{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:22:45Z","timestamp":1780669365322,"version":"3.54.1"},"reference-count":68,"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":["62306064"],"award-info":[{"award-number":["62306064"]}],"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\/iccv51701.2025.02272","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24507-24517","source":"Crossref","is-referenced-by-count":4,"title":["Unbiased Missing-Modality Multimodal Learning"],"prefix":"10.1109","author":[{"given":"Ruiting","family":"Dai","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxi","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yandong","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisi","family":"Mo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Qin","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"He","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.38094\/jastt20291"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref3","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"International conference on machine learning","author":"Andrew","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref5","article-title":"Conditional image generation with score-based diffusion models","author":"Batzolis","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3145812"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219963"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3486610"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Applied missing data analysis","author":"Enders","year":"2022","journal-title":"Guilford Publications"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00658"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28690"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/344"},{"key":"ref16","article-title":"Semantic compositional learning for low-shot scene graph generation","author":"He","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3224872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.01.146"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449944"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0697"},{"key":"ref22","article-title":"Facial expression analysis","year":"2017","journal-title":"Website"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/16113"},{"key":"ref24","article-title":"Continuous diffusion model for language modeling","author":"Jo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Show, ask, attend, and answer: A strong baseline for visual question answering","author":"Kazemi","year":"2017","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102846"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI60581.2025.10980985"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105592"},{"key":"ref29","article-title":"Image inpainting via iteratively decoupled probabilistic modeling","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02570-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2967504"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8405-3_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2015.06.002"},{"key":"ref36","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"689","article-title":"Multimodal deep learning","author":"Ngiam","year":"2011","journal-title":"ICML"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3091214"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.22489\/CinC.2023.227"},{"key":"ref43","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02566"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380259"},{"key":"ref48","article-title":"Unified directly denoising for both variance preserving and variance exploding diffusion models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403234"},{"key":"ref50","first-page":"1083","article-title":"On deep multi-view representation learning","volume-title":"International conference on machine learning","author":"Wang","year":"2015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02013"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0748"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"ref54","article-title":"Diffx: Guide your layout to cross-modal generative modeling","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"A comprehensive survey on deep multimodal learning with missing modality","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"A survey on multiview learning","author":"Xu","year":"2013","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_27"},{"key":"ref58","article-title":"Cross-modal contextualized diffusion models for text-guided visual generation and editing","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref61","article-title":"Text-to-image cross-modal generation: A systematic review","author":"\u017belaszczyk","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00089"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03343-4"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.02.033"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref66","article-title":"Mitigating modality prior-induced hallucinations in multimodal large language models via deciphering attention causality","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160060"}],"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\/11446068.pdf?arnumber=11446068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:15Z","timestamp":1777611495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02272","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}