{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:20:24Z","timestamp":1770747624814,"version":"3.49.0"},"reference-count":93,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206039"],"award-info":[{"award-number":["62206039"]}],"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":["62293544"],"award-info":[{"award-number":["62293544"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT24RC(3)025"],"award-info":[{"award-number":["DUT24RC(3)025"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3469959","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T13:21:30Z","timestamp":1729516890000},"page":"12052-12065","source":"Crossref","is-referenced-by-count":5,"title":["MaskTrack: Auto-Labeling and Stable Tracking for Video Object Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6859-8987","authenticated-orcid":false,"given":"Zhenyu","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4648-4437","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3321-6759","authenticated-orcid":false,"given":"Ping","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}]},{"given":"You","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2745098"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_48"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2906175"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00568"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref9","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","author":"Liang","year":"2020","journal-title":"arXiv:2010.07958"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00135"},{"key":"ref11","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","author":"Kei Cheng","year":"2021","journal-title":"arXiv:2106.05210"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00413"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref18","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv:1809.03327"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01240"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref23","article-title":"Lucid data dreaming for video object segmentation","author":"Khoreva","year":"2017","journal-title":"arXiv:1703.09554"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"ref27","article-title":"Tracking anything in high quality","author":"Zhu","year":"2023","journal-title":"arXiv:2307.13974"},{"key":"ref28","article-title":"Associating objects with transformers for video object segmentation","author":"Yang","year":"2021","journal-title":"arXiv:2106.02638"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00223"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451102"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref38","first-page":"1","article-title":"SipMask: Spatial information preservation for fast instance segmentation","volume-title":"Proc. ECCV","author":"Cao"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083933"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26293-7_35"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00893"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00466"},{"key":"ref47","article-title":"Towards generic anomaly detection and understanding: Large-scale visual-linguistic model (GPT-4V) takes the lead","author":"Cao","year":"2023","journal-title":"arXiv:2311.02782"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02024-8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475192"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.575"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.474"},{"key":"ref53","article-title":"ZegOT: Zero-shot segmentation through optimal transport of text prompts","author":"Kim","year":"2023","journal-title":"arXiv:2301.12171"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00400"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3203812"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141221"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093333"},{"key":"ref59","article-title":"RepViT-SAM: Towards real-time segmenting anything","author":"Wang","year":"2023","journal-title":"arXiv:2312.05760"},{"key":"ref60","article-title":"Semantic-SAM: Segment and recognize anything at any granularity","author":"Li","year":"2307","journal-title":"arXiv:2307.04767"},{"key":"ref61","first-page":"1","article-title":"Segment anything in high quality","volume-title":"Proc. NeurIPS","author":"Ke"},{"key":"ref62","article-title":"Segment anything meets point tracking","author":"Raji\u010d","year":"2023","journal-title":"arXiv:2307.01197"},{"key":"ref63","article-title":"Segment and track anything","author":"Cheng","year":"2305","journal-title":"arXiv:2305.06558"},{"key":"ref64","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2304","journal-title":"arXiv:2304.11968"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3271353"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3327386"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105868"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264519"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069230"},{"key":"ref71","article-title":"Open-vocabulary camouflaged object segmentation","author":"Pang","year":"2023","journal-title":"arXiv:2311.11241"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref73","first-page":"1","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heo"},{"key":"ref74","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20200"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref82","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"arXiv:2304.06718"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/178"},{"key":"ref87","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00195"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10726574.pdf?arnumber=10726574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:49:09Z","timestamp":1752169749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10726574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":93,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3469959","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}