{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:59Z","timestamp":1777889699331,"version":"3.51.4"},"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\/501100001666","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222211"],"award-info":[{"award-number":["62222211"]}],"id":[{"id":"10.13039\/501100001666","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\/iccv51701.2025.00058","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"541-551","source":"Crossref","is-referenced-by-count":0,"title":["Open-Set Cross Modal Generalization via Multimodal Unified Representation"],"prefix":"10.1109","author":[{"given":"Hai","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Xia","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shulei","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanting","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Fang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengpeng","family":"Ji","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sashuai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Jin","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01594"},{"key":"ref2","first-page":"422","article-title":"Mohammad Reza Loghmani, and Tatiana Tommasi. On the effectiveness of image rotation for open set domain adaptation","volume-title":"In European conference on computer vision","author":"Bucci","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref4","first-page":"190","article-title":"and William B Dolan","volume-title":"Collecting highly parallel data for paraphrase evaluation. In Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen","year":"2011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref7","author":"Chen","year":"2023","journal-title":"Valor: Vision-audiolanguage omni-perception pretraining model and dataset"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_16"},{"key":"ref10","first-page":"2","article-title":"Simmmdg: A simple and effective framework for multi-modal domain generalization","volume":"36","author":"Dong","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"issue":"59","key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.119"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890125"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02088"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02309"},{"key":"ref22","first-page":"1","author":"Liu","year":"2021","journal-title":"Crossmodal discrete representation learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00107"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","first-page":"1","author":"Lu","year":"2022","journal-title":"Unified-io: A unified model for vision, language, and multi-modal tasks"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref28","author":"Pedersoli","year":"2022","journal-title":"Estimating visual information from audio through manifold learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00024"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3419055"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29407"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00950"},{"key":"ref35","first-page":"5","author":"Soomro","year":"2012","journal-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref39","author":"Tzeng","year":"2014","journal-title":"Deep domain confusion: Maximizing for domain invariance"},{"key":"ref40","article-title":"Vlmixer: Unpaired vision-language pre-training via cross-modal cutmix","volume-title":"In International Conference on Machine Learning, pages 2268022690. PMLR","author":"Wang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01062"},{"key":"ref42","first-page":"1","article-title":"Achieving cross modal generalization with multimodal unified representation","volume":"36","author":"Xia","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2020.05.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3353170"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2020.09.013"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref47","first-page":"1","article-title":"mixup: Beyond empirical risk management","volume-title":"In 6th Int. Conf. Learning Representations (ICLR)","author":"Zhang","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2915"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2760"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00833"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3223688"}],"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\/11443602.pdf?arnumber=11443602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:40Z","timestamp":1777612540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00058","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}