{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T05:22:01Z","timestamp":1737436921909,"version":"3.33.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0160400"],"award-info":[{"award-number":["2022ZD0160400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271346","62401538","62206031"],"award-info":[{"award-number":["62271346","62401538","62206031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521668","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:32:25Z","timestamp":1735155145000},"page":"224-235","source":"Crossref","is-referenced-by-count":0,"title":["Video Instance Segmentation Without Using Mask and Identity Supervision"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3601-0015","authenticated-orcid":false,"given":"Ge","family":"Li","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5160-6841","authenticated-orcid":false,"given":"Jiale","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8022-4172","authenticated-orcid":false,"given":"Hanqing","family":"Sun","sequence":"additional","affiliation":[{"name":"Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9041-2214","authenticated-orcid":false,"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6978-8834","authenticated-orcid":false,"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-3143","authenticated-orcid":false,"given":"Fahad","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222643"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_38"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3106096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3114541"},{"article-title":"Mask2Former for video instance segmentation","year":"2021","author":"Cheng","key":"ref15"},{"key":"ref16","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00857"},{"key":"ref19","article-title":"The 3rd large-scale video object segmentation challenge - video instance segmentation track","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Yang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3180564"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02189"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.56541\/AZWK8552"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref37","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25201"},{"key":"ref39","first-page":"19370","article-title":"InsPro: Propagating instance query and proposal for online video instance segmentation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"He","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00176"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref43","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Hwang","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref45","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Heo","year":"2022"},{"article-title":"BoxVIS: Video instance segmentation with box annotations","year":"2023","author":"Li","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"ref48","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"He","year":"2021"},{"key":"ref49","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ke","year":"2021"},{"key":"ref50","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"86","key":"ref53","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814054.pdf?arnumber=10814054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:56:40Z","timestamp":1737399400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521668","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}