{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T10:46:47Z","timestamp":1782470807856,"version":"3.54.5"},"reference-count":82,"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":"National Key R&D Program of China","award":["2022ZD0160900"],"award-info":[{"award-number":["2022ZD0160900"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380119"],"award-info":[{"award-number":["020214380119"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Frontier Technology Research and Development","award":["BF2024076"],"award-info":[{"award-number":["BF2024076"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"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.2025.3557841","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:41:43Z","timestamp":1743795703000},"page":"6039-6054","source":"Crossref","is-referenced-by-count":3,"title":["JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation"],"prefix":"10.1109","volume":"47","author":[{"given":"Jiaming","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4788-9751","authenticated-orcid":false,"given":"Yutao","family":"Cui","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1391-1762","authenticated-orcid":false,"given":"Gangshan","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00303"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref17","first-page":"58736","article-title":"MixFormerV2: Efficient fully transformer tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Cui"},{"key":"ref18","first-page":"13745","article-title":"EPIC-KITCHENS VISOR benchmark: Video segmentations and object relations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Darkhalil"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref22","article-title":"Convmae: Masked convolution meets masked autoencoders","author":"Gao","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Heo"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref29","article-title":"Lucid data dreaming for object tracking","author":"Khoreva","year":"2017"},{"key":"ref30","first-page":"7","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"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.","volume":"33","author":"Liang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_27"},{"key":"ref39","first-page":"6","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref42","article-title":"TransVOS: Video object segmentation with transformers","author":"Mei","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-9482-0","volume-title":"Video Segmentation and Its Appl.","author":"Ngan","year":"2011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref49","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref50","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref51","first-page":"7","article-title":"Training deep neural networks on noisy labels with bootstrapping","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Reed"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02187"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01276"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref68","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref74","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"issue":"9","key":"ref76","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Yang"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00733"},{"key":"ref79","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.79"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref82","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10949703.pdf?arnumber=10949703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:00Z","timestamp":1749231720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":82,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3557841","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":[[2025,7]]}}}