{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T05:34:50Z","timestamp":1777354490714,"version":"3.51.4"},"reference-count":62,"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":"am","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":"NSF","award":["1908711"],"award-info":[{"award-number":["1908711"]}]},{"name":"NSF","award":["1849107"],"award-info":[{"award-number":["1849107"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3158066","type":"journal-article","created":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T20:26:08Z","timestamp":1646857568000},"page":"1738-1748","source":"Crossref","is-referenced-by-count":2,"title":["Learning to Minimize the Remainder in Supervised Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5135-0316","authenticated-orcid":false,"given":"Yan","family":"Luo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1239-4428","authenticated-orcid":false,"given":"Yongkang","family":"Wong","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan S.","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3054-8934","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"key":"ref12","first-page":"740","article-title":"Microsoft COCO: Common objects in context","volume":"8693","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/0701013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-5110-1_9"},{"key":"ref59","author":"mohri","year":"2012","journal-title":"Foundations of Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref58","first-page":"62","article-title":"Greedy algorithm","volume":"2","author":"black","year":"2005","journal-title":"Dictionary of Algorithms and Data Structures"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009958918582"},{"key":"ref52","author":"timan","year":"1963","journal-title":"Theory of Approximation of Functions of a Real Variable"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.2307\/2003844"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.6028\/jres.043.042"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref16","first-page":"7654","article-title":"The anisotropic noise in stochastic gradient descent: Its behavior of escaping from sharp minima and regularization effects","author":"zhu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","article-title":"UCI machine learning repository","author":"asuncion","year":"2007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0095-0696(78)90006-2"},{"key":"ref51","author":"achieser","year":"1956","journal-title":"Theory of Approximation"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963387"},{"key":"ref46","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_30"},{"key":"ref48","first-page":"737","article-title":"Hyperparameter optimization with approximate gradient","author":"pedregosa","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"foret","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2903628"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093343"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01295-1"},{"key":"ref49","first-page":"6467","article-title":"Gradient episodic memory for continual learning","author":"lopez-paz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2859791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2780770"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2293424"},{"key":"ref35","article-title":"An image is worth 16 × 16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","author":"tan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"ref36","article-title":"Mlp-mixer: An all-mlp architecture for vision","author":"tolstikhin","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"748","article-title":"Learning to learn without gradient descent by gradient descent","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/363"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477042"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2187436"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2351788"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2282128"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1142\/4325","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"luo","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/17M1114296"},{"key":"ref25","first-page":"18795","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"zhuang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-7152(96)00140-X"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","first-page":"249","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"hinton","year":"2012","journal-title":"CITE"},{"key":"ref28","first-page":"1233","article-title":"A generic approach for escaping saddle points","author":"reddi","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref27","first-page":"1724","article-title":"How to escape saddle points efficiently","author":"jin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"9593","article-title":"Lookahead optimizer: K steps forward, 1 step back","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","author":"nesterov","year":"2003","journal-title":"Introductory Lectures on Convex Optimization A Basic Course"},{"key":"ref62","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"0","journal-title":"European Conference on Computer Vision"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6046\/10016790\/9732209-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09732209.pdf?arnumber=9732209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T16:52:24Z","timestamp":1700326344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9732209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3158066","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}