{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:23:57Z","timestamp":1792081437236,"version":"4.4.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62076005"],"award-info":[{"award-number":["62076005"]}],"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":["62376004"],"award-info":[{"award-number":["62376004"]}],"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":["U20B2068"],"award-info":[{"award-number":["U20B2068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Dreams Foundation of Jianghuai Advance Technology Center","doi-asserted-by":"publisher","award":["2023-ZM01Z015"],"award-info":[{"award-number":["2023-ZM01Z015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085MF191"],"award-info":[{"award-number":["2008085MF191"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3425455","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T19:01:44Z","timestamp":1720551704000},"page":"12059-12072","source":"Crossref","is-referenced-by-count":56,"title":["Transformer RGBT Tracking With Spatio-Temporal Multimodal Tokens"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0164-7944","authenticated-orcid":false,"given":"Dengdi","family":"Sun","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1938-5958","authenticated-orcid":false,"given":"Yajie","family":"Pan","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0902-2260","authenticated-orcid":false,"given":"Andong","family":"Lu","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-5055","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_37"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102881"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108945"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9860018"},{"key":"ref9","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NaaCL-HLT","volume":"1","author":"Kenton"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2614135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130533"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2874312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288853"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3140929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"ref22","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087341"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3157594"},{"key":"ref25","article-title":"RWTH ASR systems for LibriSpeech: Hybrid vs attention\u2014W\/O data augmentation","author":"L\u00fcscher","year":"2019","journal-title":"arXiv:1905.03072"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3244834"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"issue":"8","key":"ref28","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref30","article-title":"Temporal aggregation for adaptive RGBT tracking","author":"Tang","year":"2022","journal-title":"arXiv:2201.08949"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125504"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00709"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00632"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.575"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.451"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02008-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3353698"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121577"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00675"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3223871"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3282668"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/s20020393"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00411"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01495-3"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060862"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072207"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2980735"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067997"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768851\/10589660.pdf?arnumber=10589660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:49:16Z","timestamp":1732736956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10589660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":57,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3425455","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}