{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:56:01Z","timestamp":1784300161749,"version":"3.55.0"},"reference-count":53,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2020AAA0106200"],"award-info":[{"award-number":["2020AAA0106200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936005"],"award-info":[{"award-number":["61936005"]}],"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":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["61872424"],"award-info":[{"award-number":["61872424"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20200037"],"award-info":[{"award-number":["BK20200037"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3097171","type":"journal-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T21:42:01Z","timestamp":1629841321000},"page":"3369-3380","source":"Crossref","is-referenced-by-count":77,"title":["DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8304-680X","authenticated-orcid":false,"given":"Jianyu","family":"Wang","sequence":"first","affiliation":[{"name":"College of Telecommunications & Information Engineering, Nanjing University of Posts, and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"College of Telecommunications & Information Engineering, Nanjing University of Posts, and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969791"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref6","first-page":"1031","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Proc. NeurIPS","author":"Yi","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240563"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229971"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref25","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref31","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350923"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref35","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao","year":"2018"},{"key":"ref36","article-title":"Clevrer: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi","year":"2019"},{"key":"ref37","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-038"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350969"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref44","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velikovi","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403177"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273600"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref50","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref53","article-title":"Spatio-temporal relational reasoning for video question answering","author":"Singh","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09488296.pdf?arnumber=9488296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:40:24Z","timestamp":1705016424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9488296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3097171","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}