{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T01:07:09Z","timestamp":1774314429802,"version":"3.50.1"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031704413","type":"print"},{"value":"9783031704420","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\/978-3-031-70442-0_9","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:09:40Z","timestamp":1725955780000},"page":"142-161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["UnSupDLA: Towards Unsupervised Document Layout Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9156-5679","authenticated-orcid":false,"given":"Talha Uddin","family":"Sheikh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7052-979X","authenticated-orcid":false,"given":"Tahira","family":"Shehzadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0456-6493","authenticated-orcid":false,"given":"Khurram Azeem","family":"Hashmi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-6867","authenticated-orcid":false,"given":"Muhammad Zeshan","family":"Afzal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surv. 52(6) (2019). https:\/\/doi.org\/10.1145\/3355610","DOI":"10.1145\/3355610"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, M., Doermann, D.S.: Voronoi++: a dynamic page segmentation approach based on voronoi and docstrum features. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 1011\u20131015 (2009). https:\/\/api.semanticscholar.org\/CorpusID:3355513","DOI":"10.1109\/ICDAR.2009.270"},{"issue":"1","key":"9_CR3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/TPAMI.2005.4","volume":"27","author":"S Marinai","year":"2005","unstructured":"Marinai, S., Gori, M., Soda, G.: Artificial neural networks for document analysis and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 23\u201335 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR4","doi-asserted-by":"crossref","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. In: 2011 International Conference on Document Analysis and Recognition, pp. 779\u2013783 (2011)","DOI":"10.1109\/ICDAR.2011.304"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking (2022). https:\/\/arxiv.org\/abs\/2204.08387","DOI":"10.1145\/3503161.3548112"},{"key":"9_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-3-030-86549-8_9","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"Z Shen","year":"2021","unstructured":"Shen, Z., Zhang, R., Dell, M., Lee, B.C.G., Carlson, J., Li, W.: LayoutParser: a unified toolkit for deep learning based document image analysis. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 131\u2013146. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_9"},{"key":"9_CR7","unstructured":"Agarwal, M., Mondal, A., Jawahar, C.V.: CDEC-net: composite deformable cascade network for table detection in document images. CoRR, vol. abs\/2008.10831 (2020). https:\/\/arxiv.org\/abs\/2008.10831"},{"key":"9_CR8","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 (CVPR) Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document ai with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"9_CR10","unstructured":"Shehzadi, T., Hashmi, K.A., Stricker, D., Liwicki, M., Afzal, M.Z.: Bridging the performance gap between DETR and R-CNN for graphical object detection in document images. arXiv preprint arXiv:2306.13526 (2023)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Stricker, D., Afzal, M.Z.: A hybrid approach for document layout analysis in document images (2024)","DOI":"10.1007\/978-3-031-70546-5_2"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Sarode, S., Stricker, D., Afzal, M.Z.: Towards end-to-end semi-supervised table detection with semantic aligned matching transformer (2024)","DOI":"10.1007\/978-3-031-70549-6_18"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Ehsan, I., Shehzadi, T., Stricker, D., Afzal, M.Z.: End-to-end semi-supervised approach with modulated object queries for table detection in documents. arXiv preprint arXiv:2405.04971 (2024)","DOI":"10.1007\/s10032-024-00471-0"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Bhatt, J., Hashmi, K.A.A., Afzal, M.Z., Stricker, D.: A survey of graphical page object detection with deep neural networks. Appl. Sci. 11(12) (2021). https:\/\/www.mdpi.com\/2076-3417\/11\/12\/5344","DOI":"10.3390\/app11125344"},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Markewich, L., et al.: Segmentation for document layout analysis: not dead yet. Int. J. Doc. Anal. Recogn. (IJDAR) (2022). https:\/\/doi.org\/10.1007\/s10032-021-00391-3","DOI":"10.1007\/s10032-021-00391-3"},{"key":"9_CR16","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/978-0-85729-859-1_20","volume-title":"Handbook of Document Image Processing and Recognition","author":"B Co\u00fcasnon","year":"2014","unstructured":"Co\u00fcasnon, B., Lemaitre, A.: Recognition of tables and forms. In: Doermann, D., Tombre, K. (eds.) Handbook of Document Image Processing and Recognition, pp. 647\u2013677. Springer, London (2014). https:\/\/doi.org\/10.1007\/978-0-85729-859-1_20"},{"issue":"1","key":"9_CR17","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":"9_CR18","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"},{"issue":"1","key":"9_CR19","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":"9_CR20","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":"9_CR21","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.