{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T01:30:46Z","timestamp":1784511046381,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62388101"],"award-info":[{"award-number":["62388101"]}],"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":["62293542"],"award-info":[{"award-number":["62293542"]}],"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":["62476044"],"award-info":[{"award-number":["62476044"]}],"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":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3557992","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T16:55:29Z","timestamp":1743785729000},"page":"9312-9323","source":"Crossref","is-referenced-by-count":23,"title":["MambaVT: Spatio-Temporal Contextual Modeling for Robust RGB-T Tracking"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2240-6880","authenticated-orcid":false,"given":"Simiao","family":"Lai","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5431-1654","authenticated-orcid":false,"given":"Jiawen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8257-1429","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Future Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6976-4004","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00709"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3391802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2023.104819"},{"key":"ref9","article-title":"Transformer-based RGB-T tracking with channel and spatial feature fusion","author":"Li","year":"2024","journal-title":"arXiv:2405.03177"},{"key":"ref10","article-title":"Unified single-stage transformer network for efficient RGB-T tracking","author":"Xia","year":"2023","journal-title":"arXiv:2308.13764"},{"key":"ref11","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref14","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref15","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref16","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref18","article-title":"Vivim: A video vision mamba for medical video segmentation","author":"Yang","year":"2024","journal-title":"arXiv:2401.14168"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"ref21","article-title":"VM-UNet: Vision mamba UNet for medical image segmentation","author":"Ruan","year":"2024","journal-title":"arXiv:2402.02491"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28352"},{"key":"ref29","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Gu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3407111"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3417253"},{"key":"ref32","article-title":"Exploring learning-based motion models in multi-object tracking","author":"Huang","year":"2024","journal-title":"arXiv:2403.10826"},{"key":"ref33","first-page":"12360","article-title":"Root mean square layer normalization","volume-title":"Proc. NeurIPS","volume":"32","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25155"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396289"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3393298"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28325"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3425455"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3377471"},{"key":"ref52","article-title":"Unified sequence-to-sequence learning for single- and multi-modal visual object tracking","author":"Chen","year":"2023","journal-title":"arXiv:2304.14394"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3435722"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2614135"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123289"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01495-3"},{"key":"ref58","article-title":"AFter: Attention-based fusion router for RGBT tracking","author":"Lu","year":"2024","journal-title":"arXiv:2405.02717"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv:2405.21060"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10949219.pdf?arnumber=10949219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:42:16Z","timestamp":1767638536000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":60,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3557992","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}