{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:48:57Z","timestamp":1777567737066,"version":"3.51.4"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416781","type":"print"},{"value":"9783031416798","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\/978-3-031-41679-8_4","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"51-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Towards End-to-End Semi-Supervised Table Detection with\u00a0Deformable Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7052-979X","authenticated-orcid":false,"given":"Tahira","family":"Shehzadi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0456-6493","authenticated-orcid":false,"given":"Khurram","family":"Azeem Hashmi","sequence":"additional","affiliation":[]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[]},{"given":"Marcus","family":"Liwicki","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-6867","authenticated-orcid":false,"given":"Muhammad","family":"Zeshan Afzal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Jiang, M., Guo, S., Wang, Z., Chao, F., Tan, K.C.: Improving deep learning based optical character recognition via neural architecture search. In: IEEE Congress on Evolutionary Computation (CEC 2020), pp. 1\u20137 (2020)","DOI":"10.1109\/CEC48606.2020.9185798"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Van Strien, D., Beelen, K., Ardanuy, M.C., Hosseini, K., McGillivray, B., Colavizza, G.: Assessing the impact of OCR quality on downstream NLP tasks (2020)","DOI":"10.5220\/0009169004840496"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Co\u00fcasnon, B., Lemaitre, A.: Recognition of tables and forms. In: Handbook of Document Image Processing and Recognition (2014)","DOI":"10.1007\/978-0-85729-859-1_20"},{"issue":"1","key":"4_CR4","first-page":"1","volume":"7","author":"R Zanibbi","year":"2004","unstructured":"Zanibbi, R., Blostein, D., Cordy, J.R.: A survey of table recognition. Doc. Anal. Recogn. 7(1), 1\u201316 (2004)","journal-title":"Doc. Anal. Recogn."},{"issue":"2","key":"4_CR5","first-page":"144","volume":"8","author":"AM Jorge","year":"2006","unstructured":"Jorge, A.M., Torgo, L., et al.: Design of an end-to-end method to extract information from tables. IJDAR 8(2), 144\u2013171 (2006)","journal-title":"IJDAR"},{"key":"4_CR6","first-page":"779","volume":"2011","author":"J Fang","year":"2011","unstructured":"Fang, J., Gao, L., Bai, K., Qiu, R., Tao, X., Tang, Z.: A table detection method for multipage pdf documents via visual seperators and tabular structures. Int. Conf. Doc. Anal. Recogn. 2011, 779\u2013783 (2011)","journal-title":"Int. Conf. Doc. Anal. Recogn."},{"key":"4_CR7","first-page":"399","volume":"2011","author":"J Chen","year":"2011","unstructured":"Chen, J., Lopresti, D.: Table detection in noisy off-line handwritten documents. Int. Conf. Doc. Anal. Recogn. 2011, 399\u2013403 (2011)","journal-title":"Int. Conf. Doc. Anal. Recogn."},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Hashmi, K.A., Bymana Ponnappa, R., Bukhari, S.S., Jenckel, M., Dengel, A.: Feedback learning: automating the process of correcting and completing the extracted information. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 5, pp. 116\u2013121 (2019)","DOI":"10.1109\/ICDARW.2019.40091"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Saha, R., Mondal, A., Jawahar, C.V.: Graphical object detection in document images. CoRR abs\/2008.10843 (2020). arXiv:2008.10843","DOI":"10.1109\/ICDAR.2019.00018"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN CoRR, abs\/1504.08083 (2015). arXiv:1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"key":"4_CR11","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR. abs\/1506.01497 (2015). arXiv:1506.01497"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR. abs\/1612.08242 (2016). arXiv:1612.08242","DOI":"10.1109\/CVPR.2017.690"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV 2017), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Orosz, T., V\u00e1gi, R., Cs\u00e1nyi, G.M., Nagy, D., \u00dcveges, I., Vad\u00e1sz, J.P., Megyeri, A.: Evaluating human versus machine learning performance in a LegalTech problem. Appl. Sci. 12(1), 297 (2022). www.mdpi.com\/2076-3417\/12\/1\/297","DOI":"10.3390\/app12010297"},{"key":"4_CR15","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. 