{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T04:51:52Z","timestamp":1785387112101,"version":"3.55.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Major Project of Hubei Province"},{"name":"Next-Generation AI Technologies","award":["2019AEA170"],"award-info":[{"award-number":["2019AEA170"]}]},{"name":"Hubei Province Key R&D Program Project","award":["2020BAB130"],"award-info":[{"award-number":["2020BAB130"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3190679","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T19:34:54Z","timestamp":1657827294000},"page":"5330-5343","source":"Crossref","is-referenced-by-count":9,"title":["Tracking With Mutual Attention Network"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1239-1240","authenticated-orcid":false,"given":"Tianpeng","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8181-0886","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-5801","authenticated-orcid":false,"given":"Jia","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3594-9879","authenticated-orcid":false,"given":"Jun","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beihang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref12","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"bertinetto","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00934"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_23"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2919201"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref53","first-page":"3","article-title":"The sixth visual object tracking VOT2018 challenge results","author":"kristan","year":"0","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.158"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3056896"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3055362"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.789"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref46","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.11.001"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/sym12030358"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2609928"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044078"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3032029"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087347"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980194"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0461-0"},{"key":"ref6","first-page":"101","article-title":"Distractor-aware siamese networks for visual object tracking","author":"zhu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00937"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00675"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01630"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076272"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"783","article-title":"Frequency channel attention networks","author":"qin","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00814"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.490"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00515"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2936503"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00510"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00282"},{"key":"ref70","article-title":"Part-based tracking by sampling","author":"ath","year":"2018"},{"key":"ref73","first-page":"1","article-title":"Tracking the known and the unknown by leveraging semantic information","volume":"2","author":"tripathi","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref24","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume":"31","author":"hu","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.226"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0075-7"},{"key":"ref26","article-title":"Bam: Bottleneck attention module","author":"park","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref25","article-title":"$ a^{2}$-nets: Double attention networks","volume":"31","author":"chen","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref69","first-page":"1690","article-title":"Channel-independent spatially regularized discriminative correlation filter for visual object tracking","volume":"33","author":"varfolomieiev","year":"2011","journal-title":"J Real-Time Image Process"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.156"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806527"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00057"},{"key":"ref21","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"ref28","first-page":"3398","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2867261"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00146"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.515"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09830040.pdf?arnumber=9830040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:06:18Z","timestamp":1701115578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9830040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3190679","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}