{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:55:12Z","timestamp":1780764912730,"version":"3.54.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016698","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076100"],"award-info":[{"award-number":["62076100"]}],"id":[{"id":"10.13039\/100016698","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016698","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276072"],"award-info":[{"award-number":["62276072"]}],"id":[{"id":"10.13039\/100016698","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities, South China University of Technology","doi-asserted-by":"publisher","award":["x2rjD2230080"],"award-info":[{"award-number":["x2rjD2230080"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Provincey","doi-asserted-by":"publisher","award":["2020B0101100002"],"award-info":[{"award-number":["2020B0101100002"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Fund for Basic and Applied Basic Research-Regional Joint Fund Project","award":["23201910250000318"],"award-info":[{"award-number":["23201910250000318"]}]},{"name":"Guangdong Provincial Fund for Basic and Applied Basic Research-Regional Joint Fund Project","award":["308155351064"],"award-info":[{"award-number":["308155351064"]}]},{"name":"Chinese Association for Artificial Intelligence (CAAI)-Huawei MindSpore Open Fund, China Computer Federation (CCF)-Zhipu AI Large Model Fund"},{"name":"Hong Kong Research Grants Council through the Collaborative Research Fund","award":["C1031-18G"],"award-info":[{"award-number":["C1031-18G"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3391415","type":"journal-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T17:34:23Z","timestamp":1713548063000},"page":"8710-8721","source":"Crossref","is-referenced-by-count":4,"title":["Video Question Generation for Dynamic Changes"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-7879","authenticated-orcid":false,"given":"Jiayuan","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiali","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7691-347X","authenticated-orcid":false,"given":"Qingbao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi Key Laboratory of Multimedia Communications and Network Technology, and the Institute of Artificial Intelligence, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36718-3_18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"issue":"4","key":"ref6","first-page":"56","article-title":"Using educational video in the classroom: Theory, research and practice","volume":"12","author":"Cruse","year":"2006","journal-title":"Library Video Company"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3265987.3265996"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_30"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2986029"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189242"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175605"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00519"},{"key":"ref31","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00211"},{"key":"ref36","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref38","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","volume":"202","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029799"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref41","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshop","author":"Lin"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10981"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10505173.pdf?arnumber=10505173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:53:30Z","timestamp":1727762010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10505173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":46,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3391415","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}