{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:33:17Z","timestamp":1780763597053,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF1202903"],"award-info":[{"award-number":["2022YFF1202903"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122035"],"award-info":[{"award-number":["62122035"]}],"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":["61972188"],"award-info":[{"award-number":["61972188"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3284979","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T17:28:39Z","timestamp":1686331719000},"page":"4518-4528","source":"Crossref","is-referenced-by-count":23,"title":["Decoupling Multimodal Transformers for Referring Video Object Segmentation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8688-8228","authenticated-orcid":false,"given":"Mingqi","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Warwick Manufacturing Group, University of Warwick, Coventry, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-9141","authenticated-orcid":false,"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3942-3900","authenticated-orcid":false,"given":"Giovanni","family":"Montana","sequence":"additional","affiliation":[{"name":"Warwick Manufacturing Group, University of Warwick, Coventry, U.K"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref34","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","author":"zhang","year":"2022","journal-title":"Proc NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref37","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3161832"},{"key":"ref36","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01144"},{"key":"ref33","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"yao","year":"2022","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref32","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"zeng","year":"2022","journal-title":"Proc ICML"},{"key":"ref2","article-title":"A survey on deep learning technique for video segmentation","author":"zhou","year":"2021","journal-title":"arXiv 2107 01153"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2655624"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref19","article-title":"R2 VOS: Robust referring video object segmentation via relational multimodal cycle consistency","author":"li","year":"2022","journal-title":"arXiv 2207 01203"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc ICML"},{"key":"ref26","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc ICLR"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref20","first-page":"123","article-title":"Video object segmentation with language referring expressions","author":"khoreva","year":"2018","journal-title":"Proc ACCV"},{"key":"ref22","article-title":"VLP: A survey on vision-language pre-training","author":"chen","year":"2022","journal-title":"arXiv 2202 09061"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref28","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref8","first-page":"3719","article-title":"Referring segmentation in images and videos with cross-modal self-attention network","volume":"44","author":"ye","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref7","first-page":"4761","article-title":"Cross-modal progressive comprehension for referring segmentation","volume":"44","author":"liu","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref40","author":"bird","year":"2009","journal-title":"Natural Language Processing with Python Analyzing Text with the Natural Language Toolkit"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10147907.pdf?arnumber=10147907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:41:53Z","timestamp":1695667313000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10147907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":40,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3284979","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}