{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:19:20Z","timestamp":1773137960269,"version":"3.50.1"},"reference-count":88,"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"}],"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.2025.3618119","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:39:41Z","timestamp":1759772381000},"page":"2968-2979","source":"Crossref","is-referenced-by-count":1,"title":["LTCA: Long-Range Temporal Context Attention for Referring Video Object Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9754-129X","authenticated-orcid":false,"given":"Cilin","family":"Yan","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1978-2025","authenticated-orcid":false,"given":"Guoliang","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3341170"},{"key":"ref4","article-title":"Multiple-human parsing in the wild","author":"Li","year":"2017","journal-title":"arXiv:1705.07206"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240509"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.204"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs13214441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00393"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128083"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3439395"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02144-1"},{"key":"ref14","article-title":"Fully self-supervised learning for semantic segmentation","author":"Wang","year":"2022","journal-title":"arXiv:2202.11981"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33612-6_21"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.109"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2543581.2543596"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1075\/is.17.2.02gro"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696569"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref34","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202574"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3361076"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02076-w"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref43","article-title":"DVIS++: Improved decoupled framework for universal video segmentation","author":"Zhang","year":"2023","journal-title":"arXiv:2312.13305"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hwang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1679"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263468"},{"key":"ref51","article-title":"F-LMM: Grounding frozen large multimodal models","author":"Wu","year":"2024","journal-title":"arXiv:2406.05821"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref56","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106153"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref61","article-title":"LISA: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv:2308.00692"},{"key":"ref62","article-title":"PixelLM: Pixel reasoning with large multimodal model","author":"Ren","year":"2023","journal-title":"arXiv:2312.02228"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref64","article-title":"InstructSeq: Unifying vision tasks with instruction-conditioned multi-modal sequence generation","author":"Fang","year":"2023","journal-title":"arXiv:2311.18835"},{"key":"ref65","article-title":"See, say, and segment: Teaching LMMs to overcome false premises","author":"Wu","year":"2023","journal-title":"arXiv:2312.08366"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"ref67","article-title":"Towards robust referring video object segmentation with cyclic relational consensus","author":"Li","year":"2022","journal-title":"arXiv:2207.01203"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284979"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3419119"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284165"},{"key":"ref72","first-page":"1","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1511.07122"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00240"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11193806.pdf?arnumber=11193806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:12Z","timestamp":1773086472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11193806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":88,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3618119","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}