{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:01:40Z","timestamp":1749268900409,"version":"3.41.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Brain-like General Vision Model and Applications project","award":["2022ZD0160402"],"award-info":[{"award-number":["2022ZD0160402"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M740079","GZC20230058"],"award-info":[{"award-number":["2023M740079","GZC20230058"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Laboratory of Intelligent Parallel Technology","award":["2024JK15"],"award-info":[{"award-number":["2024JK15"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3552779","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T19:38:05Z","timestamp":1742413085000},"page":"5538-5555","source":"Crossref","is-referenced-by-count":0,"title":["Low-Shot Video Object Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1234-6119","authenticated-orcid":false,"given":"Kun","family":"Yan","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8784-4916","authenticated-orcid":false,"given":"Fangyun","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8450-3921","authenticated-orcid":false,"given":"Shuyu","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Software and Microelectronics, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8854-2079","authenticated-orcid":false,"given":"Ping","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4756-0609","authenticated-orcid":false,"given":"Chang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.139"},{"key":"ref5","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"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"article-title":"The 2017 davis challenge on video object segmentation","year":"2017","author":"Pont-Tuset","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref12","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref13","first-page":"5049","article-title":"Mixmatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"article-title":"A simple semi-supervised learning framework for object detection","year":"2020","author":"Sohn","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref16","first-page":"22106","article-title":"Semi-supervised semantic segmentation via adaptive equalization learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00224"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref30","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01656"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00916"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00135"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3008917"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3383592\/mm1"},{"key":"ref43","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref44","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00297"},{"article-title":"Temporal ensembling for semi-supervised learning","year":"2016","author":"Laine","key":"ref46"},{"key":"ref47","first-page":"1171","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sajjadi"},{"article-title":"Semi-supervised semantic segmentation needs strong, varied perturbations","year":"2019","author":"French","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Workshop Challenges Representation Learn.","author":"Lee","key":"ref50"},{"key":"ref51","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zoph"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref53","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref54","first-page":"3365","article-title":"Learning with pseudo-ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref55","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"article-title":"ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring","year":"2019","author":"Berthelot","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"article-title":"Segment everything everywhere all at once","year":"2023","author":"Zou","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"article-title":"Segment anything in high quality","year":"2023","author":"Ke","key":"ref60"},{"article-title":"Personalize segment anything model with one shot","year":"2023","author":"Zhang","key":"ref61"},{"article-title":"Segment and track anything","year":"2023","author":"Cheng","key":"ref62"},{"article-title":"Track anything: Segment anything meets videos","year":"2023","author":"Yang","key":"ref63"},{"article-title":"Tracking anything in high quality","year":"2023","author":"Zhu","key":"ref64"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"article-title":"Uvosam: A mask-free paradigm for unsupervised video object segmentation via segment anything model","year":"2023","author":"Zhang","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20011"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref72","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"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref74","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jabri"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00303"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref78","first-page":"22836","article-title":"Breaking th","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Tokmakov"},{"article-title":"Automatic differentiation in pyTorch","year":"2017","author":"Paszke","key":"ref79"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"},{"key":"ref83","first-page":"13745","article-title":"Epic-kitchens visor benchmark: Video segmentations and object relations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Darkhalil"},{"key":"ref84","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10933555.pdf?arnumber=10933555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:19:16Z","timestamp":1749183556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10933555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":86,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3552779","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}