01, pp. 1162\u20131167 (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"4_CR16","doi-asserted-by":"crossref","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). www.mdpi.com\/2076-3417\/12\/18\/8969","DOI":"10.3390\/app12188969"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Hashmi, K.A., Stricker, D., Liwicki, M., Afzal, M.N., Afzal, M.Z.: Guided table structure recognition through anchor optimization. CoRR. abs\/2104.10538 (2021). arXiv:2104.10538","DOI":"10.1109\/ACCESS.2021.3103413"},{"key":"4_CR18","doi-asserted-by":"crossref","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). www.mdpi.com\/2076-3417\/11\/16\/7610","DOI":"10.3390\/app11167610"},{"key":"4_CR19","doi-asserted-by":"crossref","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). www.mdpi.com\/2076-3417\/12\/20\/10578","DOI":"10.3390\/app122010578"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Naik, S., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Investigating attention mechanism for page object detection in document images. Appl. Sci. 12(15), 7486 (2022). www.mdpi.com\/2076-3417\/12\/15\/7486","DOI":"10.3390\/app12157486"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Wang, K., Yan, X., Zhang, D., Zhang, L., Lin, L.: Towards human-machine cooperation: self-supervised sample mining for object detection. CoRR. abs\/1803.09867 (2018). arXiv:1803.09867","DOI":"10.1109\/CVPR.2018.00173"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Tang, P., Ramaiah, C., Xu, R., Xiong, C.: Proposal learning for semi-supervised object detection. CoRR. abs\/2001.05086 (2020). arXiv:2001.05086","DOI":"10.1109\/WACV48630.2021.00234"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Rhee, P.K., Erdenee, E., Kyun, S.D., Ahmed, M.U., Jin, S.: Active and semi-supervised learning for object detection with imperfect data. Cogn. Syst. Res. 45, 109\u2013123 (2017). www.sciencedirect.com\/science\/article\/pii\/S1389041716301127","DOI":"10.1016\/j.cogsys.2017.05.006"},{"key":"4_CR24","unstructured":"Xie, Q., Dai, Z., Hovy, E.H., Luong, M., Le, Q.V.: Unsupervised data augmentation. CoRR. abs\/1904.12848 (2019). arXiv:1904.12848"},{"key":"4_CR25","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. CoRR. abs\/2010.04159 (2020). arXiv:2010.04159"},{"key":"4_CR26","unstructured":"Itonori, K.: Table structure recognition based on textblock arrangement and ruled line position. In: Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR 1993), pp. 765\u2013768 (1993)"},{"key":"4_CR27","unstructured":"Tupaj, S., Shi, Z., Chang, C.H., Alam, H.: Extracting tabular information from text files. EECS Department, Tufts University, Medford, USA, vol. 1 (1996)"},{"key":"4_CR28","unstructured":"Chandran, S., Kasturi, R.: Structural recognition of tabulated data. In: Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR 1993), pp. 516\u2013519 (1993)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Hirayama, Y.: A method for table structure analysis using DP matching. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 2, pp. 583\u2013586 (1995)","DOI":"10.1109\/ICDAR.1995.601964"},{"key":"4_CR30","doi-asserted-by":"publisher","unstructured":"Kieninger, T.G.: Table structure recognition based on robust block segmentation. In: Lopresti, D.P., Zhou, J., Document Recognition V (Eds.), vol. 3305, International Society for Optics and Photonics. SPIE, pp. 22\u201332 (1998). https:\/\/doi.org\/10.1117\/12.304642","DOI":"10.1117\/12.304642"},{"key":"4_CR31","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":"4_CR32","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3390\/jimaging7100214","volume":"7","author":"KA Hashmi","year":"2021","unstructured":"Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Castabdetectors: cascade network for table detection in document images with recursive feature pyramid and switchable atrous convolution. J. Imaging. 7, 214 (2021)","journal-title":"J. Imaging."},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Nazir, D., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: HybridTabNet: towards better table detection in scanned document images. Appl. Sci. 11(18), 8396 (2021). www.mdpi.com\/2076-3417\/11\/18\/8396","DOI":"10.3390\/app11188396"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Pyreddy, P., Croft, W.B.: Tintin: a system for retrieval in text tables. In: Digital Library (1997)","DOI":"10.1145\/263690.263816"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Pivk, A., Cimiano, P., Sure, Y., Gams, M., Rajkovi\u010d, V., Studer, R.: Transforming arbitrary tables into logical form with tartar. Data Knowl. Eng. 60(3), 567\u2013595 (2007). www.sciencedirect.com\/science\/article\/pii\/S0169023X06000620","DOI":"10.1016\/j.datak.2006.04.002"},{"key":"4_CR36","doi-asserted-by":"publisher","unstructured":"Hu, J., Kashi, R.S., Lopresti, D.P., Wilfong, G.: Medium-independent table detection. In: Lopresti, D.P., Zhou, J., (Eds.) Document Recognition and Retrieval VII, vol. 3967, International Society for Optics and Photonics. SPIE, pp. 291\u2013302 (1999). https:\/\/doi.org\/10.1117\/12.373506","DOI":"10.1117\/12.373506"},{"issue":"1","key":"4_CR37","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1177\/0165551514551903","volume":"41","author":"S Khusro","year":"2015","unstructured":"Khusro, S., Latif, A., Ullah, I.: On methods and tools of table detection, extraction and annotation in pdf documents. J. Inf. Sci. 41(1), 41\u201357 (2015)","journal-title":"J. Inf. Sci."},{"issue":"2","key":"4_CR38","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/s10032-006-0017-x","volume":"8","author":"DW Embley","year":"2006","unstructured":"Embley, D.W., Hurst, M., Lopresti, D., Nagy, G.: Table-processing paradigms: a research survey. IJDAR 8(2), 66\u201386 (2006)","journal-title":"IJDAR"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Cesarini, F., Marinai, S., Sarti, L., Soda, G.: Trainable table location in document images. In: 2002 International Conference on Pattern Recognition, vol. 3, pp. 236\u2013240 (2002)","DOI":"10.1109\/ICPR.2002.1047838"},{"key":"4_CR40","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":"4_CR41","volume-title":"Parts that Add up to a Whole: a Framework for the Analysis of Tables","author":"A Silva","year":"2010","unstructured":"Silva, A.: Parts that Add up to a Whole: a Framework for the Analysis of Tables. Edinburgh University, UK (2010)"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Kasar, T., Barlas, P., Adam, S., Chatelain, C., Paquet, T.: Learning to detect tables in scanned document images using line information. In: 2013 12th International Conference on Document Analysis and Recognition. IEEE, pp. 1185\u20131189 (2013)","DOI":"10.1109\/ICDAR.2013.240"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Yang, X., Y\u00fcmer, M.E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural network. CoRR, abs\/1706.02337 (2017). arXiv:1706.02337","DOI":"10.1109\/CVPR.2017.462"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"He, D., Cohen, S., Price, B., Kifer, D., Giles, C.L.: Multi-scale multi-task FCN for semantic page segmentation and table detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 254\u2013261 (2017)","DOI":"10.1109\/ICDAR.2017.50"},{"key":"4_CR45","unstructured":"Kavasidis, I., et al.: A saliency-based convolutional neural network for table and chart detection in digitized documents. CoRR. abs\/1804.06236 (2018). arXiv:1804.06236"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Paliwal, S.V.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. CoRR, abs\/2001.01469 (2020). arXiv:2001.01469","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Gao, L., et al.: ICDAR 2019 competition on table detection and recognition (CTDAR). In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510\u20131515. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"4_CR48","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, September 2019","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Mondal, A., Lipps, P., Jawahar, C.V.: IIIT-AR-13K: a new dataset for graphical object detection in documents. CoRR, abs\/2008.02569 (2020). arXiv:2008.02569","DOI":"10.1007\/978-3-030-57058-3_16"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"G\u00f6bel, M.C., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1449\u20131453 (2013)","DOI":"10.1109\/ICDAR.2013.292"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: ICDAR 2017 competition on page object detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1417\u20131422 (2017)","DOI":"10.1109\/ICDAR.2017.231"},{"key":"4_CR52","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: a benchmark dataset for table detection and recognition (2019)"},{"key":"4_CR53","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 (CVPR), pp. 4634\u20134642, June 2022","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR, abs\/1411.4038 (2014). arXiv:1411.4038","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Li, X.-H., Yin, F., Liu, C.-L.: Page object detection from pdf document images by deep structured prediction and supervised clustering. