{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:29:27Z","timestamp":1777487367351,"version":"3.51.4"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031702389","type":"print"},{"value":"9783031702396","type":"electronic"}],"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\/978-3-031-70239-6_4","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T06:02:09Z","timestamp":1726725729000},"page":"47-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Text Role Classification in\u00a0Scientific Charts Using Multimodal Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9582-2670","authenticated-orcid":false,"given":"Hye Jin","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-6480","authenticated-orcid":false,"given":"Nicolas","family":"Lell","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2653-9245","authenticated-orcid":false,"given":"Ansgar","family":"Scherp","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Al-Zaidy, R.A., Giles, C.L.: A machine learning approach for semantic structuring of scientific charts in scholarly documents. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 4644\u20134649. AAAI Press (2017). http:\/\/aaai.org\/ocs\/index.php\/IAAI\/IAAI17\/paper\/view\/14275","DOI":"10.1609\/aaai.v31i2.19088"},{"key":"4_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4277-0_4","volume-title":"Document Layout Analysis","author":"S Bhowmik","year":"2023","unstructured":"Bhowmik, S.: Document region classification. In: Bhowmik, S. (ed.) Document Layout Analysis. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-4277-0_4"},{"issue":"22","key":"4_CR3","doi-asserted-by":"publisher","first-page":"29475","DOI":"10.1007\/s11042-018-6162-7","volume":"77","author":"F B\u00f6schen","year":"2018","unstructured":"B\u00f6schen, F., Beck, T., Scherp, A.: Survey and empirical comparison of different approaches for text extraction from scholarly figures. Multimed. Tools Appl. 77(22), 29475\u201329505 (2018). https:\/\/doi.org\/10.1007\/s11042-018-6162-7","journal-title":"Multimed. Tools Appl."},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"B\u00f6schen, F., Scherp, A.: Multi-oriented text extraction from information graphics. In: DocEng 2015. ACM (2015). https:\/\/doi.org\/10.1145\/2682571.2797092","DOI":"10.1145\/2682571.2797092"},{"key":"4_CR5","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR 2018, pp. 6154\u20136162. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644. http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/html\/Cai_Cascade_R-CNN_Delving_CVPR_2018_paper.html","DOI":"10.1109\/CVPR.2018.00644"},{"key":"4_CR6","doi-asserted-by":"publisher","unstructured":"Davila, K., et al.: ICDAR 2019 competition on harvesting raw tables from infographics (chart-infographics). In: 2019 International Conference on Document Analysis and Recognition, ICDAR 2019, pp. 1594\u20131599. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00203","DOI":"10.1109\/ICDAR.2019.00203"},{"issue":"11","key":"4_CR7","doi-asserted-by":"publisher","first-page":"3799","DOI":"10.1109\/TPAMI.2020.2992028","volume":"43","author":"K Davila","year":"2021","unstructured":"Davila, K., Setlur, S., Doermann, D.S., Kota, B.U., Govindaraju, V.: Chart mining: a survey of methods for automated chart analysis. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3799\u20133819 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2992028","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-030-68793-9_27","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"K Davila","year":"2021","unstructured":"Davila, K., Tensmeyer, C., Shekhar, S., Singh, H., Setlur, S., Govindaraju, V.: ICPR 2020 - competition on harvesting raw tables from infographics. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12668, pp. 361\u2013380. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68793-9_27"},{"key":"4_CR9","doi-asserted-by":"publisher","unstructured":"Davila, K., Xu, F., Ahmed, S., Mendoza, D.A., Setlur, S., Govindaraju, V.: ICPR 2022: challenge on harvesting raw tables from infographics (chart-infographics). In: 26th International Conference on Pattern Recognition, pp. 4995\u20135001. IEEE (2022). https:\/\/doi.org\/10.1109\/ICPR56361.2022.9956289","DOI":"10.1109\/ICPR56361.2022.9956289"},{"key":"4_CR10","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019, pp. 4171\u20134186. ACL (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"4_CR11","unstructured":"Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. CoRR (2017). http:\/\/arxiv.org\/abs\/1708.04552"},{"key":"4_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: ICLR 2021. OpenReview.net (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"4_CR13","doi-asserted-by":"publisher","unstructured":"Fu, J., et al.: CMA-CLIP: cross-modality attention clip for text-image classification. In: 2022 IEEE International Conference on Image Processing, ICIP, pp. 2846\u20132850. IEEE (2022). https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897323","DOI":"10.1109\/ICIP46576.2022.9897323"},{"issue":"2","key":"4_CR14","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1017\/S1351324922000110","volume":"29","author":"A Hamdi","year":"2023","unstructured":"Hamdi, A., Pontes, E.L., Sidere, N., Coustaty, M., Doucet, A.: In-depth analysis of the impact of OCR errors on named entity recognition and linking. Nat. Lang. Eng. 29(2), 425\u2013448 (2023). https:\/\/doi.org\/10.1017\/S1351324922000110","journal-title":"Nat. Lang. Eng."