence, pp. 1369\u20131377 (2023)","DOI":"10.24963\/ijcai.2023\/152"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Siddiqui, S.A., Fateh, I.A., Rizvi, S.T.R., Dengel, A., Ahmed, S.: Deeptabstr: deep learning based table structure recognition. In: International Conference on Document Analysis and Recognition, pp. 1403\u20131409 (2019)","DOI":"10.1109\/ICDAR.2019.00226"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Smock, B., Pesala, R., Abraham, R.: Pubtables-1m: towards comprehensive table extraction from unstructured documents. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4634\u20134642 (2022)","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Tengli, A., Yang, Y., Ma, N.L.: Learning table extraction from examples. In: International Conference on Computational Linguistics, pp. 987\u2013993 (2004)","DOI":"10.3115\/1220355.1220497"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., Morariu, V.I., Price, B., Cohen, S., Martinez, T.: Deep splitting and merging for table structure decomposition. In: International Conference on Document Analysis and Recognition, pp. 114\u2013121 (2019)","DOI":"10.1109\/ICDAR.2019.00027"},{"key":"25_CR32","doi-asserted-by":"publisher","unstructured":"Umer, M., Mohsin, M.A., Ul-Hasan, A., Shafait, F.: PyramidTabNet: transformer-based table recognition in image-based documents. In: International Conference on Document Analysis and Recognition, pp. 420\u2013437. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_26","DOI":"10.1007\/978-3-031-41734-4_26"},{"key":"25_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: International Conference on Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"issue":"7","key":"25_CR34","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1016\/j.patcog.2004.01.012","volume":"37","author":"Y Wang","year":"2004","unstructured":"Wang, Y., Phillips, I.T., Haralick, R.M.: Table structure understanding and its performance evaluation. Pattern Recogn. 37(7), 1479\u20131497 (2004)","journal-title":"Pattern Recogn."},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Xie, X., Fu, L., Zhang, Z., Wang, Z., Bai, X.: Toward understanding wordart: corner-guided transformer for scene text recognition. In: European Conference on Computer Vision, pp. 303\u2013321. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Xue, W., Yu, B., Wang, W., Tao, D., Li, Q.: TGRNet: a table graph reconstruction network for table structure recognition. In: IEEE International Conference on Computer Vision, pp. 1295\u20131304 (2021)","DOI":"10.1109\/ICCV48922.2021.00133"},{"issue":"1","key":"25_CR37","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1038\/s41597-023-01985-8","volume":"10","author":"F Yang","year":"2023","unstructured":"Yang, F., Hu, L., Liu, X., Huang, S., Gu, Z.: A large-scale dataset for end-to-end table recognition in the wild. Sci. Data 10(1), 110 (2023)","journal-title":"Sci. Data"},{"key":"25_CR38","unstructured":"Ye, J., .: PingAn-VCGroup\u2019s solution for ICDAR 2021 competition on scientific literature parsing task B: table recognition to HTML. arXiv preprint arXiv:2105.01848 (2021)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, J., Du, J., Wang, F.: Split, embed and merge: an accurate table structure recognizer. Pattern Recogn. 126, 108565 (2022)","DOI":"10.1016\/j.patcog.2022.108565"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno\u00a0Yepes, A.: Image-based table recognition: data, model, and evaluation. In: European Conference on Computer Vision, pp. 564\u2013580 (2020)","DOI":"10.1007\/978-3-030-58589-1_34"}],"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_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:09:39Z","timestamp":1725685779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_25","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"}}]}}