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3627\u20133632 (2018)","DOI":"10.1109\/ICPR.2018.8546073"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Holecek, M., Hoskovec, A., Baudis, P., Klinger, P.: Line-items and table understanding in structured documents. CoRR. abs\/1904.12577 (2019). arXiv:1904.12577","DOI":"10.1109\/ICDARW.2019.40098"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Riba, P., Goldmann, L., Terrades, O.R., Rusticus, D., Forn\u00e9s, A., Llad\u00f3s, J.: Table detection in business document images by message passing networks. Pattern Recogn. 127, 108641 (2022). www.sciencedirect.com\/science\/article\/pii\/S0031320322001224","DOI":"10.1016\/j.patcog.2022.108641"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Hao, L., Gao, L., Yi, X., Tang, Z.: 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":"4_CR59","doi-asserted-by":"crossref","unstructured":"Yi, X., Gao, L., Liao, Y., Zhang, X., Liu, R., Jiang, Z.: CNN based page object detection in document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 230\u2013235 (2017)","DOI":"10.1109\/ICDAR.2017.46"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. CoRR. abs\/1708.02002 (2017). arXiv:1708.02002","DOI":"10.1109\/ICCV.2017.324"},{"key":"4_CR61","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. CoRR, abs\/2106.00666 (2021). arXiv:2106.00666"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. CoRR. abs\/1703.06870 (2017). arXiv:1703.06870","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR63","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. CoRR abs\/1712.00726 (2017). arXiv:1712.00726","DOI":"10.1109\/CVPR.2018.00644"},{"key":"4_CR64","doi-asserted-by":"publisher","unstructured":"Vo, N.D., Nguyen, K., Nguyen, T.V., Nguyen, K.: Ensemble of deep object detectors for page object detection. In: Proceedings of the 12th International Conference on Ubiquitous Information Management and Communication, ser. IMCOM 2018, Association for Computing Machinery. New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3164541.3164644","DOI":"10.1145\/3164541.3164644"},{"key":"4_CR65","doi-asserted-by":"crossref","unstructured":"Gilani, A., Qasim, S.R., Malik, I., Shafait, F.: Table detection using deep learning. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 771\u2013776 (2017)","DOI":"10.1109\/ICDAR.2017.131"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: A yolo-based table detection method. In: International Conference on Document Analysis and Recognition (ICDAR 2019), pp. 813\u2013818 (2019)","DOI":"10.1109\/ICDAR.2019.00135"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"Zheng, X., Burdick, D., Popa, L., Wang, N.X.R.: Global table extractor (GTE): a framework for joint table identification and cell structure recognition using visual context. CoRR. abs\/2005.00589 (2020). arXiv:2005.00589","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"4_CR68","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. CoRR. abs\/2004.12629 (2020). arXiv:2004.12629","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"Agarwal, M., Mondal, A., Jawahar, C.V.: CDEC-Net: composite deformable cascade network for table detection in document images. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9491\u20139498 (2021)","DOI":"10.1109\/ICPR48806.2021.9411922"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"Arif, S., Shafait, F.: Table detection in document images using foreground and background features. In: Digital Image Computing: Techniques and Applications (DICTA 2018), pp. 1\u20138 (2018)","DOI":"10.1109\/DICTA.2018.8615795"},{"key":"4_CR71","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. CoRR. abs\/1703.06211 (2017). arXiv:1703.06211","DOI":"10.1109\/ICCV.2017.89"},{"key":"4_CR72","unstructured":"Liu, Y., et al.: CBNet: a novel composite backbone network architecture for object detection. CoRR. abs\/1909.03625 (2019). arXiv:1909.03625"},{"key":"4_CR73","unstructured":"Jeong, J., Lee, S., Kim, J., Kwak, N.: Consistency-based semi-supervised learning for object detection. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (Eds.) Advances in Neural Information Processing Systemsvol, vol. 32. Curran Associates Inc, (2019). www.proceedings.neurips.cc\/paper\/2019\/file\/d0f4dae80c3d0277922f8371d5827292-Paper.pdf"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Doll\u00e1r, P., Girshick, R.B., Gkioxari, G., He, K.: Data distillation: towards omni-supervised learning. CoRR. abs\/1712.04440 (2017). arXiv:1712.04440","DOI":"10.1109\/CVPR.2018.00433"},{"key":"4_CR75","unstructured":"Zoph, B., et al.: Rethinking pre-training and self-training. