{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:06:09Z","timestamp":1743001569905,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030891879"},{"type":"electronic","value":"9783030891886"}],"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.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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-89188-6_23","type":"book-chapter","created":{"date-parts":[[2021,10,24]],"date-time":"2021-10-24T22:02:23Z","timestamp":1635112943000},"page":"308-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["VTLayout: Fusion of Visual and Text Features for Document Layout Analysis"],"prefix":"10.1007","author":[{"given":"Shoubin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuyan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaiqun","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,25]]},"reference":[{"key":"23_CR1","unstructured":"Abadi, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Asim, M.N., Khan, M.U.G., Malik, M.I., Razzaque, K., Dengel, A., Ahmed, S.: Two stream deep network for document image classification. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1410\u20131416. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00227"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Augusto Borges Oliveira, D., Palhares Viana, M.: Fast CNN-based document layout analysis. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 1173\u20131180 (2017)","DOI":"10.1109\/ICCVW.2017.142"},{"issue":"6","key":"23_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. (CSUR) 52(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"23_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-540-31865-1_25","volume-title":"Advances in Information Retrieval","author":"C Goutte","year":"2005","unstructured":"Goutte, C., Gaussier, E.: A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In: Losada, D.E., Fern\u00e1ndez-Luna, J.M. (eds.) ECIR 2005. LNCS, vol. 3408, pp. 345\u2013359. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/978-3-540-31865-1_25"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Ha, J., Haralick, R.M., Phillips, I.T.: Recursive xy cut using bounding boxes of connected components. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 2, pp. 952\u2013955. IEEE (1995)","DOI":"10.1109\/ICDAR.1995.602059"},{"key":"23_CR8","unstructured":"Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Jain, R., Wigington, C.: Multimodal document image classification. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 71\u201377. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00021"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Kang, L., Kumar, J., Ye, P., Li, Y., Doermann, D.: Convolutional neural networks for document image classification. In: 2014 22nd International Conference on Pattern Recognition, pp. 3168\u20133172. IEEE (2014)","DOI":"10.1109\/ICPR.2014.546"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Kavasidis, I., et al.: A saliency-based convolutional neural network for table and chart detection in digitized documents. arXiv preprint arXiv:1804.06236 (2018)","DOI":"10.1007\/978-3-030-30645-8_27"},{"key":"23_CR13","unstructured":"Keskar, N.S., Socher, R.: Improving generalization performance by switching from Adam to SGD. arXiv preprint arXiv:1712.07628 (2017)"},{"key":"23_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"23_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"Namboodiri, A.M., Jain, A.K.: Document structure and layout analysis. In: Chaudhuri, B.B. (eds.) Digital Document Processing. Advances in Pattern Recognition. Springer, London (2007). https:\/\/doi.org\/10.1007\/978-1-84628-726-8_2","DOI":"10.1007\/978-1-84628-726-8_2"},{"issue":"11","key":"23_CR17","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/34.244677","volume":"15","author":"L O\u2019Gorman","year":"1993","unstructured":"O\u2019Gorman, L.: The document spectrum for page layout analysis. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1162\u20131173 (1993)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR18","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)"},{"key":"23_CR19","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"23_CR20","doi-asserted-by":"publisher","first-page":"28","DOI":"10.5815\/ijmecs.2012.04.04","volume":"4","author":"S Ray","year":"2012","unstructured":"Ray, S., Chandra, N.: Domain based ontology and automated text categorization based on improved term frequency-inverse document frequency. Int. J. Mod. Educ. Comput. Sci. 4(4), 28 (2012)","journal-title":"Int. J. Mod. Educ. Comput. Sci."},{"key":"23_CR21","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":"23_CR22","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: 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"},{"issue":"11","key":"23_CR24","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Siddiqui, S.A., Khan, P.I., Dengel, A., Ahmed, S.: Rethinking semantic segmentation for table structure recognition in documents. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1397\u20131402. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00225"},{"key":"23_CR26","unstructured":"Soto, C.X., Soto, C.X.: Visual detection with context for document layout analysis. Technical report, Brookhaven National Lab. (BNL), Upton, NY (United States) (2019)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Sun, N., Zhu, Y., Hu, X.: Faster R-CNN based table detection combining corner locating. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1314\u20131319. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00212"},{"key":"23_CR28","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5315\u20135324 (2017)","DOI":"10.1109\/CVPR.2017.462"},{"key":"23_CR29","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":"23_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89188-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T17:35:10Z","timestamp":1725989710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89188-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030891879","9783030891886"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89188-6_23","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":"25 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2021","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":"382","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":"93","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":"28","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":"24% - 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":"5","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)"}}]}}