{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:58:39Z","timestamp":1773799119438,"version":"3.50.1"},"reference-count":55,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20518"],"award-info":[{"award-number":["U21A20518"]}],"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":["U23A20341"],"award-info":[{"award-number":["U23A20341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Instrum. Meas."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tim.2024.3522698","type":"journal-article","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:19:56Z","timestamp":1735845596000},"page":"1-13","source":"Crossref","is-referenced-by-count":2,"title":["Multigranularity Localization Transformer With Collaborative Understanding for Referring Multiobject Tracking"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9584-202X","authenticated-orcid":false,"given":"Jiajun","family":"Chen","sequence":"first","affiliation":[{"name":"School of Robotics, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1393-5027","authenticated-orcid":false,"given":"Jiacheng","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6054-3694","authenticated-orcid":false,"given":"Guojin","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8902-4193","authenticated-orcid":false,"given":"You","family":"Yao","sequence":"additional","affiliation":[{"name":"USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9720-5915","authenticated-orcid":false,"given":"Zhiyong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Robotics, Hunan University, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MIM.2014.6825388"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3269117"},{"key":"ref4","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref5","article-title":"Language prompt for autonomous driving","author":"Wu","year":"2023","journal-title":"arXiv:2309.04379"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3201938"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3379090"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3437645"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref11","first-page":"3205","article-title":"Type-to-track: Retrieve any object via prompt-based tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Nguyen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01810"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25437"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3232092"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref20","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00863"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref23","article-title":"Contrastive learning for multi-object tracking with transformers","author":"De Plaen","year":"2023","journal-title":"arXiv:2311.08043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3446625"},{"key":"ref29","article-title":"EPCFormer: Expression prompt collaboration transformer for universal referring video object segmentation","author":"Chen","year":"2023","journal-title":"arXiv:2308.04162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3324362"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref32","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. NIPS","author":"Guo"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01288"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref38","article-title":"Aligning and prompting everything all at once for universal visual perception","author":"Shen","year":"2023","journal-title":"arXiv:2312.02153"},{"key":"ref39","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"ref45","article-title":"MLS-track: Multilevel semantic interaction in RMOT","author":"Ma","year":"2024","journal-title":"arXiv:2404.12031"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref48","article-title":"Rethinking the competition between detection and Reid in multi-object tracking","author":"Liang","year":"2020","journal-title":"arXiv:2010.12138"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"ref50","article-title":"TransTrack: Multiple object tracking with transformer","author":"Sun","year":"2020","journal-title":"arXiv:2012.15460"},{"key":"ref51","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","volume":"6","author":"Loshchilov"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref55","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"}],"container-title":["IEEE Transactions on Instrumentation and Measurement"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/19\/10764799\/10820195.pdf?arnumber=10820195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:42:18Z","timestamp":1736970138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10820195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tim.2024.3522698","relation":{},"ISSN":["0018-9456","1557-9662"],"issn-type":[{"value":"0018-9456","type":"print"},{"value":"1557-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}