{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T17:48:14Z","timestamp":1773942494338,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62322211"],"award-info":[{"award-number":["62322211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\"Pioneer\" and \"Leading Goose\" Research and Development Program of Zhejiang","award":["2024C01023"],"award-info":[{"award-number":["2024C01023"]}]},{"name":"Key Laboratory of Intelligent Processing Technology for Digital Music (Zhejiang Conservatory of Music), Ministry of Culture and Tourism","award":["2023DMKLB004"],"award-info":[{"award-number":["2023DMKLB004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3609441","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:32:12Z","timestamp":1757698332000},"page":"2757-2770","source":"Crossref","is-referenced-by-count":1,"title":["Spatial\u2013Temporal Clue Reasoning Chain for Long Video Question Answering"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0830-765X","authenticated-orcid":false,"given":"Haibo","family":"Gong","sequence":"first","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0790-9279","authenticated-orcid":false,"given":"Jiehua","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoqi","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7777-3613","authenticated-orcid":false,"given":"Yuhan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref4","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv:2402.17177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01514-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref9","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref10","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612577"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02560"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1484"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3490665"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3475510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3472810"},{"issue":"6","key":"ref29","first-page":"1111","article-title":"Review of omnimedia content quality evaluation","volume":"38","author":"Yan","year":"2022","journal-title":"J. Signal Process."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3514820"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3404374"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475540"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3494744"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref37","first-page":"59310","article-title":"Multi-factor adaptive vision selection for egocentric video question answering","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"issue":"1","key":"ref39","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1002\/nav.20053","article-title":"The Hungarian method for the assignment problem","volume":"52","author":"Kuhn","year":"1955","journal-title":"Nav. Res. Logistics"},{"key":"ref40","article-title":"AGQA 2.0: An updated benchmark for compositional spatio-temporal reasoning","author":"Grunde-McLaughlin","year":"2022","journal-title":"arXiv:2204.06105"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref42","first-page":"3343","article-title":"EgoTaskQA: Understanding human tasks in egocentric videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_46"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref50","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11162559.pdf?arnumber=11162559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:52Z","timestamp":1773086452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11162559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":50,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3609441","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}