{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:39:56Z","timestamp":1775284796490,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["61625107"],"award-info":[{"award-number":["61625107"]}],"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":["61836002"],"award-info":[{"award-number":["61836002"]}],"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":["62072397"],"award-info":[{"award-number":["62072397"]}],"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":["61732007"],"award-info":[{"award-number":["61732007"]}],"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":["61932009"],"award-info":[{"award-number":["61932009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2019YFA0706200"],"award-info":[{"award-number":["2019YFA0706200"]}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Natural Science Foundation","doi-asserted-by":"publisher","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Scientifc Research Project of Zhejiang Lab","award":["2018EC0ZX01"],"award-info":[{"award-number":["2018EC0ZX01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3051756","type":"journal-article","created":{"date-parts":[[2021,1,21]],"date-time":"2021-01-21T21:00:33Z","timestamp":1611262833000},"page":"2758-2770","source":"Crossref","is-referenced-by-count":37,"title":["Graph-Based Multi-Interaction Network for Video Question Answering"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3996-8399","authenticated-orcid":false,"given":"Mao","family":"Gu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3132-5567","authenticated-orcid":false,"given":"Weike","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref72","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1209"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref77","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref74","first-page":"4334","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref75","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601835"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601883"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.12.011"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.08.016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2608882"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700788"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.412"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.009"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.005"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref69","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2017","journal-title":"arXiv 1711 08496"},{"key":"ref22","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref24","article-title":"Few-shot learning with graph neural networks","author":"garcia","year":"2017","journal-title":"arXiv 1711 04043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.200"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3321505"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3265987.3265996"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331240"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014775"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2957309"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1217"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/513"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965987"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_24"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref3","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref9","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963950"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922062"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902106"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref41","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09332277.pdf?arnumber=9332277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:03Z","timestamp":1652194203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9332277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3051756","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}