{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:14:45Z","timestamp":1778080485964,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","award":["IT14836"],"award-info":[{"award-number":["IT14836"]}],"id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s10032-025-00527-9","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:56:34Z","timestamp":1748019394000},"page":"91-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Revisiting Table Detection Datasets for Visually Rich Documents"],"prefix":"10.1007","volume":"29","author":[{"given":"Bin","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Murat","family":"Simsek","sequence":"additional","affiliation":[]},{"given":"Burak","family":"Kantarci","sequence":"additional","affiliation":[]},{"given":"Ala Abu","family":"Alkheir","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"527_CR1","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.neucom.2022.09.094","volume":"513","author":"Y Akkaya","year":"2022","unstructured":"Akkaya, Y., Simsek, M., Kantarci, B., Khan, S.: On cropped versus uncropped training sets in tabular structure detection. Neurocomputing 513, 114\u2013126 (2022)","journal-title":"Neurocomputing"},{"key":"527_CR2","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition, in 2013 12th International Conference on Document Analysis and Recognition (IEEE), pp. 1449\u20131453 (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"527_CR3","doi-asserted-by":"crossref","unstructured":"Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: ICDAR2017 competition on page object detection, in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01 (IEEE), pp. 1417\u20131422 (2017)","DOI":"10.1109\/ICDAR.2017.231"},{"key":"527_CR4","doi-asserted-by":"crossref","unstructured":"Gao, L., Huang, Y.. D\u00e9jean, H., Meunier, J.L., Yan, Q., Fang, Y., Kleber, F., Lang, E.: ICDAR 2019 competition on table detection and recognition (cTDaR), in 2019 International Conference on Document Analysis and Recognition (ICDAR) (IEEE), pp. 1510\u20131515 (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"527_CR5","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 12th language resources and evaluation conference, pp. 1918\u20131925 (2020)"},{"key":"527_CR6","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) (IEEE), pp. 1015\u20131022 (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"527_CR7","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.neucom.2021.10.023","volume":"468","author":"J Fernandes","year":"2022","unstructured":"Fernandes, J., Simsek, M., Kantarci, B., Khan, S.: Tabledet: An end-to-end deep learning approach for table detection and table image classification in data sheet images. Neurocomputing 468, 317\u2013334 (2022)","journal-title":"Neurocomputing"},{"key":"527_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: Diffusion model for object detection. arXiv preprint arXiv:2211.09788 (2022)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"527_CR9","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":"527_CR10","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C., et\u00a0al.: Sparse r-cnn: End-to-end object detection with learnable proposals, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"527_CR11","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.neucom.2021.11.101","volume":"473","author":"A Abdallah","year":"2022","unstructured":"Abdallah, A., Berendeyev, A., Nuradin, I., Nurseitov, D.: Tncr: Table net detection and classification dataset. Neurocomputing 473, 79\u201397 (2022)","journal-title":"Neurocomputing"},{"key":"527_CR12","doi-asserted-by":"crossref","unstructured":"Mondal, A., .\u00a0Lipps, P, Jawahar, C.: IIIT-AR-13K: A new dataset for graphical object detection in documents, in Document Analysis Systems: 14th IAPR International Workshop, DAS 2020, Wuhan, China, July 26\u201329, 2020, Proceedings 14 (Springer), pp. 216\u2013230 (2020)","DOI":"10.1007\/978-3-030-57058-3_16"},{"key":"527_CR13","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection, in Proceedings of the IEEE conference on computer vision and pattern recognition , pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"527_CR14","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)"},{"key":"527_CR15","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector, in European conference on computer vision (Springer), pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"527_CR16","unstructured":"Li, Z., Zhou, F.: Fssd: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960 (2017)"},{"key":"527_CR17","doi-asserted-by":"crossref","unstructured":"Ning, C., Zhou, H., Song, Y., Tang, J.: Inception single shot multibox detector for object detection, in 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) (IEEE), pp. 549\u2013554 (2017)","DOI":"10.1109\/ICMEW.2017.8026312"},{"key":"527_CR18","doi-asserted-by":"crossref","unstructured":"Shafiee, M.J., Chywl, B., Li, F., Wong, A.: Fast yolo: A fast you only look once system for real-time embedded object detection in video. arXiv preprint arXiv:1709.05943 (2017)","DOI":"10.15353\/vsnl.v3i1.171"},{"key":"527_CR19","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"527_CR20","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"527_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn, in Proceedings of the IEEE international conference on computer vision , pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"527_CR22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"527_CR23","unstructured":"Chu, X., Tian, Z., Zhang, B., Wang, X., Wei, X., Xia, H., Shen, C.