{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:21:07Z","timestamp":1772907667631,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["62006142"],"award-info":[{"award-number":["62006142"]}],"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":["U1936203"],"award-info":[{"award-number":["U1936203"]}],"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":["62236003"],"award-info":[{"award-number":["62236003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen College Stability Support Plan","award":["GXWD20220817144428005"],"award-info":[{"award-number":["GXWD20220817144428005"]}]},{"DOI":"10.13039\/501100020196","name":"Shandong Provincial Natural Science Foundation for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["ZR2021JQ26"],"award-info":[{"award-number":["ZR2021JQ26"]}],"id":[{"id":"10.13039\/501100020196","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Major Basic Research Project of Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2021ZD15"],"award-info":[{"award-number":["ZR2021ZD15"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015642","name":"Science and Technology Innovation Program for Distinguished Young Scholars of Shandong Province Higher Education Institutions","doi-asserted-by":"publisher","award":["2021KJ036"],"award-info":[{"award-number":["2021KJ036"]}],"id":[{"id":"10.13039\/501100015642","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007927","name":"Special Fund for Distinguished Professors of Shandong Jianzhu University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007927","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcsvt.2023.3278492","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T18:10:47Z","timestamp":1684779047000},"page":"7684-7695","source":"Crossref","is-referenced-by-count":21,"title":["Multi-Granularity Interaction and Integration Network for Video Question Answering"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8520-3883","authenticated-orcid":false,"given":"Yuanyuan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0247-5221","authenticated-orcid":false,"given":"Jianlong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3556537"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3265987.3265996"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016391"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.122"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475193"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463584"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3229081"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463635"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002667"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3185900"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref29","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref32","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Zellers"},{"key":"ref33","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451103"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3366710"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/139"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10348119\/10130300.pdf?arnumber=10130300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:53:51Z","timestamp":1705024431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10130300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":49,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3278492","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}