{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:26:12Z","timestamp":1757611572238,"version":"3.44.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030865481"},{"type":"electronic","value":"9783030865498"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86549-8_1","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6763-4716","authenticated-orcid":false,"given":"Abhishek","family":"Trivedi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4134-1154","authenticated-orcid":false,"given":"Ravi Kiran","family":"Sarvadevabhatla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Acuna, D., et al.: Efficient interactive annotation of segmentation datasets with Polygon-RNN++. In: CVPR, pp. 859\u2013868 (2018)","DOI":"10.1109\/CVPR.2018.00096"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Bonechi, S., Andreini, P., et al.: COCO$$\\_$$TS dataset: pixel-level annotations based on weak supervision for scene text segmentation. In: ICANN, pp. 238\u2013250 (2019)","DOI":"10.1007\/978-3-030-30508-6_20"},{"key":"1_CR3","first-page":"733","volume":"01","author":"TM Breuel","year":"2017","unstructured":"Breuel, T.M.: Robust, simple page segmentation using hybrid convolutional MDLSTM networks. ICDAR 01, 733\u2013740 (2017)","journal-title":"ICDAR"},{"key":"1_CR4","unstructured":"Buss, J.F., Rosenberg, A.L., Knott, J.D.: Vertex types in book-embeddings. Tech. rep., Amherst, MA, USA (1987)"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/978-3-030-00889-5_27","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"YB Can","year":"2018","unstructured":"Can, Y.B., Chaitanya, K., Mustafa, B., Koch, L.M., Konukoglu, E., Baumgartner, C.F.: Learning to segment medical images with scribble-supervision alone. In: Stoyanov, D., et al. (eds.) DLMIA\/ML-CDS -2018. LNCS, vol. 11045, pp. 236\u2013244. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00889-5_27"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Clausner, C., Antonacopoulos, A., Derrick, T., Pletschacher, S.: ICDAR 2019 competition on recognition of early Indian printed documents-REID2019. In: ICDAR, pp. 1527\u20131532 (2019)","DOI":"10.1109\/ICDAR.2019.00246"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Dong, Z., Zhang, R., Shao, X.: Automatic annotation and segmentation of object instances with deep active curve network. IEEE Access 7, 147501\u2013147512 (2019)","DOI":"10.1109\/ACCESS.2019.2946650"},{"key":"1_CR8","unstructured":"Fu, J., Liu, J., Wang, Y., Zhou, J., Wang, C., Lu, H.: Stacked deconvolutional network for semantic segmentation. In: IEEE TIP (2019)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Garz, A., Seuret, M., Simistira, F., Fischer, A., Ingold, R.: Creating ground truth for historical manuscripts with document graphs and scribbling interaction. In: DAS, pp. 126\u2013131 (2016)","DOI":"10.1109\/DAS.2016.29"},{"key":"1_CR10","unstructured":"Gur, S., Shaharabany, T., Wolf, L.: End to end trainable active contours via differentiable rendering. In: ICLR (2020)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Gurjar, N., Sudholt, S., Fink, G.A.: Learning deep representations for word spotting under weak supervision. In: DAS, pp. 7\u201312 (2018)","DOI":"10.1109\/DAS.2018.35"},{"key":"1_CR12","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: ICDAR (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"9","key":"1_CR14","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE TPAMI 37(9), 1904\u20131916 (2015)","journal-title":"IEEE TPAMI"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Kassis, M., El-Sana, J.: Scribble based interactive page layout segmentation using Gabor filter. In: ICFHR, pp. 13\u201318 (2016)","DOI":"10.1109\/ICFHR.2016.0016"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Kassis, M., Abdalhaleem, A., Droby, A., Alaasam, R., El-Sana, J.: VML-HD: the historical Arabic documents dataset for recognition systems. In: 1st International Workshop on Arabic Script Analysis and Recognition, pp. 11\u201314. IEEE (2017)","DOI":"10.1109\/ASAR.2017.8067751"},{"issue":"2","key":"1_CR17","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3390\/jimaging4020043","volume":"4","author":"MWA Kesiman","year":"2018","unstructured":"Kesiman, M.W.A., et al.: Benchmarking of document image analysis tasks for palm leaf manuscripts from Southeast Asia. J. Imaging 4(2), 43 (2018)","journal-title":"J. Imaging"},{"key":"1_CR18","unstructured":"Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)"},{"key":"1_CR19","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)"},{"key":"1_CR20","unstructured":"Klette, R., Rosenfeld, A. (eds.): Digital Geometry. The Morgan Kaufmann Series in Computer Graphics. Morgan Kaufmann, San Francisco (2004)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Lais Wiggers, K., de Souza Britto Junior, A., Lameiras Koerich, A., Heutte, L., Soares de Oliveira, L.E.: Deep learning approaches for image retrieval and pattern spotting in ancient documents. arXiv e-prints (2019)","DOI":"10.1109\/IJCNN.2019.8852197"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Li, G., Muller, M., Thabet, A., Ghanem, B.: DeepGCNs: can GCNs go as deep as CNNs? In: ICCV, pp. 