{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:08:34Z","timestamp":1772554114510,"version":"3.50.1"},"reference-count":76,"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\/501100002367","name":"Frontier Research Fund of the Institute of Optics and Electronics, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["C21K005"],"award-info":[{"award-number":["C21K005"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101529"],"award-info":[{"award-number":["62101529"]}],"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":["62102205"],"award-info":[{"award-number":["62102205"]}],"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":["62102207"],"award-info":[{"award-number":["62102207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M710958"],"award-info":[{"award-number":["2022M710958"]}],"id":[{"id":"10.13039\/501100002858","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":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3249468","type":"journal-article","created":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T19:04:59Z","timestamp":1677524699000},"page":"5102-5116","source":"Crossref","is-referenced-by-count":77,"title":["Learning Spatial-Frequency Transformer for Visual Object Tracking"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3458-4492","authenticated-orcid":false,"given":"Chuanming","family":"Tang","sequence":"first","affiliation":[{"name":"Institute of Optics and Electronics, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3449-6537","authenticated-orcid":false,"given":"Yuanchao","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6982-2315","authenticated-orcid":false,"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"given":"Jianlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Optics and Electronics, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8582-8397","authenticated-orcid":false,"given":"Yongmei","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Optics and Electronics, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref57","article-title":"A normalized Gaussian Wasserstein distance for tiny object detection","author":"wang","year":"2021","journal-title":"arXiv 2110 13389"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","first-page":"1462","article-title":"Draw: A recurrent neural network for image generation","author":"gregor","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref58","first-page":"11830","article-title":"Rethinking rotated object detection with Gaussian Wasserstein distance loss","author":"yang","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","article-title":"Symbiotic attention for egocentric action recognition with object-centric alignment","author":"wang","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref55","first-page":"1","article-title":"Data-dependent Gaussian prior objective for language generation","author":"li","year":"2020","journal-title":"Proc ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref54","first-page":"1","article-title":"The infinite Gaussian mixture model","volume":"12","author":"rasmussen","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"ref46","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162599"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"ref47","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","author":"lin","year":"2021","journal-title":"arXiv 2112 00995"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"ref41","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref44","article-title":"VisEvent: Reliable object tracking via collaboration of frame and event flows","author":"wang","year":"2021","journal-title":"arXiv 2108 05015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3044287"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2874312"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00358"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083933"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165536"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref30","first-page":"771","article-title":"Ocean: Object-aware anchor-free tracking","author":"zhang","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2905157"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3113041"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927224"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3023440"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00411"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref70","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046478"},{"key":"ref68","article-title":"WebUAV-3M: A benchmark for unveiling the power of million-scale deep UAV tracking","author":"zhang","year":"2022","journal-title":"arXiv 2201 07425"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.11.007"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"ref20","article-title":"A note on over-smoothing for graph neural networks","author":"cai","year":"2020","journal-title":"arXiv 2006 13318"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref63","first-page":"300","article-title":"TrackingNet: A large-scale dataset and benchmark for object tracking in the wild","author":"m\u00fcller","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref21","article-title":"Anti-oversmoothing in deep vision transformers via the Fourier domain analysis: From theory to practice","author":"wang","year":"2022","journal-title":"arXiv 2203 05962"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00511"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref60","article-title":"Revisiting graph neural networks: All we have is low-pass filters","author":"hoang","year":"2019","journal-title":"arXiv 1905 09550"},{"key":"ref62","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10054166.pdf?arnumber=10054166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:43:34Z","timestamp":1695667414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10054166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":76,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3249468","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}