{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:36:53Z","timestamp":1783226213487,"version":"3.54.6"},"reference-count":59,"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\/501100012166","name":"National Key Research & Development Program of China","doi-asserted-by":"publisher","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education, Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP20124-0013"],"award-info":[{"award-number":["MOE-T2EP20124-0013"]}],"id":[{"id":"10.13039\/501100001459","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\/iccv51701.2025.00403","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4232-4241","source":"Crossref","is-referenced-by-count":2,"title":["Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation"],"prefix":"10.1109","author":[{"given":"Jie","family":"Xu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhao","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Niu","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2875385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icdm.2012.93"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bts220"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01536"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2016.2607421"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref9","first-page":"8536","article-title":"Coteaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"In NeurIPS","author":"Han","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00947"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3247939"},{"issue":"3","key":"ref12","first-page":"3877","article-title":"Unsupervised contrastive cross-modal hashing","volume":"45","author":"Hu","year":"2023","journal-title":"TPAMI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.35"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01116"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref17","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images. Toronto, ON, Canada"},{"key":"ref18","first-page":"1360","article-title":"Learning hash functions for cross-view similarity search","author":"Kumar","year":"2011","journal-title":"In IJCAI"},{"key":"ref19","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"In NeurIPS","author":"Li","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41795-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56424-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396381"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.672"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2879108"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_38"},{"key":"ref26","first-page":"4697","article-title":"Simple contrastive multi-view clustering with data-level fusion","author":"Luo","year":"2024","journal-title":"In IJCAI"},{"key":"ref27","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"In Proceedings of the Berkeley Symposium on Mathematical Statistics and Probability","author":"MacQueen","year":"1967"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5377-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3439726"},{"key":"ref30","first-page":"1","article-title":"Parameter-free multiview $k$-means clustering with coordinate descent method","author":"Nie","year":"2024","journal-title":"TNNLS"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"How do images align and complement lidar? towards a harmonized multi-modal 3d panoptic segmentation","volume-title":"In ICML","author":"Pan","year":"2025"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In ICML","author":"Radford","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3543848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00312"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICWAPR.2007.4421632"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00030"},{"key":"ref40","first-page":"21090","article-title":"Deep safe incomplete multi-view clustering: Theorem and algorithm","volume-title":"In ICML","author":"Tang","year":"2022"},{"key":"ref41","first-page":"21090","article-title":"Deep safe incomplete multi-view clustering: Theorem and algorithm","volume-title":"In ICML","author":"Tang","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-023-01304-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00131"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1198\/10618600152418584"},{"key":"ref46","article-title":"Attention is all you need","volume-title":"In NeurIPS","author":"Vaswani","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680564"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3203630"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32863"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01558"},{"key":"ref51","first-page":"1119","article-title":"Self-weighted contrastive learning among multiple views for mitigating representation degeneration","volume-title":"In NeurIPS","author":"Xu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3193569"},{"issue":"5","key":"ref53","first-page":"2402","article-title":"Deep partial multi-view learning","volume":"44","author":"Zhang","year":"2022","journal-title":"TPAMI"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11263"},{"key":"ref55","first-page":"41753","article-title":"Provable dynamic fusion for low-quality multimodal data","volume-title":"In ICML","author":"Zhang","year":"2023"},{"key":"ref56","article-title":"Multimodal fusion on low-quality data: A comprehensive survey","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655011"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609610"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01463"}],"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\/11445331.pdf?arnumber=11445331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:33Z","timestamp":1777612713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00403","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}