{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:44:30Z","timestamp":1756309470636,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755967"},{"type":"electronic","value":"9789819755974"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5597-4_29","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T09:10:06Z","timestamp":1722503406000},"page":"338-353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Fusion Framework of Whitespace Smear Cutting and Swin Transformer for Document Layout Analysis"],"prefix":"10.1007","author":[{"given":"Ran","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo-Ku","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,2]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Saha, R., Mondal, A., Jawahar, C.: Graphical object detection in document images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 51\u201358. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00018"},{"issue":"6","key":"29_CR2","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1109\/TPAMI.2007.70837","volume":"30","author":"F Shafait","year":"2008","unstructured":"Shafait, F., Keysers, D., Breuel, T.: Performance evaluation and benchmarking of six-page segmentation algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 30(6), 941\u2013954 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR3","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":"29_CR4","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 \u2014 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":"29_CR5","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6399\u20136408 (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"29_CR6","unstructured":"Vaswani, A., et al.: Attention is all you need (2023)"},{"key":"29_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin trans- former: Hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Li, X.H., Yin, F., Liu, C.L.: Page object detection from pdf document images by deep structured prediction and supervised clustering. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3627\u20133632. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546073"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: Publaynet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Oliveira,S.A., Seguin,B., Kaplan,F.: dhsegment: Agenericdeep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7\u201312. IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Wick, C., Puppe, F.: Fully convolutional neural networks for page segmentation of historical document images. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 287\u2013292. IEEE (2018)","DOI":"10.1109\/DAS.2018.39"},{"key":"29_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-319-95957-3_30","volume-title":"Intelligent Computing Methodologies","author":"Y Li","year":"2018","unstructured":"Li, Y., Zou, Y., Ma, J.: Deeplayout: a semantic segmentation approach to page layout analysis. In: Huang, D.-S., Gromiha, M.M., Han, K., Hussain, A. (eds.) ICIC 2018. LNCS (LNAI), vol. 10956, pp. 266\u2013277. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-95957-3_30"},{"key":"29_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-030-84522-3_40","volume-title":"Intelligent Computing Theories and Application","author":"Y Zou","year":"2021","unstructured":"Zou, Y., Ma, J.: Deep learning based semantic page segmentation of document images in chinese and english. In: Huang, D.-S., Jo, K.-H., Li, J., Gribova, V., Bevilacqua, V. (eds.) ICIC 2021. LNCS, vol. 12836, pp. 484\u2013498. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-84522-3_40"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: Doclaynet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 3743\u20133751 (2022)","DOI":"10.1145\/3534678.3539043"},{"key":"29_CR16","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018, pp. 432\u2013448. Springer International Publishing, Cham (2018)"},{"key":"29_CR17","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":"29_CR18","doi-asserted-by":"crossref","unstructured":"Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: Icdar2017 competition on page object detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1417\u20131422. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.231"},{"key":"29_CR19","unstructured":"Hang, L.: CDLA: A Chinese document layout analysis (CDLA) dataset. https:\/\/github.com\/buptlihang\/CDLA\/ (2021)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Cheng, H., et al.: M6doc: a large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15138\u201315147 (2023)","DOI":"10.1109\/CVPR52729.2023.01453"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Schmitt-Koopmann, F.M., Huang, E.M., Hutter, H.P., Stadelmann, T., Darvishy, A.: Formulanet: a benchmark dataset for mathematical formula detection. IEEE Access 10, 91588\u201391596 (2022)","DOI":"10.1109\/ACCESS.2022.3202639"},{"key":"29_CR22","unstructured":"Zou, Y.: On deep learning based structure analysis and recognition in document images. PhD Thesis, Peking University, 2022.7 https:\/\/drm.lib.pku.edu.cn\/pdfindex1.jsp?fid=9bde8c325dd4cd894400a28b25089e14. Accessed 20 Mar 2024"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5597-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T13:14:59Z","timestamp":1732540499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5597-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755967","9789819755974"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5597-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}