{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T02:16:18Z","timestamp":1784513778848,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFB1302400"],"award-info":[{"award-number":["2017YFB1302400"]}]},{"name":"Jinan \u201c20 New Colleges and Universities\u201d Funded Scientific Research Leader Studio","award":["2021GXRC079"],"award-info":[{"award-number":["2021GXRC079"]}]},{"name":"Major Agricultural Applied Technological Innovation Projects of Shandong Province","award":["SD2019NJ014"],"award-info":[{"award-number":["SD2019NJ014"]}]},{"DOI":"10.13039\/501100007129","name":"Shandong Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2019MF064"],"award-info":[{"award-number":["ZR2019MF064"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012237","name":"Beijing Advanced Innovation Center for Intelligent Robots and Systems","doi-asserted-by":"publisher","award":["2019IRS19"],"award-info":[{"award-number":["2019IRS19"]}],"id":[{"id":"10.13039\/501100012237","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":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3317447","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T18:02:08Z","timestamp":1695232928000},"page":"3663-3673","source":"Crossref","is-referenced-by-count":27,"title":["Video Question Answering With Semantic Disentanglement and Reasoning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5143-2263","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialong","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5140-7036","authenticated-orcid":false,"given":"Fengyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huijuan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1108\/JRIM-05-2020-0115"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058248"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01073"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-srw.7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3278492"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref14","article-title":"CLIP-adapter: Better vision-language models with feature adapters","author":"Gao","year":"2021","journal-title":"arXiv:2110.04544"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref16","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref20","article-title":"TRANS-BLSTM: Transformer with bidirectional LSTM for language understanding","author":"Huang","year":"2020","journal-title":"arXiv:2003.07000"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT55151.2022.9804090"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747716"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref24","article-title":"Rethinking multi-modal alignment in video question answering from feature and sample perspectives","author":"Xiao","year":"2022","journal-title":"arXiv:2204.11544"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142526"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19922"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475193"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/178"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2957309"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref46","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","author":"Pan","year":"2022","journal-title":"arXiv:2206.13559"},{"key":"ref47","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref48","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref49","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref54","first-page":"3784","article-title":"Debiased visual question answering from feature and sample perspectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wen"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref63","first-page":"26462","article-title":"Learning from inside: Self-driven Siamese sampling and reasoning for video question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref64","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Zellers"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10256202.pdf?arnumber=10256202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:35:47Z","timestamp":1715362547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10256202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":66,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3317447","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}