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)"},{"key":"527_CR24","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Yang, J., Zhang, P., Yuan, L., Zhang, L.: Dynamic detr: End-to-end object detection with dynamic attention, in Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2988\u20132997 (2021)","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"527_CR25","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of detr with spatially modulated co-attention, in Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3621\u20133630 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"527_CR26","doi-asserted-by":"crossref","unstructured":"Huang, Y., Yan, Q., Li, Y., Chen, Y., Wang, X., Gao, L., Tang, Z.: A YOLO-based table detection method, in 2019 International Conference on Document Analysis and Recognition (ICDAR) (IEEE), pp. 813\u2013818 (2019)","DOI":"10.1109\/ICDAR.2019.00135"},{"key":"527_CR27","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"},{"issue":"5","key":"527_CR28","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: high quality object detection and instance segmentation. IEEE transactions on pattern analysis and machine intelligence 43(5), 1483\u20131498 (2019)","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"10","key":"527_CR29","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al.: Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence 43(10), 3349\u20133364 (2020)","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"527_CR30","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers, in European conference on computer vision (Springer), pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"527_CR31","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":"527_CR32","doi-asserted-by":"publisher","first-page":"74151","DOI":"10.1109\/ACCESS.2018.2880211","volume":"6","author":"SA Siddiqui","year":"2018","unstructured":"Siddiqui, S.A., Malik, M.I., Agne, S., Dengel, A., Ahmed, S.: Decnt: Deep deformable cnn for table detection. IEEE access 6, 74151\u201374161 (2018)","journal-title":"IEEE access"},{"key":"527_CR33","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 (IEEE), pp. 1162\u20131167 (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"527_CR34","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) (IEEE), pp. 128\u2013133 (2019)","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"527_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103551","volume":"90","author":"E Kara","year":"2020","unstructured":"Kara, E., Traquair, M., Simsek, M., Kantarci, B., Khan, S.: Holistic design for deep learning-based discovery of tabular structures in datasheet images. Engineering Applications of Artificial Intelligence 90, 103551 (2020)","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"527_CR36","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.neucom.2021.01.103","volume":"440","author":"J Jiang","year":"2021","unstructured":"Jiang, J., Simsek, M., Kantarci, B., Khan, S.: Tabcellnet: Deep learning-based tabular cell structure detection. Neurocomputing 440, 12\u201323 (2021)","journal-title":"Neurocomputing"},{"key":"527_CR37","doi-asserted-by":"crossref","unstructured":"Fang, J., Tao, X., Tang, Z., Qiu, R., Liu, Y.: Dataset, ground-truth and performance metrics for table detection evaluation, in 2012 10th IAPR International Workshop on Document Analysis Systems (IEEE), pp. 445\u2013449 (2012)","DOI":"10.1109\/DAS.2012.29"},{"key":"527_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context, in Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13 (Springer), pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"527_CR39","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection, in Proceedings of the IEEE conference on computer vision and pattern recognition , pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"527_CR40","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"527_CR41","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33, 6840\u20136851 (2020)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"527_CR42","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"527_CR43","unstructured":"detrex contributors. detrex: An research platform for transformer-based object detection algorithms. https:\/\/github.com\/IDEA-Research\/detrex (2022)"},{"key":"527_CR44","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":"527_CR45","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database, in 2009 IEEE conference on computer vision and pattern recognition (Ieee), pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"527_CR46","doi-asserted-by":"publisher","unstructured":"Lu, T., Guo, X., Xu, B., Zhao, L., Peng, Y., Yang, H.: Next Big Thing in Big Data: The Security of the ICT Supply Chain, in 2013 International Conference on Social Computing , pp. 1066\u20131073. (2013) https:\/\/doi.org\/10.1109\/SocialCom.2013.172","DOI":"10.1109\/SocialCom.2013.172"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00527-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-025-00527-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00527-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T06:50:31Z","timestamp":1775803831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-025-00527-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["527"],"URL":"https:\/\/doi.org\/10.1007\/s10032-025-00527-9","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"15 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Ala Abu Alkheir is an employee of Lytica, which may be using the table detection techniques presented in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}