{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T18:44:00Z","timestamp":1761677040515,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030861582"},{"type":"electronic","value":"9783030861599"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86159-9_32","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:33:19Z","timestamp":1630701199000},"page":"440-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-task Learning for Newspaper Image Segmentation and Baseline Detection Using Attention-Based U-Net Architecture"],"prefix":"10.1007","author":[{"given":"Anukriti","family":"Bansal","sequence":"first","affiliation":[]},{"given":"Prerana","family":"Mukherjee","sequence":"additional","affiliation":[]},{"given":"Divyansh","family":"Joshi","sequence":"additional","affiliation":[]},{"given":"Devashish","family":"Tripathi","sequence":"additional","affiliation":[]},{"given":"Arun Pratap","family":"Singh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"32_CR1","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th $$\\{$$USENIX$$\\}$$ Symposium on Operating Systems Design and Implementation ($$\\{$$OSDI$$\\}$$ 2016), pp. 265\u2013283 (2016)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Alh\u00e9riti\u00e8re, H., Cloppet, F., Kurtz, C., Ogier, J.M., Vincent, N.: A document straight line based segmentation for complex layout extraction. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1126\u20131131. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.186"},{"key":"32_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Bansal, A., Chaudhury, S., Roy, S.D., Srivastava, J.: Newspaper article extraction using hierarchical fixed point model. In: 2014 11th IAPR International Workshop on Document Analysis Systems, pp. 257\u2013261. IEEE (2014)","DOI":"10.1109\/DAS.2014.42"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Beretta, R., Laura, L.: Performance evaluation of algorithms for newspaper article identification. In: 2011 International Conference on Document Analysis and Recognition, pp. 394\u2013398. IEEE (2011)","DOI":"10.1109\/ICDAR.2011.87"},{"key":"32_CR6","unstructured":"Chollet, F., et al.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Clausner, C., Antonacopoulos, A., Derrick, T., Pletschacher, S.: ICDAR 2019 competition on recognition of early Indian printed documents-REID 2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1527\u20131532. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00246"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: Span: a simple predict and align network for handwritten paragraph recognition. arXiv preprint arXiv:2102.08742 (2021)","DOI":"10.1007\/978-3-030-86334-0_5"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Diem, M., Kleber, F., Fiel, S., Gr\u00fcning, T., Gatos, B.: CBAD: ICDAR 2017 competition on baseline detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1355\u20131360. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.222"},{"key":"32_CR10","volume-title":"Deep Learning with Keras","author":"A Gulli","year":"2017","unstructured":"Gulli, A., Pal, S.: Deep Learning with Keras. Packt Publishing Ltd., Birmingham (2017)"},{"key":"32_CR11","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. 1, pp. 254\u2013261. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.50"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"He, D., et al.: Multi-scale FCN with cascaded instance aware segmentation for arbitrary oriented word spotting in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3519\u20133528 (2017)","DOI":"10.1109\/CVPR.2017.58"},{"key":"32_CR13","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-030-53036-5_3","volume-title":"Distributed Computing and Artificial Intelligence, 17th International Conference","author":"R Iikura","year":"2021","unstructured":"Iikura, R., Okada, M., Mori, N.: Improving BERT with focal loss for paragraph segmentation of novels. In: Dong, Y., Herrera-Viedma, E., Matsui, K., Omatsu, S., Gonz\u00e1lez Briones, A., Rodr\u00edguez Gonz\u00e1lez, S. (eds.) DCAI 2020. AISC, vol. 1237, pp. 21\u201330. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-53036-5_3"},{"key":"32_CR14","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-981-15-7907-3_7","volume-title":"Computational Methods and Data Engineering","author":"RP Kaur","year":"2021","unstructured":"Kaur, R.P., Jindal, M.K., Kumar, M.: TxtLineSeg: text line segmentation of unconstrained printed text in Devanagari script. In: Singh, V., Asari, V.K., Kumar, S., Patel, R.B. (eds.) Computational Methods and Data Engineering. AISC, vol. 1257, pp. 85\u2013100. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-15-7907-3_7"},{"key":"32_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference for Learning Representations (ICLR) (2015)"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Kosaraju, S.C., et al.: Dot-net: document layout classification using texture-based cnn. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1029\u20131034. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00168"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Lee, J., Hayashi, H., Ohyama, W., Uchida, S.: Page segmentation using a convolutional neural network with trainable co-occurrence features. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1023\u20131028. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00167"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Maia, A.L., Julca-Aguilar, F.D., Hirata, N.S.: A machine learning approach for graph-based page segmentation. In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 424\u2013431. IEEE (2018)","DOI":"10.1109\/SIBGRAPI.2018.00061"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Mechi, O., Mehri, M., Ingold, R., Amara, N.E.B.: Text line segmentation in historical document images using an adaptive U-Net architecture. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 369\u2013374. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00066"},{"key":"32_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-68793-9_30","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"J Michael","year":"2021","unstructured":"Michael, J., Weidemann, M., Laasch, B., Labahn, R.: ICPR 2020 competition on text block segmentation on a newseye dataset. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12668, pp. 405\u2013418. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68793-9_30"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Naoum, A., Nothman, J., Curran, J.: Article segmentation in digitised newspapers with a 2D Markov model. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1007\u20131014. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00165"},{"issue":"11","key":"32_CR23","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/34.244677","volume":"15","author":"L O\u2019Gorman","year":"1993","unstructured":"O\u2019Gorman, L.: The document spectrum for page layout analysis. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1162\u20131173 (1993)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR24","unstructured":"Oktay, O., et al.: Attention U-Net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)"},{"key":"32_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"32_CR26","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s10844-020-00600-1","volume":"55","author":"CY Shiah","year":"2020","unstructured":"Shiah, C.Y.: Content-based document image retrieval based on document modeling. J. Intell. Inf. Syst. 55, 287\u2013306 (2020)","journal-title":"J. Intell. Inf. Syst."},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Vidal, E., et al.: The Carabela project and manuscript collection: large-scale probabilistic indexing and content-based classification. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 85\u201390. IEEE (2020)","DOI":"10.1109\/ICFHR2020.2020.00026"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86159-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:03:18Z","timestamp":1756850598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86159-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030861582","9783030861599"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86159-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","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":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","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":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"Additionally, 13 competition reports are included.","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)"}}]}}