{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:53:26Z","timestamp":1784904806783,"version":"3.55.0"},"reference-count":61,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["2022YFB4500600"],"award-info":[{"award-number":["2022YFB4500600"]}],"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":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"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":["62272144"],"award-info":[{"award-number":["62272144"]}],"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":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}],"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":["72188101"],"award-info":[{"award-number":["72188101"]}],"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":["62272435"],"award-info":[{"award-number":["62272435"]}],"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":["U22A2094"],"award-info":[{"award-number":["U22A2094"]}],"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":["62202139"],"award-info":[{"award-number":["62202139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Anhui Province","award":["202203a05020011"],"award-info":[{"award-number":["202203a05020011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3310332","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T18:06:55Z","timestamp":1693937215000},"page":"5060-5074","source":"Crossref","is-referenced-by-count":24,"title":["Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4215-5464","authenticated-orcid":false,"given":"Sheng","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9446-249X","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132034"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475606"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051756"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475425"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3383-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref10","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350881"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12235"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00136"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413753"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref48","article-title":"COCO-Text: Dataset and benchmark for text detection and recognition in natural images","author":"veit","year":"2016","journal-title":"arXiv 1601 07140"},{"key":"ref47","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.378"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00297"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref49","first-page":"1","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"Proc ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","first-page":"1563","article-title":"ICDAR 2019 competition on scene text visual question answering","author":"biten","year":"2019","journal-title":"Proc of Int Conf Document Analysis Recognition (ICDAR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/423"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref34","author":"krasin","year":"2017","journal-title":"Openimages A public dataset for large-scale multi-label and multi-class image classification"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref36","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Sov Phys Doklady"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01459"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413924"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_40"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.278"},{"key":"ref28","first-page":"1","article-title":"RUArt: A novel text-centered solution for text-based visual question answering","volume":"25","author":"jin","year":"2021","journal-title":"IEEE TMM"},{"key":"ref27","article-title":"Pythia v0.1: The winning entry to the VQA challenge 2018","author":"jiang","year":"2018","journal-title":"arXiv 1807 09956"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16476"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10241306.pdf?arnumber=10241306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:14:11Z","timestamp":1696270451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10241306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3310332","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}