{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:40:14Z","timestamp":1756852814904,"version":"3.44.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863333"},{"type":"electronic","value":"9783030863340"}],"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\/978-3-030-86334-0_44","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:16:02Z","timestamp":1630700162000},"page":"676-691","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Machine Understanding of\u00a0Human Intent in Charts"],"prefix":"10.1007","author":[{"given":"Sihang","family":"Wu","sequence":"first","affiliation":[]},{"given":"Canyu","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Yuhao","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Guozhi","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Qianying","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Jiapeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bangdong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xinfeng","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Yichao","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Araujo, T., Chagas, P., Alves, J., Santos, C., Santos, B., Meiguins, B.: A real-world approach on the problem of chart recognition using classification, detection and perspective correction. Sensors 20, 4370 (2020)","DOI":"10.3390\/s20164370"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Baji\u0107, F., Job, J., Nenadi\u0107, K.: Chart classification using simplified VGG model. In: IWSSIP, pp. 229\u2013233 (2019)","DOI":"10.1109\/IWSSIP.2019.8787299"},{"key":"44_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-319-51811-4_2","volume-title":"MultiMedia Modeling","author":"F B\u00f6schen","year":"2017","unstructured":"B\u00f6schen, F., Scherp, A.: A comparison of approaches for automated text extraction from scholarly figures. In: Amsaleg, L., Gu\u00f0mundsson, G.\u00de, Gurrin, C., J\u00f3nsson, B.\u00de, Satoh, S. (eds.) MMM 2017. LNCS, vol. 10132, pp. 15\u201327. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-51811-4_2"},{"key":"44_CR4","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and instance segmentation. TPAMI, 1 (2019)"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: ICCV, pp. 5076\u20135084 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Man\u00e9, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: CVPR, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Davila, K., et al.: ICDAR 2019 competition on harvesting raw tables from infographics (chart-infographics). In: ICDAR, pp. 1594\u20131599 (2019)","DOI":"10.1109\/ICDAR.2019.00203"},{"key":"44_CR8","unstructured":"Davila, K., Setlur, S., Doermann, D., Bhargava, U.K., Govindaraju, V.: Chart mining: a survey of methods for automated chart analysis. TPAMI, 1 (2020)"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Davila, K., Tensmeyer, C., Shekhar, S., Singhand, H., Setlur, S., Govindaraju, V.: ICPR 2020 - competition on harvesting raw tables from infographics (chart-infographics). In: Pattern Recognition. ICPR International Workshops and Challenges, pp. 361\u2013380 (2021)","DOI":"10.1007\/978-3-030-68793-9_27"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., Cai, D.: PixelLink: detecting scene text via instance segmentation. In: AAAI, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12269"},{"issue":"1","key":"44_CR11","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/361237.361242","volume":"15","author":"RO Duda","year":"1972","unstructured":"Duda, R.O., Hart, P.E.: Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM 15(1), 11\u201315 (1972)","journal-title":"Commun. ACM"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Doll\u00e1r, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: CVPR, pp. 5351\u20135359 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"44_CR17","unstructured":"Jia, X., et al.: Highly scalable deep learning training system with mixed-precision: training imagenet in four minutes. arXiv preprint arXiv:1807.11205 (2018)"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lu, X., Qin, Y., Tang, Z., Xu, J.: Review of chart recognition in document images. Opt. Eng. 8654, 865410 (2013)","DOI":"10.1117\/12.2008467"},{"key":"44_CR20","first-page":"120","volume":"44","author":"H Mei","year":"2018","unstructured":"Mei, H., Ma, Y., Wei, Y., Chen, W.: The design space of construction tools for information visualization: a survey. Int. J. Comput. Vis. 44, 120\u2013132 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Poco, J., Heer, J.: Reverse-engineering visualizations: recovering visual encodings from chart images. Comput. Graph Forum. 36, 353\u2013363 (2017)","DOI":"10.1111\/cgf.13193"},{"issue":"2","key":"44_CR22","first-page":"57","volume":"25","author":"HC Purchase","year":"2014","unstructured":"Purchase, H.C.: Twelve years of diagrams research. Int. J. Comput. Vis. 25(2), 57\u201375 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"44_CR23","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) NIPS, pp. 91\u201399 (2015)"},{"issue":"11","key":"44_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. TPAMI 39(11), 2298\u20132304 (2016)","journal-title":"TPAMI"},{"key":"44_CR25","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: ICDAR, vol. 2, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"44_CR28","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.sigpro.2015.09.027","volume":"124","author":"B Tang","year":"2016","unstructured":"Tang, B., et al.: DeepChart: combining deep convolutional networks and deep belief networks in chart classification. Signal Process. 124, 156\u2013161 (2016)","journal-title":"Signal Process."},{"key":"44_CR29","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: KDD, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"}],"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\/978-3-030-86334-0_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:07:40Z","timestamp":1756850860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86334-0_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863333","9783030863340"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86334-0_44","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)"}}]}}