{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T21:22:40Z","timestamp":1785014560197,"version":"3.55.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"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":["IJDAR"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s10032-022-00400-z","type":"journal-article","created":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T15:03:52Z","timestamp":1651503832000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["YOLO-table: disclosure document table detection with involution"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3879-0912","authenticated-orcid":false,"given":"Daqian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruibin","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runting","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,2]]},"reference":[{"key":"400_CR1","doi-asserted-by":"crossref","unstructured":"Li, H., Yang, Q., Cao, Y., Yao, J., et al.: Cracking tabular presentation diversity for automatic cross-checking over numerical facts. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2599\u20132607 (2020)","DOI":"10.1145\/3394486.3403310"},{"issue":"3","key":"400_CR2","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/s100320200074","volume":"4","author":"J Hu","year":"2020","unstructured":"Hu, J., Kashi, R.S., Lopresti, D., et al.: Evaluating the performance of table processing algorithms. Int. J. Doc. Anal. Recogn. 4(3), 140\u2013153 (2020)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"400_CR3","unstructured":"Dai, J., Li, Y., He, K., et al.: R-fcn: Object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379\u2013387 (2016)"},{"key":"400_CR4","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"400_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"400_CR6","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et al.: 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":"400_CR7","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: SSD: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"400_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"400_CR9","doi-asserted-by":"crossref","unstructured":"Gobel, M., Hassan, T., Oro, E., et al.: Icdar 2013 table competition. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1449\u20131453 (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"400_CR10","doi-asserted-by":"crossref","unstructured":"Gao, L., Huang, Y., D\u00e9jean, H., et al.: Icdar 2019 competition on table detection and recognition (ctdar). In: 2019 15th International Conference on Document Analysis and Recognition (ICDAR), pp. 1510\u20131515 (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"400_CR11","doi-asserted-by":"crossref","unstructured":"Cesarini, F., Marinai, S., Sarti, L., et al.: Trainable table location in document images. In: Object Recognition Supported by User Interaction for Service Robots vol. 3, pp. 236\u2013240 (2002)","DOI":"10.1109\/ICPR.2002.1047838"},{"key":"400_CR12","unstructured":"Yildiz, B., Kaiser, K., Miksch, S.: pdf2table: A method to extract table information from pdf files. In: IICAI, pp. 1773\u20131785 (2005)"},{"key":"400_CR13","doi-asserted-by":"crossref","unstructured":"Silva, A.C.: Learning rich hidden Markov models in document analysis: Table location. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 843\u2013847 (2009)","DOI":"10.1109\/ICDAR.2009.185"},{"key":"400_CR14","doi-asserted-by":"crossref","unstructured":"Melinda, L., Bhagvati, C.: Parameter-free table detection method. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 454\u2013460 (2019)","DOI":"10.1109\/ICDAR.2019.00079"},{"key":"400_CR15","doi-asserted-by":"crossref","unstructured":"He, D., Cohen, S., Price, B., et al.: Multi-scale multi-task FCN for semantic page segmentation and table detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 254\u2013261 (2017)","DOI":"10.1109\/ICDAR.2017.50"},{"key":"400_CR16","doi-asserted-by":"crossref","unstructured":"Fang, J., Tao, X., Tang, Z., et al.: Dataset, ground-truth and performance metrics for table detection evaluation. In: 2012 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 445\u2013449 (2012)","DOI":"10.1109\/DAS.2012.29"},{"key":"400_CR17","doi-asserted-by":"crossref","unstructured":"Kavasidis, I., Palazzo, S., Spampinato, C., et al.: A saliency-based convolutional neural network for table and chart detection in digitized documents. arXiv preprint arXiv:1804.06236 (2018)","DOI":"10.1007\/978-3-030-30645-8_27"},{"key":"400_CR18","doi-asserted-by":"crossref","unstructured":"Gilani, A., Qasim, S. R., Malik, I., et al.: Table detection using deep learning. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 771\u2013776 (2017)","DOI":"10.1109\/ICDAR.2017.131"},{"key":"400_CR19","doi-asserted-by":"crossref","unstructured":"Shafait, F., Smith, R.: Table detection in heterogeneous documents. In: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, pp. 65\u201372 (2010)","DOI":"10.1145\/1815330.1815339"},{"key":"400_CR20","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Kieninger, T., et al.: An open approach towards the benchmarkingof table structure recognition systems. In Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, pp. 113\u2013120 (2010)","DOI":"10.1145\/1815330.1815345"},{"key":"400_CR21","doi-asserted-by":"crossref","unstructured":"Sun, N., Zhu, Y., Hu, X.: Faster R-CNN based table detection combining corner locating. