{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T02:39:07Z","timestamp":1774579147262,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1704337"],"award-info":[{"award-number":["IIS-1704337"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1722847"],"award-info":[{"award-number":["IIS-1722847"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1813709"],"award-info":[{"award-number":["IIS-1813709"]}],"id":[{"id":"10.13039\/100000001","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":[[2021,9]]},"DOI":"10.1109\/tcsvt.2020.3038720","type":"journal-article","created":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T21:53:14Z","timestamp":1605649994000},"page":"3433-3443","source":"Crossref","is-referenced-by-count":74,"title":["Grounding-Tracking-Integration"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5808-0889","authenticated-orcid":false,"given":"Zhengyuan","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0978-9004","authenticated-orcid":false,"given":"Tushar","family":"Kumar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6355-6474","authenticated-orcid":false,"given":"Tianlang","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5606-7122","authenticated-orcid":false,"given":"Jingsong","family":"Su","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2910529"},{"key":"ref33","first-page":"784","article-title":"Acquisition of localization confidence for accurate object detection","author":"jiang","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01043"},{"key":"ref30","first-page":"10668","article-title":"Where does it exist: Spatio-temporal video grounding for multi-form sentences","author":"zhang","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00537"},{"key":"ref28","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"chen","year":"2018","journal-title":"arXiv 1812 03426"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2516982"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01069"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref21","article-title":"Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking","author":"wang","year":"2018","journal-title":"arXiv 1811 10014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref40","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.490"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.162"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1177352.1177355"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_13"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00937"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.443"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"ref44","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/76\/9527373\/9261416-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9527373\/09261416.pdf?arnumber=9261416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:22Z","timestamp":1652194222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9261416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":49,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.3038720","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}