{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:31:14Z","timestamp":1742913074437,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030669058"},{"type":"electronic","value":"9783030669065"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-66906-5_21","type":"book-chapter","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T14:29:33Z","timestamp":1611325773000},"page":"225-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MSNet: A Multi-scale Segmentation Network for Documents Layout Analysis"],"prefix":"10.1007","author":[{"given":"Bo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bailing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,23]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Xu, Y., Yin F., Zhang Z.X., et al.: Page segmentation for historical handwritten documents using fully convolutional networks. In: 27th International Joint Conference on Artificial Intelligence, pp. 1057\u20131063. IEEE Computer Society, Kyoto (2017)","DOI":"10.24963\/ijcai.2018\/147"},{"issue":"7","key":"21_CR2","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"21_CR4","doi-asserted-by":"publisher","unstructured":"Badrinarayanan, V., Kendal, L.A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017). https:\/\/doi.org\/10.1109\/tpami.2016.2644615","DOI":"10.1109\/tpami.2016.2644615"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) Medical Image Computing and Computer-Assisted Intervention, MICCAI 2015. MICCAI 2015. LNCS, vol 9351. pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"21_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., et al.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR7","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., et al.: Rethinking atrous convolution for semantic image segmentation. arXiv (2017). https:\/\/arxiv.org\/abs\/1706.05587"},{"key":"21_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR10","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: 30th Neural Information Processing Systems, pp. 6000\u20136010. Curran Associates, Long Beach (2017)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., et al.: Dual attention network for scene segmentation. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154. IEEE, Long Beach (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., et al.: Squeeze-and-excitation networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141. IEEE, Salt Lake City (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"21_CR13","unstructured":"Simonyan, k., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv (2015), https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., et al.: Pyramid scene parsing network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6230\u20136239. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., et al.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1926\u20131934. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.549"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., et al.: Context encoding for semantic segmentation. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 7151\u20137160. IEEE, Salt Lake City (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"21_CR17","unstructured":"Yu, F., Koltun, V.: Multi-Scale Context Aggregation by Dilated Convolutions. arXiv (2016). https:\/\/arxiv.org\/abs\/1511.07122"},{"key":"21_CR18","unstructured":"Li, H., Xiong, P., An, J., et al.: Pyramid attention network for semantic segmentation. arXiv (2018). https:\/\/arxiv.org\/abs\/1805.10180"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., et al.: Learning a discriminative feature network for semantic segmentation. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1857\u20131866. IEEE, Salt Lake City (2018)","DOI":"10.1109\/CVPR.2018.00199"},{"key":"21_CR20","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., et al.: Attention U-Net: learning where to look for the pancreas. arXiv (2018). https:\/\/arxiv.org\/abs\/1804.03999"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., et al.: Deep high-resolution representation learning for human pose estimation. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703. IEEE, Long Beach (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"21_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-030-01261-8_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yu","year":"2018","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334\u2013349. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_20"},{"key":"21_CR23","unstructured":"Yu, C., Gao, C., Wang, J., et al.: BiSeNet v2: bilateral network with guided aggregation for real-time semantic segmentation. arXiv (2020). https:\/\/arxiv.org\/abs\/2004.02147"},{"key":"21_CR24","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. arXiv (2019). https:\/\/arxiv.org\/abs\/1908.07836"},{"key":"21_CR25","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: 28th International Conference on Neural Information Processing Systems, pp. 91\u201399. Curran Associates, Montreal (2015)"},{"issue":"2","key":"21_CR26","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2018","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et al.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386\u2013397 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR27","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv (2018). https:\/\/arxiv.org\/abs\/1804.02767"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Gilani, A., Qasim, S.R., Malik, I., et al.: Table detection using deep learning. In: 14th IAPR International Conference on Document Analysis and Recognition, pp. 771\u2013776. IEEE, Kyoto (2017)","DOI":"10.1109\/ICDAR.2017.131"},{"key":"21_CR29","unstructured":"Tensmeyer, C., Davis, B., Wigington, C., et al.: PageNet: page boundary extraction in historical handwritten documents. arXiv (2017). https:\/\/arxiv.org\/abs\/1709.01618"},{"issue":"1","key":"21_CR30","first-page":"99","volume":"85","author":"TA Tuan","year":"2017","unstructured":"Tuan, T.A., Oh, K., Na, I.S., et al.: A robust system for document layout analysis using multilevel homogeneity structure. Expert Syst. Appl. 85(1), 99\u2013113 (2017)","journal-title":"Expert Syst. Appl."},{"key":"21_CR31","unstructured":"Oliveira, D.A.B., Viana, M.P.: Fast CNN-based document layout analysis. In: 2017 IEEE Conference on International Conference on Computer Vision, pp. 1173\u20131180. IEEE, Venice (2017)"},{"key":"21_CR32","unstructured":"Howard, A.G., Zhu, M., Chen, B., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv (2017). https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Dollar, P., et al.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., et al.: DenseASPP for semantic segmentation in street scenes. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3684\u20133692. IEEE, Salt Lake City (2018)","DOI":"10.1109\/CVPR.2018.00388"}],"container-title":["Lecture Notes in Computer Science","Learning Technologies and Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66906-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T14:57:16Z","timestamp":1611327436000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-66906-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030669058","9783030669065"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66906-5_21","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":"23 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SETE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Emerging Technologies for Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sete2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icwl.org.cn\/Sete.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"56","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":"23","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":"15","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":"41% - 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":"3","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}