{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T23:15:23Z","timestamp":1792797323304,"version":"4.5.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["4182056"],"award-info":[{"award-number":["4182056"]}]},{"name":"Zhijiang Lab's International Talent Fund for Young Professionals"},{"name":"Beijing Municipal Education Commission","id":[{"id":"https:\/\/ror.org\/04bpn6s66","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,5,1]]},"DOI":"10.1109\/tpami.2019.2956703","type":"journal-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T16:10:55Z","timestamp":1575043855000},"page":"1515-1529","source":"Crossref","is-referenced-by-count":193,"title":["Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking"],"prefix":"10.1109","volume":"43","author":[{"given":"Xingping","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatih","family":"Porikli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref71","first-page":"103","article-title":"Distractor-aware siamese networks for visual object tracking","author":"zhu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref70","first-page":"188","article-title":"MEEM: Robust tracking via multiple experts using entropy minimization","author":"zhang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref39","first-page":"254","article-title":"A scale adaptive kernel correlation filter tracker with feature integration","author":"li","year":"2014","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref38","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"li","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref33","first-page":"564","article-title":"The visual object tracking VOT2015 challenge results","author":"kristan","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis Workshops"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299094"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.56"},{"key":"ref36","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2898567"},{"key":"ref34","first-page":"3","article-title":"The sixth visual object tracking VOT2018 challenge results","author":"kristan","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"ref62","first-page":"113","article-title":"The enhanced flock of trackers","author":"voj\u00ed?","year":"2014","journal-title":"Registration and Recognition in Images and Videos"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.531"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.03.025"},{"key":"ref28","first-page":"459","article-title":"Triplet loss in siamese network for object tracking","author":"dong","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.21"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.510"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref29","first-page":"127","article-title":"Tree-structured reinforcement learning for sequential object localization","author":"jie","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","article-title":"Object tracking benchmark","volume":"37","author":"yi","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.148"},{"key":"ref2","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","author":"bergstra","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.196"},{"key":"ref22","first-page":"749","article-title":"Learning to track at 100 FPS with deep regression networks","author":"held","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","article-title":"Using deep Q-learning to control optimization hyperparameters","author":"hansen","year":"2016","journal-title":"arXiv 1602 04062"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref23","first-page":"702","article-title":"Exploiting the circulant structure of tracking-by-detection with kernels","author":"henriques","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","first-page":"754","article-title":"An efficient approach for assessing hyperparameter importance","author":"hoos","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298675"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.462"},{"key":"ref51","first-page":"1","article-title":"Tunability: Importance of hyperparameters of machine learning algorithms","volume":"20","author":"probst","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.43"},{"key":"ref57","first-page":"2171","article-title":"Scalable Bayesian optimization using deep neural networks","author":"snoek","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref56","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref55","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.466"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.65"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.490"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.07.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2795740"},{"key":"ref14","first-page":"472","article-title":"Beyond correlation filters: Learning continuous convolution operators for visual tracking","author":"danelljan","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.733"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.585"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.128"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.129"},{"key":"ref19","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"ref5","first-page":"169","article-title":"Heuristically accelerated reinforcement learning: Theoretical and experimental results","author":"bianchi","year":"2012","journal-title":"Proc 20th Eur Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.05.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299177"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref47","first-page":"244","article-title":"Clustering local motion estimates for robust and efficient object tracking","author":"maresca","year":"2014","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2482905"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.515"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2631884"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9393625\/08918068.pdf?arnumber=8918068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:49:21Z","timestamp":1652179761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8918068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2956703","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,1]]}}}