{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T12:08:36Z","timestamp":1779192516786,"version":"3.51.4"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306317"],"award-info":[{"award-number":["62306317"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["LJ212510165019"],"award-info":[{"award-number":["LJ212510165019"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.inffus.2026.104368","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T17:40:15Z","timestamp":1776015615000},"page":"104368","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Modality-aware fusion with alignment and balancing for robust multimodal emotion recognition"],"prefix":"10.1016","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2138-6286","authenticated-orcid":false,"given":"Cheng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruisi","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yikang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyu","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104368_bib0001","series-title":"Navigating Cyber-Physical Systems With Cutting-Edge Technologies","first-page":"235","article-title":"Enhancing human-computer interaction through artificial intelligence and machine learning: a comprehensive review","author":"Singh","year":"2025"},{"key":"10.1016\/j.inffus.2026.104368_bib0002","doi-asserted-by":"crossref","DOI":"10.1109\/TAFFC.2025.3583594","article-title":"Cross-modal knowledge distillation for enhanced unimodal emotion recognition","author":"Jia","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104368_bib0003","series-title":"Social and Emotional Learning","first-page":"84","article-title":"Challenges and opportunities in the applied assessment of student social and emotional learning","author":"McKown","year":"2025"},{"issue":"12","key":"10.1016\/j.inffus.2026.104368_bib0004","doi-asserted-by":"crossref","first-page":"18565","DOI":"10.1109\/TNNLS.2023.3319315","article-title":"Hybrid network using dynamic graph convolution and temporal self-attention for EEG-based emotion recognition","volume":"35","author":"Cheng","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2026.104368_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111241","article-title":"Driver multi-task emotion recognition network based on multi-modal facial video analysis","volume":"161","author":"Xiang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.inffus.2026.104368_bib0006","doi-asserted-by":"crossref","first-page":"3425","DOI":"10.1109\/TII.2023.3306575","article-title":"An enhanced protective relaying scheme for TCSC compensated line connecting DFIG-based wind farm","volume":"20","author":"Mohanty","year":"2023","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.inffus.2026.104368_bib0007","article-title":"Decision tree approach for fault detection in a TCSC compensated line during power swing","volume":"146","author":"Mohanty","year":"2023","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"10.1016\/j.inffus.2026.104368_bib0008","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"},{"key":"10.1016\/j.inffus.2026.104368_bib0009","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"7551","article-title":"Modality-balanced learning for multimedia recommendation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104368_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102843","article-title":"A multimodal data generation method for imbalanced classification with dual-discriminator constrained diffusion model and adaptive sample selection strategy","volume":"117","author":"Li","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104368_bib0011","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"},{"issue":"5","key":"10.1016\/j.inffus.2026.104368_bib0012","doi-asserted-by":"crossref","first-page":"3673","DOI":"10.1109\/TPAMI.2025.3535617","article-title":"MulFS-CAP: multimodal fusion-supervised cross-modality alignment perception for unregistered infrared-visible image fusion","volume":"47","author":"Li","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"10.1016\/j.inffus.2026.104368_bib0013","doi-asserted-by":"crossref","first-page":"4643","DOI":"10.1109\/TMM.2025.3535344","article-title":"DISD-Net: a dynamic interactive network with self-distillation for cross-subject multi-modal emotion recognition","volume":"27","author":"Cheng","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104368_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2025.108633","article-title":"Cross-modal alignment and contrastive learning for enhanced cancer survival prediction","volume":"263","author":"Li","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.inffus.2026.104368_bib0015","unstructured":"C. Qian, S. Xing, S. Li, Y. Zhao, Z. Tu, DecAlign: hierarchical cross-modal alignment for decoupled multimodal representation learning, arXiv: 2503.11892(2025)."