{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:25:29Z","timestamp":1780424729204,"version":"3.54.1"},"reference-count":21,"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\/icassp49660.2025.10888208","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Sample-level Self-paced Learning to Tackle Multimodal Imbalance Problem"],"prefix":"10.1109","author":[{"given":"Ying","family":"Zhou","sequence":"first","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefeng","family":"Liang","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Xu","sequence":"additional","affiliation":[{"name":"Xidian University,Guangzhou Institute of Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Gao","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Advances in Conference and Workshop on Neural Information Processing Systems","volume":"34","author":"Huang"},{"key":"ref2","first-page":"24043","article-title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.122"},{"key":"ref4","first-page":"21630","article-title":"Perceptual score: What data modalities does your model perceive?","volume-title":"Conference and Workshop on Neural Information Processing Systems","volume":"34","author":"Gat"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref6","article-title":"Improving multi-modal learning with uni-modal teachers","author":"Du","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295094"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096641"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613846"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02030"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref15","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","volume-title":"International Conference on Learning Representations","author":"He"},{"issue":"2","key":"ref16","first-page":"20","article-title":"Openface: A general-purpose face recognition library with mobile applications","volume":"6","author":"Amos","year":"2016","journal-title":"CMU School of Computer Science"},{"key":"ref17","article-title":"Quantifying and enhancing multi-modal robustness with modality preference","volume-title":"International Conference on Learning Representations","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02581"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.937"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"}],"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\/10888208.pdf?arnumber=10888208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:53Z","timestamp":1774416113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888208","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}