{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:02:11Z","timestamp":1779235331032,"version":"3.51.4"},"reference-count":41,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02124","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["Boosting Multimodal Learning via Disentangled Gradient Learning"],"prefix":"10.1109","author":[{"given":"Shicai","family":"Wei","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunbo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"issue":"4","key":"ref3","first-page":"377","article-title":"Gur, Ani Nenkova, and Ragini Verma","volume":"5","author":"Cao","year":"2014","journal-title":"Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE transactions on affective computing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00394"},{"key":"ref8","article-title":"Improving multimodal learning with uni-modal teachers","volume-title":"arXiv preprint","author":"Du","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"ref10","first-page":"103","article-title":"Garcia, Pietro Morerio, and Vittorio Murino. Modality distillation with multiple stream networks for action recognition.","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Nuno","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.05.011"},{"key":"ref12","article-title":"Deep multimodal multilinear fusion with highorder polynomial pooling","volume":"32","author":"Hou","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref14","article-title":"Reconboost: Boosting can achieve modality reconcilement","volume-title":"arXiv preprint","author":"Hua","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3060167"},{"key":"ref16","first-page":"13289","article-title":"Mmtm: Multimodal transfer module for cnn fusion","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Reza","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02030"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00202"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref20","first-page":"18","article-title":"Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto. librosa: Audio and music signal analysis in python.","volume-title":"Proceedings of the 14th python in science conference","author":"Brian","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00146"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486455"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01919"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3265650"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_3"},{"key":"ref32","article-title":"Mmpareto: Boosting multimodal learning with innocent unimodal assistance","volume-title":"arXiv preprint","author":"Wei","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01142-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096655"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02592"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_11"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0199-z"}],"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\/11444576.pdf?arnumber=11444576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:13Z","timestamp":1777530013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02124","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}