{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:24:32Z","timestamp":1779294272546,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3434949","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T19:51:01Z","timestamp":1722282661000},"page":"12316-12329","source":"Crossref","is-referenced-by-count":10,"title":["Local-Global Self-Attention for Transformer-Based Object Tracking"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9615-1333","authenticated-orcid":false,"given":"Langkun","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Service Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-1325","authenticated-orcid":false,"given":"Long","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Service Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2895-3789","authenticated-orcid":false,"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, The University of Sheffield, Sheffield, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0234-6270","authenticated-orcid":false,"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Service Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0022-4357","authenticated-orcid":false,"given":"Gang","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Service Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7751-0936","authenticated-orcid":false,"given":"Jifeng","family":"Ning","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling District, Xianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.11.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2936503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109666"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref9","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. Adv. Neural. Inf. Process. Syst.","volume":"35","author":"Lin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3041332"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037947"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.152"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.11.008"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3290868"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212987"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","article-title":"Local-to-global self-attention in vision transformers","author":"Li","year":"2021","journal-title":"arXiv:2107.04735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00510"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106079"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00687"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148876"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3266485"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref39","first-page":"13564","article-title":"RelationNet++: Bridging visual representations for object detection via transformer decoder","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chi"},{"key":"ref40","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref41","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref42","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021","journal-title":"arXiv:2106.03650"},{"key":"ref43","article-title":"HRFormer: High-resolution transformer for dense prediction","author":"Yuan","year":"2021","journal-title":"arXiv:2110.09408"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249468"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref54","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref56","article-title":"HiViT: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276061"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3289620"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3323702"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162599"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25287"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01793"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref73","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10613604.pdf?arnumber=10613604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:20:55Z","timestamp":1736972455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10613604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":73,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3434949","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}