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (Eds.) Advances in Neural Information Processing Systems, vol. 33. Curran Associates Inc, 2020, pp. 3833\u20133845. www.proceedings.neurips.cc\/paper\/2020\/file\/27e9661e033a73a6ad8cefcde965c54d-Paper.pdf"},{"key":"4_CR76","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, D., Qin, D., Wang, L., Gong, B.: Improving object detection with selective self-supervised self-training. CoRR. abs\/2007.09162 (2020). arXiv:2007.09162","DOI":"10.1007\/978-3-030-58526-6_35"},{"key":"4_CR77","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Mask-aware semi-supervised object detection in floor plans. Appl. Sci. 12(19), 9398 (2022). www.mdpi.com\/2076-3417\/12\/19\/9398","DOI":"10.3390\/app12199398"},{"key":"4_CR78","doi-asserted-by":"crossref","unstructured":"Kallempudi, G., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Toward semi-supervised graphical object detection in document images. Future Internet. 14(6), 176 (2022). www.mdpi.com\/1999-5903\/14\/6\/176","DOI":"10.3390\/fi14060176"},{"key":"4_CR79","unstructured":"Sohn, K., Zhang, Z., Li, C., Zhang, H., Lee, C., Pfister, T.: A simple semi-supervised learning framework for object detection. CoRR. abs\/2005.04757 (2020). arXiv:2005.04757"},{"key":"4_CR80","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":"4_CR81","unstructured":"Parmar, N., Vaswani, A., Uszkoreit, J., Kaiser, L., Shazeer, N., Ku, A.: Image transformer. CoRR. abs\/1802.05751 (2018). arXiv:1802.05751"},{"key":"4_CR82","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. CoRR. abs\/1904.09925 (2019). arXiv:1904.09925","DOI":"10.1109\/ICCV.2019.00338"},{"key":"4_CR83","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, Guyon, I., et al. (Eds.), vol. 30. Curran Associates Inc. (2017). www.proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"4_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: More deformable, better results. CoRR. abs\/1811.11168 (2018). arXiv:1811.11168","DOI":"10.1109\/CVPR.2019.00953"},{"key":"4_CR85","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 (CVPR 2017), pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"4_CR86","unstructured":"Zhao, Q., et al.: M2det: a single-shot object detector based on multi-level feature pyramid network. CoRR. abs\/1811.04533 (2018). arXiv:1811.04533"},{"key":"4_CR87","unstructured":"Tarvainen, A., Valpola, H.: Weight-averaged consistency targets improve semi-supervised deep learning results. CoRR. abs\/1703.01780 (2017). arXiv:1703.01780"},{"key":"4_CR88","unstructured":"Liu, Y., et al.: Unbiased teacher for semi-supervised object detection. CoRR. abs\/2102.09480 (2021). arXiv:2102.09480"},{"issue":"1\u20132","key":"4_CR89","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"4_CR90","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR91","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: DocBank: a benchmark dataset for document layout analysis. CoRR. abs\/2006.01038, 2020. arXiv:2006.01038","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"4_CR92","unstructured":"Powers, D.M.W.: Evaluation: from precision, recall and f-measure to ROC, informedness, markedness and correlation. CoRR. abs\/2010.16061 (2020). arXiv:2010.16061"},{"key":"4_CR93","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR. abs\/1602.07261 (2016). arXiv:1602.07261","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"4_CR94","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (Eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates Inc. (2012). www.proceedings.neurips.cc\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"4_CR95","doi-asserted-by":"crossref","unstructured":"Tang, Y., Chen, W., Luo, Y., Zhang, Y.: Humble teachers teach better students for semi-supervised object detection. CoRR. abs\/2106.10456 (2021). arXiv:2106.10456","DOI":"10.1109\/CVPR46437.2021.00315"},{"key":"4_CR96","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. CoRR. abs\/2106.09018 (2021). arXiv:2106.09018","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"4_CR97","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VSR: a unified framework for document layout analysis combining vision, semantics and relations. CoRR. abs\/2105.06220 (2021). arXiv:2105.06220","DOI":"10.1007\/978-3-030-86549-8_8"}],"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\/978-3-031-41679-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:41:45Z","timestamp":1729935705000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_4","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)"}}]}}