{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:27:58Z","timestamp":1777656478262,"version":"3.51.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["2022ZD0160400"],"award-info":[{"award-number":["2022ZD0160400"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271346"],"award-info":[{"award-number":["62271346"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206031"],"award-info":[{"award-number":["62206031"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,2]]},"DOI":"10.1109\/tcsvt.2024.3474698","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T17:52:25Z","timestamp":1728323545000},"page":"1098-1110","source":"Crossref","is-referenced-by-count":6,"title":["CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0357-441X","authenticated-orcid":false,"given":"Wenqi","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5160-6841","authenticated-orcid":false,"given":"Jiale","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6978-8834","authenticated-orcid":false,"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8044-0860","authenticated-orcid":false,"given":"Shuangming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref2","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref6","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heo"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref8","article-title":"OpenVIS: Open-vocabulary video instance segmentation","author":"Guo","year":"2023","journal-title":"arXiv:2305.16835"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref12","first-page":"32214","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01085"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3246174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063377"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3321977"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01720"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929520"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16225"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"ref26","first-page":"19370","article-title":"InsPro: Propagating instance query and proposal for online video instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3361076"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00107"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref40","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref43","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv:2111.07783"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref48","first-page":"8090","article-title":"Open-vocabulary universal image segmentation with maskclip","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ding"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref50","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref52","article-title":"SED: A simple encoder\u2013decoder for open-vocabulary semantic segmentation","author":"Xie","year":"2023","journal-title":"arXiv:2311.15537"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref54","article-title":"Instance Brownian bridge as texts for open-vocabulary video instance segmentation","author":"Cheng","year":"2024","journal-title":"arXiv:2401.09732"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_13"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref57","article-title":"Mask2Former for video instance segmentation","author":"Cheng","year":"2021","journal-title":"arXiv:2112.10764"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref69","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref70","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref71","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10885778\/10706247.pdf?arnumber=10706247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:47:33Z","timestamp":1740084453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":71,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3474698","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}