{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:24:21Z","timestamp":1777433061116,"version":"3.51.4"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416750","type":"print"},{"value":"9783031416767","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\/978-3-031-41676-7_20","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"342-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["SelfDocSeg: A Self-supervised Vision-Based Approach Towards Document Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-8406","authenticated-orcid":false,"given":"Subhajit","family":"Maity","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6648-8270","authenticated-orcid":false,"given":"Sanket","family":"Biswas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6364-8654","authenticated-orcid":false,"given":"Siladittya","family":"Manna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-2202","authenticated-orcid":false,"given":"Ayan","family":"Banerjee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4533-4739","authenticated-orcid":false,"given":"Josep","family":"Llad\u00f3s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1273-7969","authenticated-orcid":false,"given":"Saumik","family":"Bhattacharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5426-2618","authenticated-orcid":false,"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, M., Doermann, D.: Voronoi++: a dynamic page segmentation approach based on voronoi and docstrum features. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1011\u20131015 (2009)","DOI":"10.1109\/ICDAR.2009.270"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Bridson, D., Papadopoulos, C., Pletschacher, S.: A realistic dataset for performance evaluation of document layout analysis. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 296\u2013300. IEEE (2009)","DOI":"10.1109\/ICDAR.2009.271"},{"key":"20_CR3","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":"20_CR4","unstructured":"Banerjee, A., Biswas, S., Llad\u00f3s, J., Pal, U.: SwinDocSegmenter: an end-to-end unified domain adaptive transformer for document instance segmentation. In: Document Analysis and Recognition-ICDAR 2023: 17th International Conference, San Jose, California, August 21\u201326, 2023, Proceedings. Springer (2023)"},{"key":"20_CR5","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEit: BERT pre-training of image transformers. In: International Conference on Learning Representations (2022)"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Bar, A., et al.: DETReg: unsupervised pretraining with region priors for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01420"},{"issue":"6","key":"20_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355610","volume":"52","author":"GM Binmakhashen","year":"2019","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surv. (CSUR) 52(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"20_CR8","unstructured":"Biswas, S., Banerjee, A., Llad\u00f3s, J., Pal, U.: DocSegTr: an instance-level end-to-end document image segmentation transformer. arXiv preprint arXiv:2201.11438 (2022)"},{"issue":"3","key":"20_CR9","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","volume":"24","author":"S Biswas","year":"2021","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(3), 269\u2013281 (2021)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"20_CR10","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":"20_CR11","unstructured":"Borchmann, \u0141., et al.: Due: End-to-end document understanding benchmark. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"20_CR12","unstructured":"Bradski, G.: The OpenCV Library. Dr. Dobb\u2019s Journal of Software Tools (2000)"},{"key":"20_CR13","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: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"20_CR14","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":"20_CR15","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 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"20_CR16","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning (2020)"},{"key":"20_CR17","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"20_CR18","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 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Clausner, C., Antonacopoulos, A., Pletschacher, S.: ICDAR 2019 competition on recognition of documents with complex layouts-RDCL2019. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1521\u20131526 (2019)","DOI":"10.1109\/ICDAR.2019.00245"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: Dan: a segmentation-free document attention network for handwritten document recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3235826"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: Up-detr: Unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"20_CR22","doi-asserted-by":"publisher","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) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13804. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"20_CR23","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"20_CR24","unstructured":"Dozat, T.: Incorporating nesterov momentum into Adam (2016)"},{"key":"20_CR25","unstructured":"Falcon, F.N., et al.: W.: PyTorch lightning. GitHub. Note: https:\/\/github.com\/PyTorchLightning\/pytorch-lightning3 (2019)"},{"key":"20_CR26","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: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.304"},{"key":"20_CR27","doi-asserted-by":"publisher","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) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13804. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_22","DOI":"10.1007\/978-3-031-25069-9_22"},{"key":"20_CR28","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"20_CR29","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":"20_CR30","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. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"20_CR32","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 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"20_CR33","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 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"20_CR34","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"H\u00e9naff, O.J., et al.: Object discovery and representation networks. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19812-0_8"},{"key":"20_CR36","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":"20_CR37","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. 2, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"issue":"12","key":"20_CR38","doi-asserted-by":"publisher","first-page":"8846","DOI":"10.1109\/TPAMI.2021.3122572","volume":"44","author":"L Kang","year":"2021","unstructured":"Kang, L., Riba, P., Rusinol, M., Fornes, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8846\u20138860 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR39","unstructured":"Kim, G., et al.: Donut: document understanding transformer without OCR. arXiv preprint arXiv:2111.15664 (2021)"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., Cui, L., Zhang, C., Wei, F.: DiT: self-supervised pre-training for document image transformer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3530\u20133539 (2022)","DOI":"10.1145\/3503161.3547911"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: SelfDoc: self-supervised document representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652\u20135660 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"20_CR42","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"20_CR44","unstructured":"Liu, S., Li, Z., Sun, J.: Self-EMD: self-supervised object detection without ImageNet. arXiv preprint arXiv:2011.13677 (2020)"},{"key":"20_CR45","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"20_CR46","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, 23\u201335 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10032-021-00391-3","volume":"25","author":"L Markewich","year":"2021","unstructured":"Markewich, L., et al.: Segmentation for document layout analysis: not dead yet. Int. J. Doc. Anal. Recogn. (IJDAR) 25, 1\u201311 (2021). https:\/\/doi.org\/10.1007\/s10032-021-00391-3","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"20_CR48","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":"20_CR49","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"20_CR50","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019), http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"20_CR51","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":"20_CR52","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 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"20_CR53","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. 1, pp. 1162\u20131167. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"20_CR54","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":"20_CR55","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":"20_CR56","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, Josep, Lopresti, Daniel, Uchida, Seiichi (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 564\u2013579. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_36"},{"key":"20_CR57","unstructured":"Susmelj, I., Heller, M., Wirth, P., Prescott, J., et al.: Lightly. GitHub. Note: https:\/\/github.com\/lightly-ai\/lightly (2020)"},{"key":"20_CR58","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. 35, pp. 13878\u201313888 (2021)","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"20_CR59","doi-asserted-by":"crossref","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multi-page docVQA. arXiv preprint arXiv:2212.05935 (2022)","DOI":"10.2139\/ssrn.4466918"},{"key":"20_CR60","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"20_CR61","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":"20_CR62","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888 (2017)"},{"key":"20_CR63","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1015\u20131022 (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"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\/978-3-031-41676-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:06:56Z","timestamp":1692342416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41676-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416750","9783031416767"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41676-7_20","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)"}}]}}