\u00a03, pp. 236\u2013240 (2002)","DOI":"10.1109\/ICPR.2002.1047838"},{"key":"9_CR22","unstructured":"Shehzadi, T., Hashmi, K.A., Stricker, D., Afzal, M.Z.: Object detection with transformers: a review (2023)"},{"key":"9_CR23","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, vol. abs\/1706.02337 (2017). http:\/\/arxiv.org\/abs\/1706.02337","DOI":"10.1109\/CVPR.2017.462"},{"key":"9_CR24","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) (2022)","DOI":"10.3390\/app12199398"},{"key":"9_CR25","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, 2017, pp. 254\u2013261 (2017)","DOI":"10.1109\/ICDAR.2017.50"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Hashmi, K.A., Stricker, D., Afzal, M.Z.: Sparse semi-DETR: sparse learnable queries for semi-supervised object detection. arXiv preprint arXiv:2404.01819 (2024)","DOI":"10.1109\/CVPR52733.2024.00558"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: TokenCut: segmenting objects in images and videos with self-supervised transformer and normalized cut. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3305122"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: SelfDoc: self-supervised document representation learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5648\u20135656 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Majid, A., Hameed, M., Farooq, A., Yousaf, A.: Intelligent predictor using cancer-related biologically information extraction from cancer transcriptomes. In: 2020 International Symposium on Recent Advances in Electrical Engineering & Computer Sciences (RAEE & CS), vol.\u00a05, pp. 1\u20135 (2020)","DOI":"10.1109\/RAEECS50817.2020.9265692"},{"issue":"1","key":"9_CR31","first-page":"98","volume":"13","author":"A Yousaf","year":"2021","unstructured":"Yousaf, A., Shehzadi, T., Farooq, A., Ilyas, K.: Protein active site prediction for early drug discovery and designing. Int. Rev. Appl. Sci. Eng. 13(1), 98\u2013105 (2021)","journal-title":"Int. Rev. Appl. Sci. Eng."},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Saeed, W., Saleh, M.S., Gull, M.N., Raza, H., Saeed, R., Shehzadi, T.: Geometric features and traffic dynamic analysis on 4-leg intersections. Int. Rev. Appl. Sci. Eng. (2023)","DOI":"10.1556\/1848.2023.00681"},{"key":"9_CR33","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) (2022). https:\/\/www.mdpi.com\/2076-3417\/12\/18\/8969","DOI":"10.3390\/app12188969"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"K\u00f6lsch, A., Afzal, M.Z., Ebbecke, M., Liwicki, M.: Real-time document image classification using deep CNN and extreme learning machines. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a001, pp. 1318\u20131323 (2017)","DOI":"10.1109\/ICDAR.2017.217"},{"key":"9_CR35","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) (2022). https:\/\/www.mdpi.com\/2076-3417\/12\/20\/10578","DOI":"10.3390\/app122010578"},{"key":"9_CR36","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) (2022). https:\/\/www.mdpi.com\/2076-3417\/12\/15\/7486","DOI":"10.3390\/app12157486"},{"key":"9_CR37","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) (2021). https:\/\/www.mdpi.com\/2076-3417\/11\/16\/7610","DOI":"10.3390\/app11167610"},{"key":"9_CR38","unstructured":"Hashmi, K.A., Stricker, D., Liwicki, M., Afzal, M.N., M.Z.: Guided table structure recognition through anchor optimization. CoRR, vol. abs\/2104.10538 (2021). https:\/\/arxiv.org\/abs\/2104.10538"},{"key":"9_CR39","unstructured":"Borchmann, \u0141., et al.: DUE: end-to-end document understanding benchmark. In: NeurIPS Datasets and Benchmarks (2021). https:\/\/api.semanticscholar.org\/CorpusID:244906279"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.-P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol.\u00a02, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"9_CR41","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing (2019). https:\/\/api.semanticscholar.org\/CorpusID:207900784"},{"key":"9_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-86549-8_36","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"T Stanis\u0142awek","year":"2021","unstructured":"Stanis\u0142awek, T., et al.: Kleister: key information extraction datasets involving long documents with complex layouts. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 564\u2013579. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_36"},{"key":"9_CR43","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). https:\/\/api.semanticscholar.org\/CorpusID:2760893","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"9_CR44","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":"9_CR45","doi-asserted-by":"crossref","unstructured":"Shen, Z., Zhang, K., Dell, M.: A large dataset of historical Japanese documents with complex layouts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 548\u2013549 (2020)","DOI":"10.1109\/CVPRW50498.2020.00282"},{"key":"9_CR46","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"9_CR47","doi-asserted-by":"publisher","first-page":"109834","DOI":"10.1016\/j.patcog.2023.109834","volume":"144","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multipage DocVQA. Pattern Recogn. 144, 109834 (2023)","journal-title":"Pattern Recogn."},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Yoshida, S.: VisualMRC: machine reading comprehension on document images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, no.