{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:58:45Z","timestamp":1781035125610,"version":"3.54.1"},"reference-count":32,"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\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M761805"],"award-info":[{"award-number":["2024M761805"]}],"id":[{"id":"10.13039\/501100002858","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\/iccv51701.2025.01159","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12470-12478","source":"Crossref","is-referenced-by-count":0,"title":["Sliced Wasserstein Bridge for Open-Vocabulary Video Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Zheyun","family":"Qin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanchen","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhumin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0506-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_25"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1565"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref8","article-title":"Instance brownian bridge as texts for open-vocabulary video instance segmentation","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_18"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_13"},{"key":"ref12","article-title":"Metric learning for temporal sequence alignment","author":"Garreau","year":"2014","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref14","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32338"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00855"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01846"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328485"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123456"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00262"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3474698"}],"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\/11445688.pdf?arnumber=11445688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:49:34Z","timestamp":1781034574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445688\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01159","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}