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1314\u20131319 (2019)","DOI":"10.1109\/ICDAR.2019.00212"},{"key":"400_CR22","doi-asserted-by":"crossref","unstructured":"Gao, L., Yi, X., Jiang, Z., et al.: ICDAR 2017 Competition on Page Object Detection. In: 2017 14th International Conference on Document Analysis and Recognition (ICDAR), pp. 1417\u20131422 (2017)","DOI":"10.1109\/ICDAR.2017.231"},{"key":"400_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Yan, Q., Li, Y., et al.: A YOLO-based table detection method. In 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 813\u2013818 (2019)","DOI":"10.1109\/ICDAR.2019.00135"},{"key":"400_CR24","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"issue":"1","key":"400_CR25","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1927\/1\/012004","volume":"1927","author":"X Zhang","year":"2021","unstructured":"Zhang, X., Bai, Y., Wei, N., et al.: Cloud computer research on table detection model based on the DC-LSTM model. J. Phys. Conf. Ser. 1927(1), 012004 (2021)","journal-title":"J. Phys. Conf. Ser."},{"key":"400_CR26","unstructured":"Li, M., Cui, L., Huang, S., et al.: TableBank: Table Benchmark for Image-based Table Detection and Recognition. In: Proceedings of the 12th Language Resources and Evaluation (2020)"},{"key":"400_CR27","doi-asserted-by":"crossref","unstructured":"Riba, P., Dutta, A., Goldmann, L., et al.: Table detection in invoice documents by graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 122\u2013127 (2019)","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"400_CR28","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 991\u2013995 (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"400_CR29","doi-asserted-by":"crossref","unstructured":"Li, D., Hu, J., Wang, C., et al.: Involution: Inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12321\u201312330 (2021)","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"400_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"400_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., et al.: 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":"400_CR32","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., et al.: You only look one-level feature. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13039\u201313048 (2021)","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"400_CR33","unstructured":"Yu, F., Koltun, V: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)"},{"key":"400_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: 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":"400_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., et al.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"400_CR36","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., et al.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"400_CR37","doi-asserted-by":"crossref","unstructured":"Khan, U., Zahid, S., Ali, M. A., et al.: TabAug: data driven augmentation for enhanced table structure recognition. In: International Conference on Document Analysis and Recognition, pp. 585\u2013601 (2021)","DOI":"10.1007\/978-3-030-86331-9_38"},{"key":"400_CR38","unstructured":"Shepley, A., Falzon, G., Kwan, P.: Confluence: A robust non-IoU alternative to non-maxima suppression in object detection. arXiv preprint arXiv:2012.00257 (2020)"},{"key":"400_CR39","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van Gool, L: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR\u201906), vol. 3, pp. 850\u2013855 (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"400_CR40","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":"400_CR41","doi-asserted-by":"crossref","unstructured":"Schreiber, S., Agne, S., Wolf, I., et al.: 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. 1, pp. 1162\u20131167 (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"400_CR42","doi-asserted-by":"crossref","unstructured":"Tran, D. N., Tran, T. A., Oh, A., et al.: Table detection from document image using vertical arrangement of text blocks. Int. J. Contents 77\u201385 (2015)","DOI":"10.5392\/IJoC.2015.11.4.077"},{"key":"400_CR43","doi-asserted-by":"crossref","unstructured":"Hao, L., Gao, L., Yi, X., et al.: A table detection method for pdf documents based on convolutional neural networks. In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS), pp. 287\u2013292 (2016)","DOI":"10.1109\/DAS.2016.23"},{"key":"400_CR44","doi-asserted-by":"crossref","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., et al.: ascadeTabNet: 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":"400_CR45","doi-asserted-by":"crossref","unstructured":"SNazir, D., Hashmi, K. A., Pagani, A., et al.: HybridTabNet: Towards better table detection in scanned document images. Appl. Sci. 11(18), 8396 (2021)","DOI":"10.3390\/app11188396"},{"key":"400_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, X., Burdick, D., Popa, L., et al.: 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":"400_CR47","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., et al.: DiT: Self-supervised Pre-training for Document Image Transformer. arXiv preprint arXiv:2203.02378 (2022)","DOI":"10.1145\/3503161.3547911"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-022-00400-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-022-00400-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-022-00400-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T15:11:35Z","timestamp":1727104295000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-022-00400-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["400"],"URL":"https:\/\/doi.org\/10.1007\/s10032-022-00400-z","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,2]]},"assertion":[{"value":"15 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}