{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:40:11Z","timestamp":1756852811657,"version":"3.44.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863364"},{"type":"electronic","value":"9783030863371"}],"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\/978-3-030-86337-1_45","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"678-692","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["ICDAR 2021 Competition on\u00a0Components Segmentation Task of\u00a0Document Photos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1356-5759","authenticated-orcid":false,"given":"Celso A. M.","family":"Lopes Junior","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9538-6505","authenticated-orcid":false,"given":"Ricardo B.","family":"das Neves Junior","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8327-9734","authenticated-orcid":false,"given":"Byron L. D.","family":"Bezerra","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6955-9249","authenticated-orcid":false,"given":"Alejandro H.","family":"Toselli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9285-2555","authenticated-orcid":false,"given":"Donato","family":"Impedovo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"issue":"12","key":"45_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The lov\u00e1sz-softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4413\u20134421 (2018)","DOI":"10.1109\/CVPR.2018.00464"},{"key":"45_CR3","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2956516","DOI":"10.1109\/TPAMI.2019.2956516"},{"issue":"4","key":"45_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"45_CR5","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"3","key":"45_CR8","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297\u2013302 (1945)","journal-title":"Ecology"},{"issue":"3","key":"45_CR9","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1109\/TPAMI.2014.2343981","volume":"37","author":"MA Ferrer","year":"2014","unstructured":"Ferrer, M.A., Diaz-Cabrera, M., Morales, A.: Static signature synthesis: A neuromotor inspired approach for biometrics. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 667\u2013680 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"45_CR10","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, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"45_CR11","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Junior, C.A., da Silva, M.H.M., Bezerra, B.L.D., Fernandes, B.J.T., Impedovo, D.: FCN+ RL: a fully convolutional network followed by refinement layers to offline handwritten signature segmentation. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206594"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: Pointrend: image segmentation as rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9799\u20139808 (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Improving semantic segmentation via decoupled body and edge supervision. arXiv preprint arXiv:2007.10035 (2020)","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"45_CR16","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":"45_CR17","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, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Liu, J.J., Hou, Q., Cheng, M.M., Wang, C., Feng, J.: Improving convolutional networks with self-calibrated convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10096\u201310105 (2020)","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150\u20131157. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"das Neves Junior, R.B., Ver\u00e7osa, L.F., Mac\u00eado, D., Bezerra, B.L.D., Zanchettin, C.: A fast fully octave convolutional neural network for document image segmentation. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9206711"},{"issue":"6","key":"45_CR22","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1049\/ip-vis:20031078","volume":"150","author":"J Ortega-Garcia","year":"2003","unstructured":"Ortega-Garcia, J., et al.: MCYT baseline corpus: a bimodal biometric database. IEE Proc.-Vis. Image Signal Process. 150(6), 395\u2013401 (2003)","journal-title":"IEE Proc.-Vis. Image Signal Process."},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-Net: going deeper with nested u-structure for salient object detection. Pattern Recognit. 106, 107404 (2020)","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"45_CR24","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, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"45_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":"45_CR26","doi-asserted-by":"crossref","unstructured":"de S\u00e1 Soares, A., das Neves Junior, R.B., Bezerra, B.L.D.: Bid dataset: a challenge dataset for document processing tasks. In: Anais Estendidos do XXXIII Conference on Graphics, Patterns and Images, pp. 143\u2013146. SBC (2020)","DOI":"10.5753\/sibgrapi.est.2020.12997"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Silva, P.G., Junior, C.A., Lima, E.B., Bezerra, B.L., Zanchettin, C.: Speeding-up the handwritten signature segmentation process through an optimized fully convolutional neural network. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1417\u20131423. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00228"},{"key":"45_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"CH Sudre","year":"2017","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA\/ML-CDS -2017. LNCS, vol. 10553, pp. 240\u2013248. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28"},{"key":"45_CR30","unstructured":"Sun, K., et al.: High-resolution representations for labeling pixels and regions. arxiv 2019. arXiv preprint arXiv:1904.04514 (2019)"},{"key":"45_CR31","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"45_CR32","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"45_CR33","unstructured":"Tao, A., Sapra, K., Catanzaro, B.: Hierarchical multi-scale attention for semantic segmentation. arXiv preprint arXiv:2005.10821 (2020)"},{"key":"45_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"issue":"1","key":"45_CR35","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3390\/rs12010167","volume":"12","author":"S Wei","year":"2020","unstructured":"Wei, S., et al.: Precise and robust ship detection for high-resolution sar imagery based on hr-sdnet. Remote Sens. 12(1), 167 (2020)","journal-title":"Remote Sens."},{"key":"45_CR36","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. arXiv preprint arXiv:1909.11065 (2019)"},{"key":"45_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/978-3-030-58610-2_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Xie, J., Chen, X., Wang, J.: SegFix: model-agnostic boundary refinement for segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 489\u2013506. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_29"},{"key":"45_CR38","unstructured":"Zhang, H., et al.: Resnest: Split-attention networks. arXiv preprint arXiv:2004.08955 (2020)"},{"key":"45_CR39","unstructured":"Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels. arXiv preprint arXiv:1805.07836 (2018)"},{"key":"45_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"45_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Z Zhou","year":"2018","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., Liang, J.: UNet++: a nested u-net architecture for medical image segmentation. In: Stoyanov, D., et al. (eds.) DLMIA\/ML-CDS -2018. LNCS, vol. 11045, pp. 3\u201311. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1"},{"key":"45_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019)","DOI":"10.1109\/CVPR.2019.00953"}],"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\/978-3-030-86337-1_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:11:16Z","timestamp":1756851076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_45","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)"}}]}}