{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:55:52Z","timestamp":1775570152961,"version":"3.50.1"},"reference-count":107,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["T2293723"],"award-info":[{"award-number":["T2293723"]}],"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":["226-2022-00051"],"award-info":[{"award-number":["226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","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":[[2024,9]]},"DOI":"10.1109\/tpami.2024.3383592","type":"journal-article","created":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T18:48:35Z","timestamp":1712083715000},"page":"6247-6262","source":"Crossref","is-referenced-by-count":21,"title":["Scalable Video Object Segmentation With Identification Mechanism"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-8313","authenticated-orcid":false,"given":"Zongxin","family":"Yang","sequence":"first","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8475","authenticated-orcid":false,"given":"Jiaxu","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6206-7911","authenticated-orcid":false,"given":"Xiaohan","family":"Wang","sequence":"additional","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref6","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20200"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_43"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"ref16","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref17","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref20","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","first-page":"2","article-title":"Towards multi-object association from foreground-background integration","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","volume":"2","author":"Yang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_30"},{"key":"ref26","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref27","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00893"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/178"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_35"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00909"},{"key":"ref32","first-page":"22 836","article-title":"Breaking the","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Tokmakov"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00668"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2481711"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_36"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.55"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00125"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00085"},{"key":"ref48","article-title":"CFBI+: Collaborative video object segmentation by multi-scale foreground-background integration","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Yang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163375"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00223"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00139"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2819173"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref61","first-page":"527","article-title":"Adaptive neural networks for efficient inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bolukbasi"},{"key":"ref62","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref63","article-title":"Layer normalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshops","author":"Ba"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"8","key":"ref65","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref66","article-title":"End-to-end ASR: From supervised to semi-supervised learning with modern architectures","volume-title":"Proc. Int. Conf. Mach. Learn. Workshops","author":"Synnaeve"},{"key":"ref67","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref71","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Parmar"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3296944"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00405"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_37"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_27"},{"key":"ref88","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.77"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01181"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2465960"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref99","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00141"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25203"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10627928\/10487964.pdf?arnumber=10487964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:44:50Z","timestamp":1723052690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10487964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":107,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3383592","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":[[2024,9]]}}}