{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T04:59:11Z","timestamp":1784177951608,"version":"3.55.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Technological Innovation 2030 Megaproject New Generation Artificial Intelligence of China","award":["2020AAA0106501"],"award-info":[{"award-number":["2020AAA0106501"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2059"],"award-info":[{"award-number":["U22B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176079"],"award-info":[{"award-number":["62176079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106061"],"award-info":[{"award-number":["62106061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["YQ2022F005"],"award-info":[{"award-number":["YQ2022F005"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3290477","type":"journal-article","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T17:26:37Z","timestamp":1687973197000},"page":"1957-1968","source":"Crossref","is-referenced-by-count":8,"title":["DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3437-8899","authenticated-orcid":false,"given":"Tingting","family":"Wu","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5838-0320","authenticated-orcid":false,"given":"Xiao","family":"Ding","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6769-2115","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4466-0516","authenticated-orcid":false,"given":"Jinglong","family":"Gao","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minji","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Du","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1481-9630","authenticated-orcid":false,"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.99"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2312251"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2684626"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2937181"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001521"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref14","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. 23rd Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"ref16","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang","year":"2018"},{"key":"ref17","first-page":"11095","article-title":"Data parameters: A new family of parameters for learning a differentiable curriculum","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Saxena","year":"2019"},{"key":"ref18","article-title":"Curriculum loss: Robust learning and generalization against label corruption","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lyu","year":"2020"},{"key":"ref19","article-title":"An empirical study of example forgetting during deep neural network learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Toneva","year":"2019"},{"key":"ref20","first-page":"4308","article-title":"SuperLoss: A generic loss for robust curriculum learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Castells","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref22","first-page":"115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bergstra","year":"2013"},{"key":"ref23","article-title":"MNIST handwritten digit database","volume":"2","author":"LeCun","year":"2010","journal-title":"ATT Labs"},{"key":"ref24","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref26","first-page":"8536","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Han","year":"2018"},{"key":"ref27","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref29","article-title":"Noise against noise: Stochastic label noise helps combat inherent label noise","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref30","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.463"},{"key":"ref32","article-title":"Visualizing and understanding curriculum learning for long short-term memory networks","author":"Cirik","year":"2016"},{"key":"ref33","first-page":"751","article-title":"From baby steps to leapfrog: How less is more in unsupervised dependency parsing","volume-title":"Proc. Hum. Lang. Technol.: Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Spitkovsky","year":"2010"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.374"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","first-page":"5754","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"issue":"8","key":"ref38","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref39","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref40","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref41","first-page":"240","article-title":"Non-stochastic best arm identification and hyperparameter optimization","volume-title":"Proc. Artif. Intell. Statist.","author":"Jamieson","year":"2016"},{"issue":"1","key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.542"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6513"},{"key":"ref46","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hacohen","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093408"},{"key":"ref48","first-page":"3822","article-title":"Breaking the curse of space explosion: Towards efficient NAS with curriculum search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.06.029"},{"key":"ref51","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren","year":"2018"},{"key":"ref52","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00742"},{"key":"ref54","first-page":"19523","article-title":"Beyond neural scaling laws: Beating power law scaling via data pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sorscher","year":"2022"},{"key":"ref55","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paul","year":"2021"},{"key":"ref56","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kalantidis","year":"2020"},{"key":"ref57","article-title":"Semantic redundancies in image-classification datasets: The 10 you dont need","author":"Birodkar","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3133268"},{"key":"ref59","article-title":"Self: Learning to filter noisy labels with self-ensembling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nguyen","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10167857.pdf?arnumber=10167857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:27:33Z","timestamp":1706758053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10167857\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3290477","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}