{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:01:28Z","timestamp":1752192088197,"version":"3.41.2"},"reference-count":58,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen-Hong Kong-Macau Science & Technology Category C Project","award":["SGDX20220530111205037"],"award-info":[{"award-number":["SGDX20220530111205037"]}]},{"name":"Hong Kong RGC General Research Fund Project","award":["11213124"],"award-info":[{"award-number":["11213124"]}]},{"name":"Collaborative Research Fund Project","award":["C1049-24GF"],"award-info":[{"award-number":["C1049-24GF"]}]},{"name":"Hong Kong ITC Innovation and Technology Fund Project","award":["ITS\/034\/22MS"],"award-info":[{"award-number":["ITS\/034\/22MS"]}]},{"name":"Guangdong Provincial Basic and Applied Basic Research - Offshore Wind Power Joint Fund Project","award":["2022A1515240066"],"award-info":[{"award-number":["2022A1515240066"]}]},{"name":"Guangdong Province Technological Project","award":["2023A0505030014"],"award-info":[{"award-number":["2023A0505030014"]}]},{"name":"InnoHK initiative"},{"name":"The Government of the HKSAR"},{"name":"Laboratory for AI-Powered Financial Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535276","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T13:44:24Z","timestamp":1738071864000},"page":"4284-4296","source":"Crossref","is-referenced-by-count":0,"title":["Domain Generalization Study of Empirical Risk Minimization From Causal Perspectives"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4412-4684","authenticated-orcid":false,"given":"Zhenling","family":"Mo","sequence":"first","affiliation":[{"name":"Department of Data Science, College of Computing, City University of Hong Kong, Kowloon, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2717-5033","authenticated-orcid":false,"given":"Zijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Data Science, College of Computing, City University of Hong Kong, Kowloon, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0558-2279","authenticated-orcid":false,"given":"Kwok-Leung","family":"Tsui","sequence":"additional","affiliation":[{"name":"Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, USA"}]}],"member":"263","reference":[{"article-title":"Invariant risk minimization","year":"2020","author":"Arjovsky","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1981.1056373"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3136717"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3160057"},{"key":"ref6","first-page":"23519","article-title":"Towards a theoretical framework of out-of-distribution generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ye"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3121564"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3195549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3263549"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3223783"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"article-title":"Finding lost DG: Explaining domain generalization via model complexity","year":"2022","author":"Li","key":"ref13"},{"key":"ref14","first-page":"1","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulrajani","year":"2022"},{"volume-title":"Causality: Models, Reasoning, and Inference","year":"2000","author":"Pearl","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1142\/s0219525908001465"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00826"},{"key":"ref18","first-page":"1","article-title":"Empirical or invariant risk minimization A sample complexity perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ahuja","year":"2022"},{"key":"ref19","first-page":"3438","article-title":"Invariance principle meets information bottleneck for out-of-distribution generalization","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Ahuja","year":"2021"},{"key":"ref20","first-page":"28131","article-title":"An empirical investigation of domain generalization with empirical risk minimizers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Vedantam"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01849"},{"key":"ref22","first-page":"1","article-title":"Understanding the failure modes of out-of-distribution generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagarajan","year":"2022"},{"article-title":"Understanding the behaviour of the empirical cross-entropy beyond the training distribution","year":"2019","author":"Vera","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01555"},{"key":"ref25","first-page":"145","article-title":"Invariant risk minimization games","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Ahuja","year":"2020"},{"article-title":"Meta-learned invariant risk minimization","year":"2021","author":"Bae","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467324"},{"key":"ref28","first-page":"7313","article-title":"Domain generalization using causal matching","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Mahajan","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01108"},{"key":"ref30","first-page":"4555","article-title":"Selecting data augmentation for simulating interventions","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ilse","year":"2021"},{"article-title":"Mixup: Beyond empirical risk minimization","year":"2017","author":"Zhang","key":"ref31"},{"article-title":"RegMixup: Mixup as a regularizer can surprisingly improve accuracy and out distribution robustness","year":"2022","author":"Pinto","key":"ref32"},{"article-title":"Manifold mixup: Better representations by interpolating hidden states","year":"2019","author":"Verma","key":"ref33"},{"key":"ref34","first-page":"16846","article-title":"Recovering latent causal factor for generalization to distributional shifts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"article-title":"Learning causal semantic representation for out-of-distribution prediction","year":"2021","author":"Liu","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_33"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3279990"},{"volume-title":"Elements of Information Theory","year":"1991","author":"Thomas","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/13-aos1145"},{"key":"ref40","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref41","first-page":"725","article-title":"Unreproducible research is reproducible","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Bouthillier","year":"2019"},{"article-title":"Torch.Manualseed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision","year":"2021","author":"Picard","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref44"},{"article-title":"Do CIFAR-10 classifiers generalize to CIFAR-10","year":"2018","author":"Recht","key":"ref45"},{"article-title":"Wide residual networks","year":"2017","author":"Zagoruyko","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.36001\/phme.2016.v3i1.1577"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2023.109175"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.107833"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.106913"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1164\/ajrccm.162.3.9905104"},{"issue":"1","key":"ref52","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2974574"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref56","first-page":"440","article-title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","volume-title":"Proc. 45th Annu. Meeting Assoc. Comput. Linguistics","author":"Blitzer","year":"2007"},{"article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","year":"2020","author":"Sanh","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/18.79902"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10856554.pdf?arnumber=10856554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:02Z","timestamp":1752103202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535276","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}