{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T22:06:18Z","timestamp":1790201178120,"version":"4.1.0"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134577","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:00:56Z","timestamp":1784822456000},"page":"134577","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Bridging the capacity gap: Asymmetric realignment for robust multimodal learning"],"prefix":"10.1016","volume":"702","author":[{"given":"Yunfeng","family":"Kou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134577_bib0005","author":"Alemi"},{"key":"10.1016\/j.neucom.2026.134577_bib0010","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"609","article-title":"Look, listen and learn","author":"Arandjelovic","year":"2017"},{"key":"10.1016\/j.neucom.2026.134577_bib0015","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","article-title":"Crema-d: crowd-sourced emotional multimodal actors dataset","volume":"5","author":"Cao","year":"2014","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134577_bib0020","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10462-024-10759-6","article-title":"A survey on imbalanced learning: latest research, applications and future directions","volume":"57","author":"Chen","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.neucom.2026.134577_bib0025","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"958","article-title":"A survey on multimodal large language models for autonomous driving","author":"Cui","year":"2024"},{"key":"10.1016\/j.neucom.2026.134577_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20029","article-title":"Pmr: prototypical modal rebalance for multimodal learning","author":"Fan","year":"2023"},{"key":"10.1016\/j.neucom.2026.134577_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"16754","article-title":"Asymmetric reinforcing against multi-modal representation bias","author":"Gao","year":"2025"},{"key":"10.1016\/j.neucom.2026.134577_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26876","article-title":"Embracing unimodal aleatoric uncertainty for robust multimodal fusion","author":"Gao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134577_bib0045","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/JSAIT.2020.2991561","article-title":"The information bottleneck problem and its applications in machine learning","volume":"1","author":"Goldfeld","year":"2020","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"10.1016\/j.neucom.2026.134577_bib0050","author":"Goodfellow"},{"key":"10.1016\/j.neucom.2026.134577_bib0055","doi-asserted-by":"crossref","first-page":"2551","DOI":"10.1109\/TPAMI.2022.3171983","article-title":"Trusted multi-view classification with dynamic evidential fusion","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134577_bib0060","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Difference bonds consistency and complementarity to enhance multimodal representation learning","author":"He","year":"2025"},{"key":"10.1016\/j.neucom.2026.134577_bib0065","author":"Hua"},{"key":"10.1016\/j.neucom.2026.134577_bib0070","series-title":"International Conference on Machine Learning","first-page":"9226","article-title":"Modality competition: what makes joint training of multi-modal network fail in deep learning?(Provably)","author":"Huang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134577_bib0075","author":"Jiang"},{"key":"10.1016\/j.neucom.2026.134577_bib0080","series-title":"2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC)","first-page":"1643","article-title":"Adversarial attacks in multimodal systems: a practitioner\u2019s survey","author":"Kapoor","year":"2025"},{"key":"10.1016\/j.neucom.2026.134577_bib0085","author":"Kingma"},{"key":"10.1016\/j.neucom.2026.134577_bib0090","series-title":"The Thirty-Ninth Annual Conference on Neural Information Processing Systems","article-title":"Balancing multimodal training through game-theoretic regularization","author":"Kontras","year":"2025"},{"key":"10.1016\/j.neucom.2026.134577_bib0095","author":"Kontras"},{"key":"10.1016\/j.neucom.2026.134577_bib0100","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22214","article-title":"Boosting multi-modal model performance with adaptive gradient modulation","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134577_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126427","article-title":"GraphMFT: a graph network based multimodal fusion technique for emotion recognition in conversation","volume":"550","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134577_bib0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102216","article-title":"Adapt and explore: multimodal mixup for representation learning","volume":"105","author":"Lin","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134577_bib0115","series-title":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","first-page":"1039","article-title":"Multimodal pre-training with self-distillation for product understanding in e-commerce","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134577_bib0120","author":"Madry"},{"key":"10.1016\/j.neucom.2026.134577_bib0125","series-title":"International Conference on Multimedia Modeling","first-page":"15","article-title":"Sentiment analysis on multi-view social data","author":"Niu","year":"2016"},{"key":"10.1016\/j.neucom.2026.134577_bib0130","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8238","article-title":"Balanced multimodal learning via on-the-fly gradient modulation","author":"Peng","year":"2022"},{"issue":"2","key":"10.1016\/j.neucom.2026.134577_bib0135","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1109\/TPAMI.2024.3476487","article-title":"Robust multimodal learning with missing modalities via parameter-efficient adaptation","volume":"47","author":"Reza","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134577_bib0140","series-title":"European Conference on Computer Vision","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"Silberman","year":"2012"},{"key":"10.1016\/j.neucom.2026.134577_bib0145","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"Tian","year":"2018"},{"key":"10.1016\/j.neucom.2026.134577_bib0150","unstructured":"N. Tishby, F.C. Pereira, W. Bialek, The information bottleneck method, 2000. arXiv preprint physics\/0004057."},{"key":"10.1016\/j.neucom.2026.134577_bib0155","article-title":"DiagLLM: multimodal reasoning with large language model for explainable bearing fault diagnosis","volume":"68","author":"Wang","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.neucom.2026.134577_bib0160","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s12559-026-10558-x","article-title":"GPPLEA: guided polarity prompt learning for enhanced emotion analysis in low-sample social media environments","volume":"18","author":"Wang","year":"2026","journal-title":"Cogn. Comput."