{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T01:11:44Z","timestamp":1790125904232,"version":"4.0.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3303600"],"award-info":[{"award-number":["2022YFC3303600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62137002"],"award-info":[{"award-number":["62137002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293553"],"award-info":[{"award-number":["62293553"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293554"],"award-info":[{"award-number":["62293554"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192781"],"award-info":[{"award-number":["62192781"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176209"],"award-info":[{"award-number":["62176209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106190"],"award-info":[{"award-number":["62106190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61937001"],"award-info":[{"award-number":["61937001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\u201cLENOVO-XJTU\u201d Intelligent Industry Joint Laboratory Project, Natural Science Basic Research Program of Shaanxi","award":["2023-JC-YB-593"],"award-info":[{"award-number":["2023-JC-YB-593"]}]},{"name":"Youth Innovation Team of Shaanxi Universities, XJTU Teaching Reform Research Project \u201cAcquisition Learning Based on Knowledge Forest\u201d"},{"name":"Shaanxi Undergraduate and Higher Education Teaching Reform Research Program","award":["23BY195"],"award-info":[{"award-number":["23BY195"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3374511","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:47:40Z","timestamp":1710359260000},"page":"2131-2144","source":"Crossref","is-referenced-by-count":3,"title":["Alignment Relation is What You Need for Diagram Parsing"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7658-0116","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-8795","authenticated-orcid":false,"given":"Lingling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Technology Research and Development, Xi’an Jiaotong University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7574-3931","authenticated-orcid":false,"given":"Xin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang'an University, Xi’an, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6004-0675","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Technology Research and Development, Xi’an Jiaotong University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5536-6515","authenticated-orcid":false,"given":"Shaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianying","family":"Wang","sequence":"additional","affiliation":[{"name":"Lenovo Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216771"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3189825"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181511"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1801227"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564428"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref11","first-page":"160","article-title":"Semantic parsing to probabilistic programs for situated question answering","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Krishnamurthy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/228"},{"key":"ref13","first-page":"2263","article-title":"ChartQA: A benchmark for question answering about charts with visual and logical reasoning","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Masry"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475255"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3522689"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref17","first-page":"1","article-title":"Integrating image data extraction and table parsing methods for chart question answering","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Masry"},{"key":"ref18","first-page":"140","article-title":"Learning pipelines with limited data and domain knowledge: A study in parsing physics problems","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Sachan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2707858"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3229631"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref27","first-page":"5469","article-title":"ISAAQ\u2014Mastering textbook questions with pre-trained transformers and bottom-up and top-down attention","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Gomez-Perez"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4324\/9781315009292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref31","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","volume-title":"Proc. 20th Chin. Nat. Conf. Comput. Linguist.","author":"Zhuang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00438"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00385"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1347"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref45","first-page":"785","article-title":"RACE: Large-scale reading comprehension dataset from examinations","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Lai"},{"key":"ref46","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv:1803.05457"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10472414.pdf?arnumber=10472414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:01:57Z","timestamp":1725249717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3374511","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}