{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:20:02Z","timestamp":1773138002333,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62262005"],"award-info":[{"award-number":["62262005"]}],"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":["62376282"],"award-info":[{"award-number":["62376282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High-level Innovative Talents in Guizhou Province","award":["GCC[2023]033"],"award-info":[{"award-number":["GCC[2023]033"]}]},{"name":"Natural Science Research Project of Department of Education of Guizhou Province","award":["QJJ[2024]009"],"award-info":[{"award-number":["QJJ[2024]009"]}]},{"name":"Guizhou Provincial Department of Science and Technology","award":["QKHCG-DXGA[2025]-ZD002"],"award-info":[{"award-number":["QKHCG-DXGA[2025]-ZD002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3615851","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T17:55:32Z","timestamp":1759168532000},"page":"3652-3664","source":"Crossref","is-referenced-by-count":2,"title":["Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4707-343X","authenticated-orcid":false,"given":"Changcheng","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Big Data and Computer Science, Guizhou Normal University, Guiyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8750-3505","authenticated-orcid":false,"given":"Qiong","family":"Cao","sequence":"additional","affiliation":[{"name":"JD Future Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9127-3387","authenticated-orcid":false,"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-3802","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"JD Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4757-2475","authenticated-orcid":false,"given":"Canqun","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3165376"},{"key":"ref13","article-title":"TransTrack: Multiple object tracking with transformer","author":"Sun","year":"2020","journal-title":"arXiv:2012.15460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref18","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref19","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00434"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref27","article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","author":"Liang","year":"2021","journal-title":"arXiv:2106.01061"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374786"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263468"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref32","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3305869"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251111"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113791"},{"key":"ref41","article-title":"MOTChallenge 2015: Towards a benchmark for multi-target tracking","author":"Leal-Taix\u00e9","year":"2015","journal-title":"arXiv:1504.01942"},{"key":"ref42","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016","journal-title":"arXiv:1603.00831"},{"key":"ref43","article-title":"MOT20: A benchmark for multi object tracking in crowded scenes","author":"Dendorfer","year":"2020","journal-title":"arXiv:2003.09003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67835-7_5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106539"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3005662"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182709"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00846"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25437"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref58","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref59","article-title":"Bridging the gap between end-to-end and non-end-to-end multi-object tracking","author":"Yan","year":"2023","journal-title":"arXiv:2305.12724"},{"key":"ref60","article-title":"MOTRv3: Release-fetch supervision for end-to-end multi-object tracking","author":"Yu","year":"2023","journal-title":"arXiv:2305.14298"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01810"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447535"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3301975"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11184532.pdf?arnumber=11184532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:25Z","timestamp":1773086485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11184532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":72,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3615851","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}