{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:16Z","timestamp":1777889716837,"version":"3.51.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62276192"],"award-info":[{"award-number":["62276192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01329","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14326-14335","source":"Crossref","is-referenced-by-count":0,"title":["TemCoCo: Temporally Consistent Multi-Modal Video Fusion with Visual-Semantic Collaboration"],"prefix":"10.1109","author":[{"given":"Meiqi","family":"Gong","sequence":"first","affiliation":[{"name":"Electronic Information School, Wuhan University,Wuhan,China,430072"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Electronic Information School, Wuhan University,Wuhan,China,430072"}]},{"given":"Xunpeng","family":"Yi","sequence":"additional","affiliation":[{"name":"Electronic Information School, Wuhan University,Wuhan,China,430072"}]},{"given":"Linfeng","family":"Tang","sequence":"additional","affiliation":[{"name":"Electronic Information School, Wuhan University,Wuhan,China,430072"}]},{"given":"Jiayi","family":"Ma","sequence":"additional","affiliation":[{"name":"Electronic Information School, Wuhan University,Wuhan,China,430072"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390404"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02153"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"ref4","article-title":"Temporally coherent gans for video super-resolution (tecogan)","author":"Chu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023541"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/87"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3417546"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268209"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00565"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10147-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01952-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3521416"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3665893"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3145476"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.02.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3038013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"ref22","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287300"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273451"},{"key":"ref26","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.12.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234340"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2024.105422"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00450"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3443673"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2045707"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3238511"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103407"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102450"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.06.008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078906"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261282"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02448"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443330.pdf?arnumber=11443330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:59Z","timestamp":1777612559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01329","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}