{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:27:20Z","timestamp":1783636040691,"version":"3.55.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890569","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Open-Modality Latent Modality Interaction Maximization for Audio-Visual Learning"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Yang","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Jiang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xi","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jizhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065823"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP49548.2020.9163474"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3119969"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01103"},{"key":"ref14","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"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096709"},{"key":"ref16","first-page":"21157","article-title":"u-hubert: Unified mixed-modal speech pretraining and zero-shot transfer to unlabeled modality","volume":"35","author":"Hsu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref19","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"ref24","article-title":"Robust cross-modal knowledge distillation for unconstrained videos","author":"Xia","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095836"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25378"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890569.pdf?arnumber=10890569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:51Z","timestamp":1774416111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890569","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}