{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:13:39Z","timestamp":1787012019236,"version":"3.56.0"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"School of Engineering, Zurich University of Applied Sciences"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3298050","type":"journal-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T13:51:52Z","timestamp":1690206712000},"page":"76202-76221","source":"Crossref","is-referenced-by-count":24,"title":["Automatic Chart Understanding: A Review"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0551-3214","authenticated-orcid":false,"given":"Ali Mazraeh","family":"Farahani","sequence":"first","affiliation":[{"name":"Artificial Intelligence Department, Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2548-8455","authenticated-orcid":false,"given":"Peyman","family":"Adibi","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Department, Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1902-5895","authenticated-orcid":false,"given":"Mohammad Saeed","family":"Ehsani","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Department, Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans-Peter","family":"Hutter","sequence":"additional","affiliation":[{"name":"School of Computer Science, Zurich University of Applied Sciences (ZHAW), Winterthur, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7402-5206","authenticated-orcid":false,"given":"Alireza","family":"Darvishy","sequence":"additional","affiliation":[{"name":"School of Computer Science, Zurich University of Applied Sciences (ZHAW), Winterthur, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24251\/hicss.2020.512"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31522-0_94"},{"key":"ref3","volume-title":"Mathematical expression recognition using a new deep neural model","author":"Mirkazemy","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202639"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0023-3_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref11","article-title":"Medical image captioning via generative pretrained transformers","author":"Selivanov","year":"2022","journal-title":"arXiv:2209.13983"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992028"},{"key":"ref13","article-title":"Improving language understanding by generative pre-training\u2014GPT","author":"Radford","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10151-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108980"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref20","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. NIPS","author":"Mikolov"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1748\/4\/042060"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-022-00424-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449923"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.264"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/S1471068422000229"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-022-01380-x"},{"key":"ref35","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1284420.1284427"},{"key":"ref40","article-title":"Automated data extraction from scholarly line graphs","volume-title":"Proc. Int. Workshop Graph. Recognit.","author":"Choudhury"},{"key":"ref41","volume-title":"Plot Digitizer","year":"2023"},{"key":"ref42","volume-title":"Auto-Trace","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047247"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2007.385396"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDIM.2011.6093320"},{"key":"ref46","volume-title":"Tesseract: An Open-Source Optical Character Recognition Engine","volume":"159","author":"Kay","year":"2007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cola.2022.101107"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-83500-2_12"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2005.54"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-7166-0_20"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13686"},{"key":"ref52","first-page":"41","article-title":"Abstractive summarization of line graphs from popular media","volume-title":"Proc. Workshop Autom. Summarization Different Genres, Media, Lang.","author":"Greenbacker"},{"key":"ref53","first-page":"595","article-title":"Multimodal neural language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kiros"},{"key":"ref54","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2015","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1158"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref57","article-title":"Aligning where to see and what to tell: Image caption with region-based attention and scene factorization","author":"Jin","year":"2015","journal-title":"arXiv:1506.06272"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093592"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3399715.3399829"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2021.2004347"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/PacificVis48177.2020.1043"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114770"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.08.009"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref71","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3053513"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3135655"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref76","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Welling"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132034"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108455"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2884486"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852427"},{"key":"ref87","first-page":"1","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Hudson"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093269"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_27"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376467"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851830"},{"key":"ref94","article-title":"FigureQA: An annotated figure dataset for visual reasoning","author":"Ebrahimi Kahou","year":"2017","journal-title":"arXiv:1710.07300"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_41"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.277"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/VIS54862.2022.00016"},{"key":"ref98","volume-title":"Bokeh: Python Library for Interactive Visualization"},{"key":"ref99","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107645"},{"key":"ref103","article-title":"Cross-modal and multimodal data analysis based on functional mapping of spectral descriptors and manifold regularization","author":"Behmanesh","year":"2021","journal-title":"arXiv:2105.05631"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3213589"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2022.0676"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10192564.pdf?arnumber=10192564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T10:35:49Z","timestamp":1709289349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10192564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3298050","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}