{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:08:17Z","timestamp":1784905697949,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62072416"],"award-info":[{"award-number":["62072416"]}],"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":["62272423"],"award-info":[{"award-number":["62272423"]}],"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":["61873246"],"award-info":[{"award-number":["61873246"]}],"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":["62006213"],"award-info":[{"award-number":["62006213"]}],"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":["62102373"],"award-info":[{"award-number":["62102373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Universities of Henan Province","award":["21HASTIT028"],"award-info":[{"award-number":["21HASTIT028"]}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["202300410495"],"award-info":[{"award-number":["202300410495"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Colleges and Universities in Henan Province","award":["21A120010"],"award-info":[{"award-number":["21A120010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3285441","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T17:19:37Z","timestamp":1686676777000},"page":"1720-1730","source":"Crossref","is-referenced-by-count":41,"title":["One-Stream Vision-Language Memory Network for Object Tracking"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5130-5555","authenticated-orcid":false,"given":"Huanlong","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1848-320X","authenticated-orcid":false,"given":"Jingchao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3178-0607","authenticated-orcid":false,"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Guangxi Key Lab of Multi-Source Information Mining &amp; Security, Guangxi Normal University, Guilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3190679"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2015.30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2862151"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00680"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956703"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959256"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103547"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00302"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12629"},{"key":"ref24","first-page":"10944","article-title":"What makes multi-modal learning better than single","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref28","article-title":"Language-driven semantic segmentation","author":"Kamath","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref31","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074239"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref42","article-title":"Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking","author":"Wang","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref44","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gao","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2936503"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref49","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale,","author":"Dosovitskiy","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1049\/ell2.12610"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.3038720"},{"key":"ref55","article-title":"Learning target-aware representation for visual tracking via informative interactions","author":"Zhang","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3206668"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10149530.pdf?arnumber=10149530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:58:06Z","timestamp":1725904686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10149530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3285441","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}