{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:24Z","timestamp":1780949244630,"version":"3.54.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3662479","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:09:48Z","timestamp":1770671388000},"page":"9072-9086","source":"Crossref","is-referenced-by-count":0,"title":["WmLSTM: A Plug-and-Play Window-Level mLSTM-Based Temporal Encoder for Robust Visual Tracking"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2324-2013","authenticated-orcid":false,"given":"Yao","family":"Chen","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7540-0902","authenticated-orcid":false,"given":"Guancheng","family":"Jia","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1501-0470","authenticated-orcid":false,"given":"Ding","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5013-2501","authenticated-orcid":false,"given":"Yufei","family":"Zha","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9690-7026","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology (ASGO) and the School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3578667"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3569633"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212987"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275573"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00411"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2561"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28286"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32528"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3417"},{"key":"ref17","first-page":"1","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Modeling","author":"Gu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_7"},{"key":"ref19","first-page":"35624","article-title":"A closer look at self-supervised lightweight vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref21","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref22","first-page":"1","article-title":"HiViT: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32440"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01785"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00634"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33191"},{"key":"ref27","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01391"},{"key":"ref29","first-page":"1","article-title":"Vision-LSTM: XLSTM as generic vision backbone","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Alkin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00951"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20142"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01216"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3545752"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00657"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00881"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00162"},{"key":"ref43","first-page":"1","article-title":"Mobile vision transformer-based visual object tracking","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Gopal"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25085-9_26"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_37"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01493"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111128"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282905"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25155"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25327"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11382000.pdf?arnumber=11382000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:55:22Z","timestamp":1780948522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11382000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":61,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3662479","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}