{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:31:50Z","timestamp":1771882310548,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["2023YFB4301800"],"award-info":[{"award-number":["2023YFB4301800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFF0908100"],"award-info":[{"award-number":["2024YFF0908100"]}]},{"DOI":"10.13039\/100016692","name":"Key Research and Development Program of Shaanxi","doi-asserted-by":"publisher","award":["Program"],"award-info":[{"award-number":["Program"]}],"id":[{"id":"10.13039\/100016692","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3661407","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:07:05Z","timestamp":1770757625000},"page":"2050-2065","source":"Crossref","is-referenced-by-count":0,"title":["Monocular Multi-Object 3D Visual Language Tracking"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1414-6181","authenticated-orcid":false,"given":"Hongkai","family":"Wei","sequence":"first","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7901-5158","authenticated-orcid":false,"given":"Rong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0069-9041","authenticated-orcid":false,"given":"Haixiang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4043-8448","authenticated-orcid":false,"given":"Shijie","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5550-6354","authenticated-orcid":false,"given":"Xiangyu","family":"Song","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0384-3743","authenticated-orcid":false,"given":"Mingtao","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0699-3992","authenticated-orcid":false,"given":"Keyu","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6462-6087","authenticated-orcid":false,"given":"Yongle","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7928-897X","authenticated-orcid":false,"given":"Hua","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Chang’an University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3406-673X","authenticated-orcid":false,"given":"Naveed","family":"Akhtar","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1177352.1177355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929520"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416880"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00897"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01785"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01296"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00531"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00355"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108640"},{"key":"ref12","article-title":"ByteTrackV2: 2D and 3D multi-object tracking by associating every detection box","author":"Zhang","year":"2023","journal-title":"arXiv:2303.15334"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2957464"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref20","article-title":"MOT16: A benchmark for multi-object tracking","author":"Milan","year":"2016","journal-title":"arXiv:1603.00831"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref23","article-title":"MOT20: A benchmark for multi object tracking in crowded scenes","author":"Dendorfer","year":"2020","journal-title":"arXiv:2003.09003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01842-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref27","first-page":"90579","article-title":"DeTrack: In-model latent denoising learning for visual object tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref28","article-title":"SAM2MOT: A novel paradigm of multi-object tracking by segmentation","author":"Jiang","year":"2025","journal-title":"arXiv:2504.04519"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref33","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557570"},{"key":"ref35","article-title":"Visual language tracking with multi-modal interaction: A robust benchmark","author":"Li","year":"2024","journal-title":"arXiv:2409.08887"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0476"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28205"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1241"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/183"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00816"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4157"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/250"},{"key":"ref45","first-page":"13","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks (NeurIPS Datasets Benchmarks)","author":"Wilson"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341635"},{"key":"ref47","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref48","first-page":"21","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00810"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","first-page":"12786","article-title":"TokenLearner: Adaptive space-time tokenization for videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Ryoo"},{"key":"ref53","first-page":"20","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. ICLR","author":"Bolya"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref55","first-page":"48","article-title":"KAN: Kolmogorov\u2013Arnold networks","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref56","first-page":"12","article-title":"Information constraints on auto-encoding variational Bayes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lopez"},{"key":"ref57","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref59","first-page":"13","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC), 2017., 2017","author":"Faghri"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3165376"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01810"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01567"},{"key":"ref68","first-page":"21","article-title":"OVTR: End-to-end open-vocabulary multiple object tracking with transformer","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060164"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973512"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422289"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00976"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11391514.pdf?arnumber=11391514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:50:33Z","timestamp":1771879833000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3661407","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}