{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:36:34Z","timestamp":1775838994755,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Program for International Cooperation of Ministry of Science and Technology of China","award":["2024YFE0100700"],"award-info":[{"award-number":["2024YFE0100700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106011"],"award-info":[{"award-number":["62020106011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557719","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"2924-2934","source":"Crossref","is-referenced-by-count":2,"title":["Towards Open-Vocabulary Video Semantic Segmentation"],"prefix":"10.1109","volume":"27","author":[{"given":"Xinhao","family":"Li","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-0264","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8667-9656","authenticated-orcid":false,"given":"Guolei","family":"Sun","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology, and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6930-8674","authenticated-orcid":false,"given":"Le","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7607-707X","authenticated-orcid":false,"given":"Ce","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00714"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00710"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3372835"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157995"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2932566"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405619"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32338"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00628"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_69"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.224"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00686"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00907"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.345"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475409"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.477"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.595"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.114"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00713"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00906"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00269"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00313"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_30"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387326"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01280"},{"key":"ref38","first-page":"7170","article-title":"Mask propagation for efficient video semantic segmentation","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Weng","year":"2023"},{"key":"ref39","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref49","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3070138"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00830"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3347633"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01150"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01693"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3394681"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948313.pdf?arnumber=10948313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:54Z","timestamp":1748539854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557719","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}