{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T09:18:17Z","timestamp":1768814297819,"version":"3.49.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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":["62101529"],"award-info":[{"award-number":["62101529"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Frontier Research Fund, Institute of Optics and Electronics, China Academy of Sciences","award":["C21K005"],"award-info":[{"award-number":["C21K005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tits.2023.3264664","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T17:34:24Z","timestamp":1681320864000},"page":"8121-8135","source":"Crossref","is-referenced-by-count":5,"title":["Transformer Sub-Patch Matching for High-Performance Visual Object Tracking"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3458-4492","authenticated-orcid":false,"given":"Chuanming","family":"Tang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Qintao","family":"Hu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Company Ltd., Shenzhen, China"}]},{"given":"Gaofan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jinzhen","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jianlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"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":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3027521"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6733"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083933"},{"key":"ref59","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3103601"},{"key":"ref58","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":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2482905"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2984256"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2950508"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3212594"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/127"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/130"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref41","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","first-page":"16743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","author":"lin","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref4","first-page":"1","article-title":"Deep learning for visual tracking: A comprehensive survey","volume":"99","author":"marvasti-zadeh","year":"2021","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.902731"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref5","first-page":"10469","article-title":"ReCF: Exploiting response reasoning for correlation filters in real-time UAV tracking","volume":"23","author":"li","year":"2021","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref40","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148876"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230064"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref33","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 (NIPS)"},{"key":"ref32","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2749981"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2723575"},{"key":"ref39","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref38","first-page":"432","article-title":"An introductory survey on attention mechanisms in NLP problems","author":"hu","year":"2019","journal-title":"Proc SAI Intell Syst Conf"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.232"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6466878"},{"key":"ref25","first-page":"95300","article-title":"A FragTrack algorithm enhancement for total occlusion management in visual object tracking","author":"adamo","year":"2015","journal-title":"Proc SPIE"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref64","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6899"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"ref65","article-title":"TransTrack: Multiple object tracking with transformer","author":"sun","year":"2020","journal-title":"arXiv 2012 15460"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.84"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2010.0127"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref62","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref61","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10202228\/10101686.pdf?arnumber=10101686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:08:03Z","timestamp":1692641283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10101686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":74,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3264664","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}