{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:00:52Z","timestamp":1777568452363,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["62122010"],"award-info":[{"award-number":["62122010"]}],"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":["61976250"],"award-info":[{"award-number":["61976250"]}],"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":["62076246"],"award-info":[{"award-number":["62076246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0115502"],"award-info":[{"award-number":["2022ZD0115502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Education Sciences Planning Fund of the Chinese Ministry of Education","award":["DEA220353"],"award-info":[{"award-number":["DEA220353"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3288353","type":"journal-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T21:41:19Z","timestamp":1687556479000},"page":"4529-4541","source":"Crossref","is-referenced-by-count":14,"title":["Unified Transformer With Isomorphic Branches for Natural Language Tracking"],"prefix":"10.1109","volume":"33","author":[{"given":"Rong","family":"Wang","sequence":"first","affiliation":[{"name":"Police Information Engineering and Network Security College, People’s Public Security University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9903-802X","authenticated-orcid":false,"given":"Zongheng","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"given":"Qianli","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1919-6519","authenticated-orcid":false,"given":"Xiaoqian","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Sociology, China University of Political Science and Law, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1172-1554","authenticated-orcid":false,"given":"Tianrui","family":"Hui","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Quange","family":"Tan","sequence":"additional","affiliation":[{"name":"Police Information Engineering and Network Security College, People’s Public Security University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"998","article-title":"Feature augmented memory with global attention network for VideoQA","volume-title":"Proc. IJCAI","author":"JiayinCai"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.U09\/CVPR.2019.00552"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","article-title":"FNet: Mixing tokens with Fourier transforms","author":"Lee-Thorp","year":"2021","journal-title":"arXiv:2105.03824"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235720"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2014.x.041"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.375"},{"key":"ref25","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"Chen","year":"2018","journal-title":"arXiv:1812.03426"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01276"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref29","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","author":"Li","year":"2021","journal-title":"arXiv:2106.03089"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3223725"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3179314"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3226488"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3045747"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2944654"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2902883"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2848358"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056684"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063144"},{"key":"ref45","first-page":"91","article-title":"Faster R-CNN: Towards realtime object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref50","article-title":"TrTr: Visual tracking with transformer","author":"Zhao","year":"2021","journal-title":"arXiv:2105.03817"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref54","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00937"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00626"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00472"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref62","article-title":"Robust visual object tracking with natural language region proposal network","author":"Feng","year":"2019","journal-title":"arXiv:1912.02048"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref64","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref65","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. Syst. Demonstrations","author":"Wolf"},{"key":"ref66","first-page":"1","article-title":"Fixing weight decay regularization in Adam","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00140"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10159158.pdf?arnumber=10159158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T11:26:47Z","timestamp":1709292407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10159158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3288353","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}