},{"issue":"3","key":"10.1016\/j.neucom.2026.134577_bib0165","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TCSS.2025.3613939","article-title":"CIME: contextual interaction-based multimodal emotion analysis with enhanced semantic information","volume":"12","author":"Wang","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.neucom.2026.134577_bib0170","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s12559-025-10463-9","article-title":"Contrastive-based removal of negative information in multimodal emotion analysis","volume":"17","author":"Wang","year":"2025","journal-title":"Cogn. Comput."},{"key":"10.1016\/j.neucom.2026.134577_bib0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.array.2025.100445","article-title":"RAFT: robust adversarial fusion transformer for multimodal sentiment analysis","author":"Wang","year":"2025","journal-title":"Array"},{"key":"10.1016\/j.neucom.2026.134577_bib0180","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12695","article-title":"What makes training multi-modal classification networks hard?","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134577_bib0185","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2250","article-title":"Improving multimodal learning via imbalanced learning","author":"Wei","year":"2025"},{"key":"10.1016\/j.neucom.2026.134577_bib0190","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27338","article-title":"Enhancing multimodal cooperation via sample-level modality valuation","author":"Wei","year":"2024"},{"key":"10.1016\/j.neucom.2026.134577_bib0195","author":"Wei"},{"key":"10.1016\/j.neucom.2026.134577_bib0200","series-title":"European Conference on Computer Vision","first-page":"71","article-title":"Diagnosing and re-learning for balanced multimodal learning","author":"Wei","year":"2024"},{"key":"10.1016\/j.neucom.2026.134577_bib0205","article-title":"Integrating audio\u2013visual text generation with contrastive learning for enhanced multimodal emotion analysis","author":"Xiang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134577_bib0210","series-title":"International Conference on Representation Learning","first-page":"15860","article-title":"Quantifying and enhancing multi-modal robustness with modality preference","author":"Yang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134577_bib0215","doi-asserted-by":"crossref","first-page":"7265","DOI":"10.1109\/TMM.2024.3362600","article-title":"Meta noise adaption framework for multimodal sentiment analysis with feature noise","volume":"26","author":"Yuan","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134577_bib0220","doi-asserted-by":"crossref","first-page":"6301","DOI":"10.1109\/TMM.2022.3207572","article-title":"Robust multimodal sentiment analysis via tag encoding of uncertain missing modalities","volume":"25","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134577_bib0225","series-title":"International Conference on Machine Learning","first-page":"41753","article-title":"Provable dynamic fusion for low-quality multimodal data","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134577_bib0230","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27456","article-title":"Multimodal representation learning by alternating unimodal adaptation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134577_bib0235","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9423","article-title":"Debiasing multimodal large language models via noise-aware preference optimization","author":"Zhang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134577_bib0240","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"2608","article-title":"Missing modality imagination network for emotion recognition with uncertain missing modalities","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neucom.2026.134577_bib0245","article-title":"TEMPO: training-time equilibration of modalities for per-sample optimization in multimodal sentiment","author":"Zhao","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134577_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102663","article-title":"Triple disentangled representation learning for multimodal affective analysis","volume":"114","author":"Zhou","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134577_bib0255","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Adaptive mask co-optimization for modal dependence in multimodal learning","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neucom.2026.134577_bib0260","article-title":"FMSA: few-shot multimodal sentiment analysis for social media via integrated prompt learning and vision-language models","author":"Zhu","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134577_bib0265","doi-asserted-by":"crossref","first-page":"56039","DOI":"10.1007\/s11042-023-17347-w","article-title":"Emotion recognition based on brain-like multimodal hierarchical perception","volume":"83","author":"Zhu","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.neucom.2026.134577_bib0270","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.134577_bib0275","article-title":"EUPA: embodied uncertainty-aware multimodal affect perception for consumer electronic systems","author":"Zhu","year":"2026","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.neucom.2026.134577_bib0280","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103268","article-title":"RMER-DT: robust multimodal emotion recognition in conversational contexts based on diffusion and transformers","volume":"123","author":"Zhu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134577_bib0285","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities","author":"Zuo","year":"2023"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019752?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019752?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:18:15Z","timestamp":1790198295000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226019752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":57,"alternative-id":["S0925231226019752"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134577","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bridging the capacity gap: Asymmetric realignment for robust multimodal learning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134577","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134577"}}