{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:33:05Z","timestamp":1779294785922,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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 (NFSC)","doi-asserted-by":"publisher","award":["62103431"],"award-info":[{"award-number":["62103431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,1]]},"DOI":"10.1109\/ricai60863.2023.10489325","type":"proceedings-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T18:46:09Z","timestamp":1712861169000},"page":"1125-1133","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Modal Object Tracking with Vision-Language Adaptive Fusion and Alignment"],"prefix":"10.1109","author":[{"given":"Jixiang","family":"Zuo","sequence":"first","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiping","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueyan","family":"Liu","sequence":"additional","affiliation":[{"name":"China North Artificial Intelligence & Innovation Research Institute,Collective Intelligence &Collaboration Laboratory,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xijun","family":"Zhao","sequence":"additional","affiliation":[{"name":"China North Artificial Intelligence & Innovation Research Institute,Collective Intelligence &Collaboration Laboratory,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref6","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arxiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.02.023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3301933"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.U09\/CVPR.2019.00552"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arxiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref28","first-page":"16743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475349"},{"key":"ref30","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume":"35","author":"Guo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)","location":"Hangzhou, China","start":{"date-parts":[[2023,12,1]]},"end":{"date-parts":[[2023,12,3]]}},"container-title":["2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10488913\/10488921\/10489325.pdf?arnumber=10489325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:11:42Z","timestamp":1712902302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10489325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ricai60863.2023.10489325","relation":{},"subject":[],"published":{"date-parts":[[2023,12,1]]}}}