{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:19:04Z","timestamp":1777889944340,"version":"3.51.4"},"reference-count":73,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161600"],"award-info":[{"award-number":["2022ZD0161600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023542","name":"Centre for Perceptual and Interactive Intelligence (CPII) Ltd under the Innovation and Technology Commission (ITC)'s InnoHK","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023542","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\/iccv51701.2025.01264","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13614-13624","source":"Crossref","is-referenced-by-count":0,"title":["SAM2LONG: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree"],"prefix":"10.1109","author":[{"given":"Shuangrui","family":"Ding","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Rui","family":"Qian","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Yuhang","family":"Zang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Yuhang","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Yuwei","family":"Guo","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00303"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01797"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00626"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00065"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00879"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/34.481539"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref18","article-title":"Motion-inductive self-supervised object discovery in videos","author":"Ding","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3611020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00152"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00916"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.533"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"ref37","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertainregion refinement","volume":"33","author":"Liang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28192"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00770"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref47","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01529"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_19"},{"key":"ref50","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1979.1102177"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02187"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01276"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref63","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2632"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref67","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3081597"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref70","article-title":"Joint modeling of feature, correspondence, and a compressed memory for video object segmentation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00568"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01760"}],"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\/11445943.pdf?arnumber=11445943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:40Z","timestamp":1777613080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01264","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}