{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:20:18Z","timestamp":1780053618693,"version":"3.54.0"},"reference-count":62,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076024"],"award-info":[{"award-number":["62076024"]}],"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":["62006018"],"award-info":[{"award-number":["62006018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cheung Kong Scholars Programme of China","award":["FRF-TP-18-010C1"],"award-info":[{"award-number":["FRF-TP-18-010C1"]}]},{"name":"National Major Special Project of China","award":["2018YFB0704301"],"award-info":[{"award-number":["2018YFB0704301"]}]},{"name":"Shunde Graduate Program of University of Science and Technology Beijing","award":["BK19AE011"],"award-info":[{"award-number":["BK19AE011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3120194","type":"journal-article","created":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T19:51:21Z","timestamp":1639511481000},"page":"1-12","source":"Crossref","is-referenced-by-count":32,"title":["RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7990-5544","authenticated-orcid":false,"given":"Zan-Xia","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heran","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5478-7898","authenticated-orcid":false,"given":"Fang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyan","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Industrial Design, School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xiao","sequence":"additional","affiliation":[{"name":"Tencent Technology (Shenzhen) Company Limited, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0023-0220","authenticated-orcid":false,"given":"Xu-Cheng","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.34"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00251"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref18","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref23","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Hudson","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz195"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.05.110"},{"key":"ref27","article-title":"SDNet: Contextualized attention-based deep network for conversational question answering","author":"Zhu","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3009491"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187876"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref31","article-title":"Object relation detection based on one-shot learning","author":"Zhou","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240611"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2933728"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2954750"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6731"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00470"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref39","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref42","article-title":"FusionNet: Fusing via fully-aware attention with application to machine comprehension","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Huang","year":"2018"},{"key":"ref43","article-title":"Pyramid mask text detector","author":"Liu","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref45","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.378"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref52","article-title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","author":"Krasin","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref58","first-page":"2013","article-title":"DarkNet: Open source neural networks in C","author":"Redmon"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09583957.pdf?arnumber=9583957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:05:29Z","timestamp":1705017929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9583957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3120194","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}