{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T07:01:33Z","timestamp":1785308493349,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["2020AAA0106800"],"award-info":[{"award-number":["2020AAA0106800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902401"],"award-info":[{"award-number":["61902401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972071"],"award-info":[{"award-number":["61972071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906052"],"award-info":[{"award-number":["61906052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036011"],"award-info":[{"award-number":["62036011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972394"],"award-info":[{"award-number":["61972394"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2033210"],"award-info":[{"award-number":["U2033210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences (CAS) Key Research Program of Frontier Sciences","doi-asserted-by":"publisher","award":["QYZDJ-SSWJSC040"],"award-info":[{"award-number":["QYZDJ-SSWJSC040"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association, CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3117077","type":"journal-article","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T17:49:25Z","timestamp":1633888165000},"page":"8553-8566","source":"Crossref","is-referenced-by-count":25,"title":["Toward Accurate Pixelwise Object Tracking via Attention Retrieval"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0479-332X","authenticated-orcid":false,"given":"Zhipeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8426-9335","authenticated-orcid":false,"given":"Yufan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5888-6735","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9237-8825","authenticated-orcid":false,"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houwen","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1177352.1177355"},{"key":"ref71","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref39","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00746"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.372"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.336"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.196"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00626"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.531"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2838670"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00140"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2609928"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00698"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.156"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00146"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2932615"},{"key":"ref2","first-page":"547","article-title":"The eighth visual object tracking VOT2020 challenge results","author":"kristan","year":"2020","journal-title":"Proc ECCV Workshops"},{"key":"ref1","article-title":"Deep learning for visual tracking: A comprehensive survey","author":"marvasti-zadeh","year":"2019","journal-title":"arXiv 1912 00535"},{"key":"ref20","article-title":"Rethinking the competition between detection and Reid in multi-object tracking","author":"liang","year":"2020","journal-title":"arXiv 2010 12138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00376"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.238"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00680"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00774"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.116"},{"key":"ref52","first-page":"6","article-title":"Tracking the known and the unknown by leveraging semantic information","author":"tripathi","year":"2019","journal-title":"Proc BMVC"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00472"},{"key":"ref17","first-page":"107","article-title":"Towards real-time multi-object tracking","author":"wang","year":"2020","journal-title":"Proc 16th Eur Conf Comput Vis (ECCV)"},{"key":"ref18","article-title":"FairMOT: On the fairness of detection and re-identification in multiple object tracking","author":"zhang","year":"2020","journal-title":"arXiv 2004 01888"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00716"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.828427"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"ref7","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc ECCV"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00403"},{"key":"ref9","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc MICCI"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00940"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"ref42","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"xu","year":"2018","journal-title":"arXiv 1809 03327"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref43","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09563126.pdf?arnumber=9563126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:08Z","timestamp":1652194208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9563126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3117077","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}