9267\u20139276 (2019)","DOI":"10.1109\/ICCV.2019.00936"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Ling, H., Gao, J., Kar, A., Chen, W., Fidler, S.: Fast interactive object annotation with curve-GCN. In: CVPR, pp. 5257\u20135266 (2019)","DOI":"10.1109\/CVPR.2019.00540"},{"key":"1_CR25","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Ma, L., Long, C., Duan, L., Zhang, X., Li, Y., Zhao, Q.: Segmentation and recognition for historical Tibetan document images. IEEE Access 8, 52641\u201352651 (2020)","DOI":"10.1109\/ACCESS.2020.2975023"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Marcos, D., Tuia, D., et al.: Learning deep structured active contours end-to-end. In: CVPR, pp. 8877\u20138885 (2018)","DOI":"10.1109\/CVPR.2018.00925"},{"key":"1_CR28","unstructured":"Oktay, O., et al.: Attention U-Net: learning where to look for the pancreas. In: Medical Imaging with Deep Learning (2018)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Pal, K., Terras, M., Weyrich, T.: 3D reconstruction for damaged documents: imaging of the great parchment book. In: Frinken, V., Barrett, B., Manmatha, R., M\u00e4rgner, V. (eds.) HIP@ICDAR 2013, pp. 14\u201321. ACM (2013)","DOI":"10.1145\/2501115.2501125"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Prusty, A., Aitha, S., Trivedi, A., Sarvadevabhatla, R.K.: Indiscapes: instance segmentation networks for layout parsing of historical Indic manuscripts. In: ICDAR, pp. 999\u20131006 (2019)","DOI":"10.1109\/ICDAR.2019.00164"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Ribera, J., G\u00fcera, D., Chen, Y., Delp, E.J.: Locating objects without bounding boxes. In: CVPR, June 2019","DOI":"10.1109\/CVPR.2019.00664"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Saini, R., Dobson, D., et al.: ICDAR 2019 historical document reading challenge on large structured Chinese family records. In: ICDAR, pp. 1499\u20131504 (2019)","DOI":"10.1109\/ICDAR.2019.00241"},{"issue":"4","key":"1_CR33","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1073\/pnas.93.4.1591","volume":"93","author":"JA Sethian","year":"1996","unstructured":"Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. PNAS 93(4), 1591\u20131595 (1996)","journal-title":"PNAS"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., et al.: An open approach towards benchmarking of table structure recognition systems. In: DAS, pp. 113\u2013120 (2010)","DOI":"10.1145\/1815330.1815345"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Simistira, F., Seuret, M., Eichenberger, N., Garz, A., Liwicki, M., Ingold, R.: DIVA-HisDB: a precisely annotated large dataset of challenging medieval manuscripts. In: ICFHR, pp. 471\u2013476 (2016)","DOI":"10.1109\/ICFHR.2016.0093"},{"key":"1_CR36","unstructured":"Slimane, F., Ingold, R., Kanoun, S., Alimi, A.M., Hennebert, J.: Database and evaluation protocols for Arabic printed text recognition. DIUF-University of Fribourg-Switzerland (2009)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., Wang, L.: Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: CVPR, pp. 3136\u20133145 (2019)","DOI":"10.1109\/CVPR.2019.00325"},{"key":"1_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/978-3-030-01270-0_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Tang","year":"2018","unstructured":"Tang, M., Perazzi, F., Djelouah, A., Ayed, I.B., Schroers, C., Boykov, Y.: On regularized losses for weakly-supervised CNN segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 524\u2013540. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_31"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Wiggers, K.L., Junior, A.S.B., Koerich, A.L., Heutte, L., de Oliveira, L.E.S.: Deep learning approaches for image retrieval and pattern spotting in ancient documents. ArXiv abs\/1907.09404 (2019)","DOI":"10.1109\/IJCNN.2019.8852197"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Yalniz, I.Z., Manmatha, R.: A fast alignment scheme for automatic OCR evaluation of books. In: ICDAR, pp. 754\u2013758 (2011)","DOI":"10.1109\/ICDAR.2011.157"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: CVPR, pp. 5315\u20135324 (2017)","DOI":"10.1109\/CVPR.2017.462"},{"key":"1_CR42","unstructured":"Zhang, L., Song, H., Lu, H.: Graph node-feature convolution for representation learning. arXiv preprint arXiv:1812.00086 (2018)"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Jimeno Yepes, A.: PubLayNet: largest dataset ever for document layout analysis. In: ICDAR, pp. 1015\u20131022 (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, J., Guo, B., Zheng, Y.: Document image retrieval based on convolutional neural network. In: Advances in Intelligent Information Hiding and Multimedia Signal Processing, pp. 221\u2013229 (2020)","DOI":"10.1007\/978-981-13-9714-1_24"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86549-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:04:33Z","timestamp":1756937073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86549-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865481","9783030865498"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86549-8_1","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)"}}]}}