{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T14:36:19Z","timestamp":1773498979465,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62101309"],"award-info":[{"award-number":["62101309"]}],"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":["62271180"],"award-info":[{"award-number":["62271180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2021QF109"],"award-info":[{"award-number":["ZR2021QF109"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tcsvt.2024.3361076","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:57:52Z","timestamp":1706813872000},"page":"2963-2974","source":"Crossref","is-referenced-by-count":17,"title":["Learning Better Video Query With SAM for Video Instance Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-8294","authenticated-orcid":false,"given":"Hao","family":"Fang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8163-3050","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7977-9728","authenticated-orcid":false,"given":"Xiaofei","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6069-5391","authenticated-orcid":false,"given":"Xinxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3098118"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127562"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115815"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3117964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3061153"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3027741"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2911396"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978703"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014491"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16225"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_35"},{"key":"ref17","article-title":"Robust online video instance segmentation with track queries","author":"Zhan","year":"2022","journal-title":"arXiv:2211.09108"},{"key":"ref18","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123456"},{"key":"ref22","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hwang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00103"},{"key":"ref24","article-title":"Mask2Former for video instance segmentation","author":"Cheng","year":"2021","journal-title":"arXiv:2112.10764"},{"key":"ref25","article-title":"SeqFormer: Sequential transformer for video instance segmentation","author":"Wu","year":"2021","journal-title":"arXiv:2112.08275"},{"key":"ref26","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heo"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2021","journal-title":"arXiv:2112.01527"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","article-title":"Segment anything in high quality","author":"Ke","year":"2023","journal-title":"arXiv:2306.01567"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01106"},{"key":"ref34","first-page":"1192","article-title":"Prototypical cross-attention networks for multiple object tracking and segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ke"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00794"},{"key":"ref36","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_30"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_10"},{"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":"10.1109\/CVPR.2019.01186"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref45","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref48","first-page":"1","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222906"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref52","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00707"},{"key":"ref54","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NeurIPS","author":"Cheng"},{"key":"ref55","first-page":"21898","article-title":"SOLQ: Segmenting objects by learning queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dong"},{"key":"ref56","article-title":"Segment anything","author":"Kirillov","year":"2023","journal-title":"arXiv:2304.02643"},{"key":"ref57","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023","journal-title":"arXiv:2304.11968"},{"key":"ref58","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv:2305.06558"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref60","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang"},{"key":"ref61","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023","journal-title":"arXiv:2305.03048"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"Kuhn","year":"1955","journal-title":"Nav. Res. Logistics Quart."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00291"},{"key":"ref67","article-title":"The 3rd large-scale video object segmentation challenge\u2014Video instance segmentation track","volume-title":"Proc. Workshop Conjunction (CVPR)","author":"Yang"},{"key":"ref68","article-title":"The 4th large-scale video object segmentation challenge\u2014Video instance segmentation track","volume-title":"Proc. Workshop Conjunct. (CVPR)","author":"Yang"},{"key":"ref69","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref73","article-title":"Offline-to-online knowledge distillation for video instance segmentation","author":"Kim","year":"2023","journal-title":"arXiv:2302.07516"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10949577\/10418101.pdf?arnumber=10418101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T11:38:53Z","timestamp":1743853133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":73,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3361076","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}