\u00a015, pp. 13\u00a0878\u201313\u00a0888 (2021)","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"9_CR50","first-page":"39","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu, J., et al.: UniDoc: unified pretraining framework for document understanding. Adv. Neural. Inf. Process. Syst. 34, 39\u201350 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-031-25069-9_22","volume-title":"Computer Vision - ECCV 2022 Workshops","author":"A Gemelli","year":"2023","unstructured":"Gemelli, A., Biswas, S., Civitelli, E., Llad\u00f3s, J., Marinai, S.: Doc2Graph: a task agnostic document understanding framework based on graph neural networks. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13804, pp. 329\u2013344. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_22"},{"key":"9_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"Computer Vision - ECCV 2022","author":"G Kim","year":"2022","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29"},{"key":"9_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-25069-9_19","volume-title":"Computer Vision - ECCV 2022 Workshops","author":"B Davis","year":"2023","unstructured":"Davis, B., Morse, B., Price, B., Tensmeyer, C., Wigington, C., Morariu, V.: End-to-end document recognition and understanding with dessurt. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13804, pp. 280\u2013296. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19"},{"key":"9_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/978-3-030-86334-0_36","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"S Biswas","year":"2021","unstructured":"Biswas, S., Riba, P., Llad\u00f3s, J., Pal, U.: DocSynth: a layout guided approach for controllable document image synthesis. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12823, pp. 555\u2013568. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_36"},{"key":"9_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-030-86337-1_8","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"M Yim","year":"2021","unstructured":"Yim, M., Kim, Y., Cho, H.-C., Park, S.: SynthTIGER: synthetic text image GEneratoR towards better text recognition models. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 109\u2013124. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_8"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44, 8846\u20138860 (2021). https:\/\/api.semanticscholar.org\/CorpusID:239999745","DOI":"10.1109\/TPAMI.2021.3122572"},{"key":"9_CR57","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.\u00a001, pp. 1162\u20131167 (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"9_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-031-41734-4_12","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"Z Zhong","year":"2023","unstructured":"Zhong, Z., et al.: A hybrid approach to document layout analysis for heterogeneous document images. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14191, pp. 189\u2013206. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_12"},{"key":"9_CR59","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: Vision grid transformer for document layout analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19\u00a0462\u201319\u00a0472 (2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"9_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-3-031-41676-7_18","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"A Banerjee","year":"2023","unstructured":"Banerjee, A., Biswas, S., Llad\u00f3s, J., Pal, U.: SwinDocSegmenter: an end-to-end unified domain adaptive transformer for document instance segmentation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14187, pp. 307\u2013325. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41676-7_18"},{"key":"9_CR61","doi-asserted-by":"crossref","unstructured":"Biswas, S., Riba, P., Llad\u00f3s, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recogn. (IJDAR) 24, 269\u2013281 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237309680","DOI":"10.1007\/s10032-021-00380-6"},{"key":"9_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/978-3-031-41679-8_4","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"T Shehzadi","year":"2023","unstructured":"Shehzadi, T., Azeem Hashmi, K., Stricker, D., Liwicki, M., Zeshan Afzal, M.: Towards end-to-end semi-supervised table detection with deformable transformer. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14188, pp. 51\u201376. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_4"},{"key":"9_CR63","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"9_CR64","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"9_CR65","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. CoRR, vol. abs\/2010.11929 (2020). https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"9_CR66","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"9_CR67","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR68","unstructured":"Grill, J.-B., et al.: Bootstrap your own latent a new approach to self-supervised learning. