{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:29:31Z","timestamp":1775010571945,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100017440","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20383"],"award-info":[{"award-number":["U23A20383"]}],"id":[{"id":"10.13039\/100017440","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of Guangxi Science and Technology","award":["2024GXNSFGA010001"],"award-info":[{"award-number":["2024GXNSFGA010001"]}]},{"name":"Project of Guangxi Science and Technology","award":["2022GXNSFDA035079"],"award-info":[{"award-number":["2022GXNSFDA035079"]}]},{"name":"Guangxi \u201cYoung Bagui Scholar\u201d Teams for Innovation and Research Project"},{"name":"Guangxi \u201cBagui Scholar\u201d Teams for Innovation and Research Project"},{"name":"Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing"},{"name":"Guangxi Talent Highland Project of Big Data Intelligence and Application"},{"name":"Research Project of Guangxi Normal University","award":["2022TD002"],"award-info":[{"award-number":["2022TD002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3395352","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T20:06:28Z","timestamp":1714507588000},"page":"9053-9063","source":"Crossref","is-referenced-by-count":26,"title":["One-Stream Stepwise Decreasing for Vision-Language Tracking"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1513-0313","authenticated-orcid":false,"given":"Guangtong","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2353-5246","authenticated-orcid":false,"given":"Qihua","family":"Liang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China"}]},{"given":"Zhiyi","family":"Mo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3867-6753","authenticated-orcid":false,"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0280-2640","authenticated-orcid":false,"given":"Shuxiang","family":"Song","sequence":"additional","affiliation":[{"name":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University, Guilin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref3","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref4","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Neural Inf. Process. Syst.,Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195759"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref13","first-page":"1","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"ref18","first-page":"1","article-title":"Divert more attention to vision-language tracking","volume-title":"Proc. NeurIPS","author":"Guo"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North","author":"Devlin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref23","article-title":"Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking","author":"Wang","year":"2018","journal-title":"arXiv:1811.10014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.789"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102886"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037947"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987601"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739868\/10510485.pdf?arnumber=10510485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:11:17Z","timestamp":1732666277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10510485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":38,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3395352","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}