{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:20:31Z","timestamp":1780957231522,"version":"3.54.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222211"],"award-info":[{"award-number":["62222211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02088","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22488-22498","source":"Crossref","is-referenced-by-count":2,"title":["Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations"],"prefix":"10.1109","author":[{"given":"Hai","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Xia","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sashuai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanting","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shulei","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01594"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00216"},{"key":"ref3","first-page":"21189","article-title":"Exploiting domain-specific features to enhance domain generalization","volume":"34","author":"Bui","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref7","first-page":"1779","article-title":"Club: A contrastive log-ratio upper bound of mutual information","volume-title":"International conference on machine learning","author":"Cheng","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"ref9","article-title":"MMAction Contributors","volume-title":"Openmmlabs next generation video understanding toolbox and benchmark","year":"2020"},{"key":"ref10","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_16"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2133"},{"key":"ref15","article-title":"Ace: A generative cross-modal retrieval framework with coarse-to-fine semantic modeling","author":"Fang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref17","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","journal-title":"arXiv preprint"},{"issue":"59","key":"ref18","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"Journal of machine learning research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.195"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/wacvw58289.2023.00042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Unlocking the potential of multimodal unified discrete representation through training-free codebook optimization and hierarchical alignment","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890125"},{"key":"ref25","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably)","volume-title":"International conference on machine learning","author":"Huang","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref27","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref30","first-page":"3118","article-title":"Domain generalization for medical imaging classification with linear-dependency regularization","volume":"33","author":"Li","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Crossmodal discrete representation learning","author":"Liu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00107"},{"key":"ref33","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lu","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00277"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2022.3224067"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00024"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01657"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29407"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref44","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178128"},{"key":"ref46","article-title":"Vlmixer: Unpaired vision-language pre-training via cross-modal cutmix","volume-title":"International Conference on Machine Learning","author":"Wang","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2024.00.310"},{"key":"ref48","article-title":"Achieving cross modal generalization with multimodal unified representation","author":"Xia","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2760"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7003"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444327.pdf?arnumber=11444327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:01Z","timestamp":1777531561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02088","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}