{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:08:30Z","timestamp":1791486510569,"version":"4.3.4"},"reference-count":124,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576109"],"award-info":[{"award-number":["62576109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072112"],"award-info":[{"award-number":["62072112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3611020","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T17:30:51Z","timestamp":1758130251000},"page":"946-961","source":"Crossref","is-referenced-by-count":8,"title":["LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2749-5133","authenticated-orcid":false,"given":"Lingyi","family":"Hong","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongying","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenchao","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenzhi","family":"Tan","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1699-7998","authenticated-orcid":false,"given":"Yuang","family":"Feng","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5734-1305","authenticated-orcid":false,"given":"Xinyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4388-9757","authenticated-orcid":false,"given":"Pinxue","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Engineering Research Center of AI&Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4930-6284","authenticated-orcid":false,"given":"Jinglun","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Engineering Research Center of AI&Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7112-2596","authenticated-orcid":false,"given":"Zhaoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Engineering Research Center of AI&Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8992-0756","authenticated-orcid":false,"given":"Shuyong","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-8543","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3339-8751","authenticated-orcid":false,"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of AI&Robotics, Ministry of Education, Academy for Engineering & Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9482-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.784651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2014.6918642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.79"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.38"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2016.7797057"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref14","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref16","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"ref23","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00305"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_25"},{"key":"ref29","first-page":"13745","article-title":"Epic-Kitchens visor benchmark: Video segmentations and object relations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Darkhalil","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02187"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00195"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref35","article-title":"The 4th large-scale video object segmentation challenge - Video instance segmentation track","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit Workshops.","author":"Yang","year":"2022"},{"key":"ref36","article-title":"The 4th large-scale video object segmentation challenge - Video object segmentation track","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit Workshops.","author":"Yang","year":"2022"},{"key":"ref37","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref45","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01520"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00488"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00866"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_34"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00511"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611804"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref65","first-page":"10607","article-title":"Make one-shot video object segmentation efficient again","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Meinhardt","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00830"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.238"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00626"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00568"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.790"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00147"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00152"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00542"},{"key":"ref79","first-page":"324","article-title":"MaskRNN: Instance level video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref82","article-title":"Lucid data dreaming for object tracking","volume-title":"Proc. DAVIS Challenge Video Object Segmentation","author":"Khoreva","year":"2017"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00916"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137660"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00135"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00141"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00142"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3219230"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01144"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3185487"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01038"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01519"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00724"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref111","first-page":"817","article-title":"AVisT: A benchmark for visual object tracking in adverse visibility","author":"Noman","year":"2022","journal-title":"Proc. Brit. Mach. Vis. Conf."},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00496"},{"key":"ref113","article-title":"Improving underwater visual tracking with a large scale dataset and image enhancement","author":"Alawode","year":"2023"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00180"},{"issue":"1","key":"ref116","first-page":"105","article-title":"PaddlePaddle: An open-source deep learning platform from industrial practice","volume":"1","author":"Ma","year":"2019","journal-title":"Front. Data Domputing"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00901"},{"key":"ref119","first-page":"1130","article-title":"SegGPT: Towards segmentingeverything in context","author":"Wang","year":"2023","journal-title":"Proc. Int. Conf. Comput. Vis."},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref122","article-title":"The 2019 davis challenge on VoS: Unsupervised multi-object segmentation","author":"Caelles","year":"2019"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0136-6"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11168273.pdf?arnumber=11168273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:07:28Z","timestamp":1764839248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11168273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":124,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3611020","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}