{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:31Z","timestamp":1792786951117,"version":"4.5.0"},"reference-count":112,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan"},{"name":"Ministry of Education of China","award":["JYB2025XDXM103"],"award-info":[{"award-number":["JYB2025XDXM103"]}],"id":[{"id":"https:\/\/ror.org\/03m01yf64","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Goose\u201d R&D Program of Zhejiang","award":["2024C01161"],"award-info":[{"award-number":["2024C01161"]}]},{"name":"National Natural Science Foundation of China","award":["62372405"],"award-info":[{"award-number":["62372405"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3692914","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:57:21Z","timestamp":1778788641000},"page":"11415-11430","source":"Crossref","is-referenced-by-count":1,"title":["Mask-Guided Self-Supervised Video Object Segmentation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4077-1398","authenticated-orcid":false,"given":"Ruijie","family":"Quan","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4637-0328","authenticated-orcid":false,"given":"Liulei","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-8313","authenticated-orcid":false,"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01794"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01038"},{"key":"ref9","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":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_11"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref23","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":"ref24","article-title":"Switch to generalize: Domain-switch learning for cross-domain few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2819173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2966453"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00852"},{"key":"ref29","first-page":"318","article-title":"Joint-task self-supervised learning for temporal correspondence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17220"},{"key":"ref31","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jabri","year":"2020"},{"key":"ref32","first-page":"25308","article-title":"Dense unsupervised learning for video segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Araslanov","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref35","first-page":"2142","article-title":"Self-supervised learning for video correspondence flow","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Lai","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093294"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00709"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00640"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00109"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01427"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540054"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_43"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.55"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2745098"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.185"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.21"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818105"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123456"},{"key":"ref53","first-page":"1367","article-title":"Computational optimal transport: Complexity by accelerated gradient descent is better than by Sinkhorn\u2019s algorithm","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dvurechensky","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"ref59","article-title":"Suppressing the heterogeneity: A strong feature extractor for few-shot segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01280"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00898"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00981"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_26"},{"key":"ref67","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00061"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00223"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_5"},{"key":"ref72","article-title":"Dynamic in static: Hybrid visual correspondence for self-supervised video object segmentation","author":"Pei","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00652"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00631"},{"key":"ref75","article-title":"TransTrack: Multiple object tracking with transformer","author":"Sun","year":"2020"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00133"},{"key":"ref80","first-page":"8089","article-title":"Cycle-contrast for self-supervised video representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00496"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00406"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3269228"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00331"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321192121"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00383"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.348"},{"key":"ref92","first-page":"844","article-title":"Unsupervised learning of object frames by dense equivariant image labelling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Thewlis","year":"2017"},{"key":"ref93","first-page":"4489","article-title":"Unsupervised learning of dense visual representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Pinheiro","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553469"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2946823"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0485"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00248"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref102","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01410"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00817"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240660"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.590"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11520567.pdf?arnumber=11520567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:23:30Z","timestamp":1790270610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11520567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":112,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3692914","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":[[2026,10]]}}}