{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T18:24:49Z","timestamp":1769279089602,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100019550","name":"Scheme for Promotion of Academic and Research Collaboration (SPARC), Ministry of Human Resource Development (MHRD), Government of India","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019550","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3186471","type":"journal-article","created":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:36:23Z","timestamp":1656362183000},"page":"72092-72106","source":"Crossref","is-referenced-by-count":4,"title":["EKTVQA: Generalized Use of External Knowledge to Empower Scene Text in Text-VQA"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8392-1574","authenticated-orcid":false,"given":"Arka Ujjal","family":"Dey","sequence":"first","affiliation":[{"name":"IIT Jodhpur, Rajasthan, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ernest","family":"Valveny","sequence":"additional","affiliation":[{"name":"Computer Vision Center, Universitat Autònoma de Barcelona, Bellaterra, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav","family":"Harit","sequence":"additional","affiliation":[{"name":"IIT Jodhpur, Rajasthan, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.06.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3440756"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00470"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00356"},{"key":"ref16","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_41"},{"key":"ref19","article-title":"Structured multimodal attentions for TextVQA","author":"Gao","year":"2020","journal-title":"arXiv:2006.00753"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00864"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref26","first-page":"86","article-title":"Representing general relational knowledge in ConceptNet 5","volume-title":"Proc. LREC","author":"Speer"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"issue":"2","key":"ref29","first-page":"5","article-title":"Image question answering: A visual semantic embedding model and a new dataset","volume":"1","author":"Ren","year":"2015","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"ref31","first-page":"2659","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst., (NeurIPS)","author":"Narasimhan"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref33","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413924"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.278"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1805986.1806020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.378"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"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":"ref49","first-page":"1","article-title":"Pythia\u2014A platform for vision & language research","volume-title":"Proc. SysML Workshop, (NeurIPS)","author":"Singh"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref51","article-title":"C-VQA: A compositional split of the visual question answering (VQA) v1.0 dataset","author":"Agrawal","year":"2017","journal-title":"arXiv:1704.08243"},{"key":"ref52","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09807310.pdf?arnumber=9807310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:35:51Z","timestamp":1706762151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9807310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3186471","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}