{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:23:19Z","timestamp":1783567399410,"version":"3.55.0"},"reference-count":59,"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\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"publisher","award":["RS-2023-00210908"],"award-info":[{"award-number":["RS-2023-00210908"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010274","name":"DGIST","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010274","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\/iccv51701.2025.00429","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4507-4517","source":"Crossref","is-referenced-by-count":2,"title":["CAVIS: Context-Aware Video Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Seunghun","family":"Lee","sequence":"first","affiliation":[{"name":"DGIST,Daegu,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwan","family":"Seo","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiljoon","family":"Han","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minwoo","family":"Choi","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunghoon","family":"Im","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01797"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref7","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1565"},{"key":"ref9","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref11","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00617"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1679"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2267"},{"key":"ref20","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume":"34","author":"Hwang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00107"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01280"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref33","article-title":"Mot16: A benchmark for multi-object tracking","author":"Milan","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.09.009"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00399"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00030"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.394"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00273"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00409"},{"key":"ref48","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref50","volume-title":"The 3rd large-scale video object segmentation challenge - video instance segmentation track","author":"Yang","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_35"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3552694"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref59","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv"}],"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\/11445971.pdf?arnumber=11445971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:40Z","timestamp":1777529740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445971\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00429","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}