},{"key":"4_CR15","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: ICCV 2017, pp. 2980\u20132988. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR16","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR 2016, pp. 770\u2013778. IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR17","doi-asserted-by":"publisher","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: MM 2022, pp. 4083\u20134091. ACM (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"4_CR18","unstructured":"Kiela, D., Bhooshan, S., Firooz, H., Testuggine, D.: Supervised multimodal bitransformers for classifying images and text. CoRR (2019). http:\/\/arxiv.org\/abs\/1909.02950"},{"issue":"3","key":"4_CR19","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1111\/cgf.13193","volume":"36","author":"J Poco","year":"2017","unstructured":"Poco, J., Heer, J.: Reverse-engineering visualizations: recovering visual encodings from chart images. Comput. Graph. Forum 36(3), 353\u2013363 (2017). https:\/\/doi.org\/10.1111\/cgf.13193","journal-title":"Comput. Graph. Forum"},{"key":"4_CR20","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021. PMLR (2021). http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Rezaei-Dastjerdehei, M.R., Mijani, A., Fatemizadeh, E.: Addressing imbalance in multi-label classification using weighted cross entropy loss function. In: 2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME), pp. 333\u2013338. IEEE (2020)","DOI":"10.1109\/ICBME51989.2020.9319440"},{"key":"4_CR22","doi-asserted-by":"publisher","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. CoRR (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.02623","DOI":"10.48550\/arXiv.2212.02623"},{"key":"4_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-030-68793-9_28","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"C Wang","year":"2021","unstructured":"Wang, C., Cui, K., Zhang, S., Xu, C.: Visual and textual information fusion method for chart recognition. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12668, pp. 381\u2013389. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68793-9_28"},{"key":"4_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1007\/978-3-030-86334-0_44","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"S Wu","year":"2021","unstructured":"Wu, S., et al.: Improving machine understanding of\u00a0human intent in charts. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12823, pp. 676\u2013691. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_44"},{"key":"4_CR25","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: ACL\/IJCNLP 2021, pp. 2579\u20132591. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.201","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"4_CR26","doi-asserted-by":"publisher","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 2020, pp. 1192\u20131200. ACM (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"4_CR27","doi-asserted-by":"publisher","unstructured":"Yan, P., Ahmed, S., Doermann, D.S.: Context-aware chart element detection. CoRR (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.04151","DOI":"10.48550\/arXiv.2305.04151"},{"key":"4_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1007\/11669487_29","volume-title":"Document Analysis Systems VII","author":"L Yang","year":"2006","unstructured":"Yang, L., Huang, W., Tan, C.L.: Semi-automatic ground truth generation for chart image recognition. In: Bunke, H., Spitz, A.L. (eds.) DAS 2006. LNCS, vol. 3872, pp. 324\u2013335. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11669487_29"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70239-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T06:02:42Z","timestamp":1726725762000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70239-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031702389","9783031702396"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70239-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"25 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2024.di.unito.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}