{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:22:29Z","timestamp":1780464149085,"version":"3.54.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031059803","type":"print"},{"value":"9783031059810","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-05981-0_21","type":"book-chapter","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T12:02:50Z","timestamp":1652097770000},"page":"261-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Exploiting Spatial Attention and\u00a0Contextual Information for\u00a0Document Image Segmentation"],"prefix":"10.1007","author":[{"given":"Yuman","family":"Sang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifeng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangrui","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghui","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,10]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Alberti, M., Bouillon, M., Ingold, R., Liwicki, M.: Open evaluation tool for layout analysis of document images. In: ICDAR, vol. 4, pp. 43\u201347. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.311"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Clausner, C., Papadopoulos, C., Pletschacher, S.: ICDAR2015 competition on recognition of documents with complex layouts-RDCL2015. In: ICDAR, pp. 1151\u20131155. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333941"},{"issue":"12","key":"21_CR3","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."},{"issue":"6","key":"21_CR4","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. 52(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv."},{"key":"21_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":"21_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2016.10.023","volume":"64","author":"S Eskenazi","year":"2017","unstructured":"Eskenazi, S., Gomez-Kr\u00e4mer, P., Ogier, J.M.: A comprehensive survey of mostly textual document segmentation algorithms since 2008. Pattern Recogn. 64, 1\u201314 (2017)","journal-title":"Pattern Recogn."},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Fink, M., Layer, T., Mackenbrock, G., Sprinzl, M.: Baseline detection in historical documents using convolutional U-Nets. In: IAPR International Workshop on Document Analysis Systems, pp. 37\u201342. IEEE (2018)","DOI":"10.1109\/DAS.2018.34"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: CVPR, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"21_CR9","volume-title":"Probabilistic Graphical Models: Principles and Techniques","author":"D Koller","year":"2009","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)"},{"key":"21_CR10","first-page":"109","volume":"24","author":"P Kr\u00e4henb\u00fchl","year":"2011","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. Adv. Neural Inf. Process. Syst. 24, 109\u2013117 (2011)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"21_CR11","unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data (2001)"},{"key":"21_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/978-3-030-57058-3_17","volume-title":"Document Analysis Systems","author":"X-H Li","year":"2020","unstructured":"Li, X.-H., Yin, F., Liu, C.-L.: Page segmentation using convolutional neural network and graphical model. In: Bai, X., Karatzas, D., Lopresti, D. (eds.) DAS 2020. LNCS, vol. 12116, pp. 231\u2013245. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57058-3_17"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Yin, F., Xue, T., Liu, L., Ogier, J.M., Liu, C.: Instance aware document image segmentation using label pyramid networks and deep watershed transformation. In: ICDAR, pp. 514\u2013519. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00088"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Lu, T., Dooms, A.: Probabilistic homogeneity for document image segmentation. Pattern Recogn. 109, 107591 (2021)","DOI":"10.1016\/j.patcog.2020.107591"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Niu, R., Sun, X., Tian, Y., Diao, W., Chen, K., Fu, K.: Hybrid multiple attention network for semantic segmentation in aerial images. IEEE Trans. Geosci. Remote Sensing 60, 1\u201318 (2021)","DOI":"10.1109\/TGRS.2021.3065112"},{"key":"21_CR17","unstructured":"Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. In: ICFHR, pp. 7\u201312. IEEE (2018)"},{"key":"21_CR18","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.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","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Simistira, F., et al.: ICDAR2017 competition on layout analysis for challenging medieval manuscripts. In: ICDAR, vol. 1, pp. 1361\u20131370. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.223"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Lee Giles, C.: 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":"21_CR22","doi-asserted-by":"crossref","unstructured":"Ye, J., Zhang, Y., Liu, C.: Joint training of conditional random fields and neural networks for stroke classification in online handwritten documents. In: ICPR, pp. 3264\u20133269. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7900138"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Yi, X., Gao, L., Liao, Y., Zhang, X., Liu, R., Jiang, Z.: CNN based page object detection in document images. In: ICDAR, vol. 1, pp. 230\u2013235. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.46"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: ICDAR, pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-05981-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T04:08:17Z","timestamp":1727150897000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-05981-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031059803","9783031059810"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-05981-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pakdd.net\/index.html","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"558","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":"121","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":"22% - 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":"3.75","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":"6.45","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)"}}]}}