{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:33Z","timestamp":1777865373605,"version":"3.51.4"},"reference-count":52,"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\/501100003052","name":"Ministry of Trade, Industry and Energy (MOTIE), South Korea, through the Technology Innovation Program","doi-asserted-by":"publisher","award":["RS-2024-00445759"],"award-info":[{"award-number":["RS-2024-00445759"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","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\/iccv51701.2025.01273","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13719-13729","source":"Crossref","is-referenced-by-count":0,"title":["LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation"],"prefix":"10.1109","author":[{"given":"Seunghun","family":"Lee","sequence":"first","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwan","family":"Seo","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minwoo","family":"Choi","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiljoon","family":"Han","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jahoon","family":"Jeong","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zane","family":"Durante","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Adeli","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang Hyun","family":"Park","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunghoon","family":"Im","sequence":"additional","affiliation":[{"name":"DGIST,Daegu,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1565"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref8","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00857"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1679"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2267"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00890"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref22","article-title":"Context-aware video instance segmentation","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00107"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref28","article-title":"Novis: A case for end-to-end near-online video instance segmentation","author":"Meinhardt","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref30","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref33","article-title":"Omnitracker: Unifying object tracking by tracking-with-detection","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref38","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00124"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3552694"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01522"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_26"},{"key":"ref52","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\/11445100.pdf?arnumber=11445100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:49Z","timestamp":1777530049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01273","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}