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020. Curran Associates Inc., Red Hook (2020)"},{"key":"9_CR69","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15\u00a0750\u201315\u00a0758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"9_CR70","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. CoRR, vol. abs\/2111.06377 (2021). https:\/\/arxiv.org\/abs\/2111.06377"},{"key":"9_CR71","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"9_CR72","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. CoRR, vol. abs\/2106.00666 (2021). https:\/\/arxiv.org\/abs\/2106.00666"},{"key":"9_CR73","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. CoRR, vol. abs\/1708.02002 (2017). http:\/\/arxiv.org\/abs\/1708.02002","DOI":"10.1109\/ICCV.2017.324"},{"key":"9_CR74","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":"9_CR75","unstructured":"ZDa, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: unsupervised pre-training for object detection with transformers. CoRR, vol. abs\/2011.09094 (2020). https:\/\/arxiv.org\/abs\/2011.09094"},{"key":"9_CR76","unstructured":"Bar, A., et al.: DETReg: unsupervised pretraining with region priors for object detection. CoRR, vol. abs\/2106.04550 (2021). https:\/\/arxiv.org\/abs\/2106.04550"},{"key":"9_CR77","unstructured":"Liu, S., Li, Z., Sun, J.: Self-EMD: self-supervised object detection without ImageNet. arXiv preprint arXiv:2011.13677 (2020)"},{"key":"9_CR78","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-031-19812-0_8","volume-title":"Computer Vision - ECCV 2022","author":"OJ H\u00e9naff","year":"2022","unstructured":"H\u00e9naff, O.J., et al.: Object discovery and representation networks. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 123\u2013143. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_8"},{"key":"9_CR79","doi-asserted-by":"crossref","unstructured":"Davoudi, H., Fiorucci, M., Traviglia, A.: Ancient document layout analysis: autoencoders meet sparse coding. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5936\u20135942 (2021)","DOI":"10.1109\/ICPR48806.2021.9413280"},{"key":"9_CR80","unstructured":"Wu, X., et al.: Cross-domain document layout analysis via unsupervised document style guide. CoRR, vol. abs\/2201.09407 (2022). https:\/\/arxiv.org\/abs\/2201.09407"},{"key":"9_CR81","doi-asserted-by":"crossref","unstructured":"Wang, X., Girdhar, R., Yu, S.X., Misra, I.: Cut and learn for unsupervised object detection and instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3124\u20133134 (2023)","DOI":"10.1109\/CVPR52729.2023.00305"},{"issue":"8","key":"9_CR82","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888\u2013905 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR83","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2917\u20132927 (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"9_CR84","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Misra, I., Hebert, M.: Cut, paste and learn: surprisingly easy synthesis for instance detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1301\u20131310 (2017)","DOI":"10.1109\/ICCV.2017.146"},{"key":"9_CR85","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: DocLayNet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 3743\u20133751 (2022)","DOI":"10.1145\/3534678.3539043"},{"key":"9_CR86","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: a benchmark dataset for table detection and recognition (2019)"},{"key":"9_CR87","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. CoRR, vol. abs\/1712.00726 (2017). http:\/\/arxiv.org\/abs\/1712.00726"},{"key":"9_CR88","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-ResNet and the impact of residual connections on learning. CoRR, vol. abs\/1602.07261 (2016). http:\/\/arxiv.org\/abs\/1602.07261","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"9_CR89","doi-asserted-by":"crossref","unstructured":"Yang, H., Hsu, W.: Transformer-based approach for document layout understanding. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 4043\u20134047 (2022)","DOI":"10.1109\/ICIP46576.2022.9897491"},{"key":"9_CR90","unstructured":"Zhang, P., et al.: VSR: a unified framework for document layout analysis combining vision, semantics and relations. CoRR, vol. abs\/2105.06220 (2021). https:\/\/arxiv.org\/abs\/2105.06220"},{"key":"9_CR91","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-031-41734-4_4","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"J Wang","year":"2023","unstructured":"Wang, J., et al.: A graphical approach to document layout analysis. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14191, pp. 53\u201369. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_4"},{"key":"9_CR92","doi-asserted-by":"publisher","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: DocLayNet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022. ACM (2022). https:\/\/doi.org\/10.1145\/3534678.3539043","DOI":"10.1145\/3534678.3539043"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70442-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T23:12:15Z","timestamp":1732749135000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70442-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031704413","9783031704420"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70442-0_9","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":"11 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Document Analysis Systems","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":"31 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"das2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/das2024.seecs.edu.pk\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}