{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T03:51:20Z","timestamp":1773114680774,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0113202"],"award-info":[{"award-number":["2021ZD0113202"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476055"],"award-info":[{"award-number":["62476055"]}],"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":["62171125"],"award-info":[{"award-number":["62171125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017684","name":"Innovation Project of Jiangsu Province","doi-asserted-by":"publisher","award":["BZ2023042"],"award-info":[{"award-number":["BZ2023042"]}],"id":[{"id":"10.13039\/501100017684","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017684","name":"Innovation Project of Jiangsu Province","doi-asserted-by":"publisher","award":["BY2022564"],"award-info":[{"award-number":["BY2022564"]}],"id":[{"id":"10.13039\/501100017684","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":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3490665","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T13:40:24Z","timestamp":1730727624000},"page":"2074-2086","source":"Crossref","is-referenced-by-count":4,"title":["Collaborative Aware Bidirectional Semantic Reasoning for Video Question Answering"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6122-273X","authenticated-orcid":false,"given":"Xize","family":"Wu","sequence":"first","affiliation":[{"name":"LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7171-1318","authenticated-orcid":false,"given":"Jiasong","family":"Wu","sequence":"additional","affiliation":[{"name":"LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2993-7142","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9434-6341","authenticated-orcid":false,"given":"Lotfi","family":"Senhadji","sequence":"additional","affiliation":[{"name":"Univ-Rennes, INSERM, LTSI-UMR 1099, Rennes, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3833-7915","authenticated-orcid":false,"given":"Huazhong","family":"Shu","sequence":"additional","affiliation":[{"name":"LIST, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409453"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref6","first-page":"49250","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374111"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014775"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3381347"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3218656"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407664"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475193"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290012"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.317"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292597"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00853"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01538"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref34","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref35","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref38","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yi"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00261"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref45","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref46","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref47","article-title":"MPLUG-owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023","journal-title":"arXiv:2311.04257"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02059"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269429"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref54","first-page":"46212","article-title":"EgoSchema: A diagnostic benchmark for very long-form video language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Mangalam"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.122"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01189-x"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10741539.pdf?arnumber=10741539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:45Z","timestamp":1767638445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10741539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":62,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3490665","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}