{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:29:33Z","timestamp":1775010573335,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108301"],"award-info":[{"award-number":["2020AAA0108301"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072112"],"award-info":[{"award-number":["62072112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific and Technological Innovation Action Plan of Shanghai Science and Technology Committee","award":["22511102202"],"award-info":[{"award-number":["22511102202"]}]},{"name":"Fudan University-CIOMP Joint Fund","award":["FC2019-005"],"award-info":[{"award-number":["FC2019-005"]}]},{"name":"Double First-Class Construction Fund","award":["XM03211178"],"award-info":[{"award-number":["XM03211178"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tcsvt.2023.3272319","type":"journal-article","created":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T22:12:37Z","timestamp":1683065557000},"page":"6897-6911","source":"Crossref","is-referenced-by-count":24,"title":["Memory Network With Pixel-Level Spatio-Temporal Learning for Visual Object Tracking"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2643-968X","authenticated-orcid":false,"given":"Zechu","family":"Zhou","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"given":"Xinyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7112-2596","authenticated-orcid":false,"given":"Zhaoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4388-9757","authenticated-orcid":false,"given":"Pinxue","family":"Guo","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"given":"Qian-Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3339-8751","authenticated-orcid":false,"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, and the Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref56","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"ref14","first-page":"1","article-title":"Tracking holistic object representations","author":"sauer","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3094645"},{"key":"ref54","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00135"},{"key":"ref50","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","volume":"33","author":"liang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.196"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00411"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162599"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207202"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455418"},{"key":"ref6","first-page":"850","article-title":"Fully-convolutional Siamese networks for object tracking","author":"bertinetto","year":"2016","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987601"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref35","first-page":"100","article-title":"A memory model based on the Siamese network for long-term tracking","author":"lee","year":"2018","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"ref37","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":"ref36","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3206668"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3037947"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00247"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968163"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2857489"},{"key":"ref39","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2944654"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"ref26","first-page":"771","article-title":"Ocean: Object-aware anchor-free tracking","author":"zhang","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978194"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00854"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10297951\/10114400.pdf?arnumber=10114400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:40:56Z","timestamp":1700509256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10114400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":66,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3272319","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}