{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:48:00Z","timestamp":1767332880533,"version":"3.48.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3648122","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T18:46:53Z","timestamp":1766602013000},"page":"217632-217643","source":"Crossref","is-referenced-by-count":0,"title":["L2CU: Learning to Complement Unseen Users"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4887-7122","authenticated-orcid":false,"given":"Dileepa","family":"Pitawela","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5571-6220","authenticated-orcid":false,"given":"Gustavo","family":"Carneiro","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0873-2698","authenticated-orcid":false,"given":"Hsiang-Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6147","article-title":"Predict responsibly: Improving fairness and accuracy by learning to defer","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Madras"},{"key":"ref2","first-page":"10520","article-title":"Who should predict? Exact algorithms for learning to defer to humans","volume-title":"Proc. 26th Int. Conf. Artif. Intell. Statist.","author":"Mozannar"},{"key":"ref3","article-title":"FiFAR: A fraud detection dataset for learning to defer","author":"Alves","year":"2023","journal-title":"arXiv:2312.13218"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2111547119"},{"key":"ref6","article-title":"Expert-agnostic learning to defer","author":"Strong","year":"2025","journal-title":"arXiv:2502.10533"},{"key":"ref7","first-page":"3475","article-title":"Learning to defer to a population: A meta-learning approach","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Tailor"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2017.2732506"},{"key":"ref9","article-title":"The algorithmic automation problem: Prediction, triage, and human effort","author":"Raghu","year":"2019","journal-title":"arXiv:1903.12220"},{"key":"ref10","first-page":"9140","article-title":"Differentiable learning under triage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Okati"},{"key":"ref11","first-page":"7076","article-title":"Consistent estimators for learning to defer to an expert","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"1","author":"Mozannar"},{"key":"ref12","first-page":"22184","article-title":"Calibrated learning to defer with one-vs-all classifiers","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref13","first-page":"1","article-title":"Probabilistic learning to defer: Handling missing expert annotations and controlling workload distribution","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Nguyen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112376"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300641"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445432"},{"key":"ref18","first-page":"4421","article-title":"Combining human predictions with model probabilities via confusion matrices and calibration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kerrigan"},{"key":"ref19","first-page":"4004","article-title":"Uncalibrated models can improve human-AI collaboration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vodrahalli"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"article-title":"CROWDLAB: Supervised learning to infer consensus labels and quality scores for data with multiple annotators","volume-title":"Proc. NeurIPS Human Loop Learn. Workshop","author":"Goh","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00945"},{"key":"ref23","first-page":"2224","article-title":"Robust and sparse fuzzy K-means clustering","volume-title":"Proc. Twenty-Fifth Int. Joint Conf. Artif. Intell.","author":"Xu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CICN.2010.80"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref26"},{"article-title":"Learning with noisy labels revisited: A study using real-world human annotations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wei","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00971"},{"article-title":"Is the performance of my deep network too good to be true? A direct approach to estimating the Bayes error in binary classification","volume-title":"Proc. ICLR","author":"Ishida","key":"ref29"},{"key":"ref30","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. NIPS","author":"Zhang","key":"ref36"},{"article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref39","first-page":"4804","article-title":"Beyond synthetic noise: Deep learning on controlled noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Jiang"},{"key":"ref40","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","key":"ref41"},{"key":"ref42","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref43","first-page":"4409","article-title":"Instance-dependent label-noise learning under a structural causal model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00046"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_21"},{"key":"ref46","first-page":"21475","article-title":"Identifiability of label noise transition matrix","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref47","article-title":"Fast dawid-skene: A fast vote aggregation scheme for sentiment classification","author":"Sinha","year":"2018","journal-title":"arXiv:1803.02781"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01216"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25620"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29613"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3168696"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3137752"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3388209"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11314492.pdf?arnumber=11314492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:45:42Z","timestamp":1767332742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11314492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3648122","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}