},{"issue":"5","key":"10.1016\/j.inffus.2026.104368_bib0016","doi-asserted-by":"crossref","first-page":"6672","DOI":"10.1109\/TCSS.2024.3412074","article-title":"Dense graph convolutional with joint cross-attention network for multimodal emotion recognition","volume":"1","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"10.1016\/j.inffus.2026.104368_bib0017","series-title":"ICASSP 2025\u20132025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Enhancing multimodal emotion recognition through multi-granularity cross-modal alignment","author":"Wang","year":"2025"},{"issue":"3","key":"10.1016\/j.inffus.2026.104368_bib0018","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1109\/TAFFC.2024.3357656","article-title":"CFDA-CSF: a multi-modal domain adaptation method for cross-subject emotion recognition","volume":"15","author":"Jim\u00e9nez-Guarneros","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104368_bib0019","series-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"8301","article-title":"Inter-modality and intra-sample alignment for multi-modal emotion recognition","author":"Wang","year":"2024"},{"issue":"3","key":"10.1016\/j.inffus.2026.104368_bib0020","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1109\/TAFFC.2024.3354382","article-title":"A multi-level alignment and cross-modal unified semantic graph refinement network for conversational emotion recognition","volume":"15","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104368_bib0021","doi-asserted-by":"crossref","first-page":"4298","DOI":"10.1109\/TASLP.2024.3434495","article-title":"Masked graph learning with recurrent alignment for multimodal emotion recognition in conversation","volume":"32","author":"Meng","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang Process."},{"key":"10.1016\/j.inffus.2026.104368_bib0022","series-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"11051","article-title":"Fine-grained disentangled representation learning for multimodal emotion recognition","author":"Sun","year":"2024"},{"key":"10.1016\/j.inffus.2026.104368_bib0023","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"14314","article-title":"EMOE: modality-specific enhanced dynamic emotion experts","author":"Fang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104368_bib0024","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"9330","article-title":"Ada2I: enhancing modality balance for multimodal conversational emotion recognition","author":"Nguyen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104368_bib0025","series-title":"Findings of the Association for Computational Linguistics ACL 2024","first-page":"14448","article-title":"Amanda: adaptively modality-balanced domain adaptation for multimodal emotion recognition","author":"Zhang","year":"2024"},{"issue":"12","key":"10.1016\/j.inffus.2026.104368_bib0026","doi-asserted-by":"crossref","first-page":"6472","DOI":"10.1109\/TAI.2024.3445325","article-title":"Deep imbalanced learning for multimodal emotion recognition in conversations","volume":"5","author":"Meng","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"1","key":"10.1016\/j.inffus.2026.104368_bib0027","doi-asserted-by":"crossref","first-page":"5473","DOI":"10.1038\/s41598-025-89202-x","article-title":"MemoCMT: multimodal emotion recognition using cross-modal transformer-based feature fusion","volume":"15","author":"Khan","year":"2025","journal-title":"Sci. Rep."},{"issue":"3","key":"10.1016\/j.inffus.2026.104368_bib0028","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/JSTSP.2024.3422823","article-title":"Incongruity-aware cross-modal attention for audio-visual fusion in dimensional emotion recognition","volume":"18","author":"Praveen","year":"2024","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.inffus.2026.104368_bib0029","unstructured":"F. Liu, Z. Fu, Y. Wang, Q. Zheng, TACFN: transformer-based adaptive cross-modal fusion network for multimodal emotion recognition, arXiv: 2505.06536(2025)."},{"key":"10.1016\/j.inffus.2026.104368_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4803","article-title":"Recursive joint cross-modal attention for multimodal fusion in dimensional emotion recognition","author":"Praveen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104368_bib0031","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"333","article-title":"MambaMER: adaptive EEG-guided multimodal emotion recognition with Mamba","author":"Ping","year":"2025"},{"key":"10.1016\/j.inffus.2026.104368_bib0032","series-title":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","first-page":"1600","article-title":"MDDMamba: a model for multi-modal depression detection with a memory-saving cross-modal attention mechanism based on Mamba","author":"Liu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104368_bib0033","doi-asserted-by":"crossref","first-page":"59808","DOI":"10.52202\/079017-1910","article-title":"Coupled Mamba: enhanced multimodal fusion with coupled state space model","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.inffus.2026.104368_bib0034","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","article-title":"Deap: a database for emotion analysis; using physiological signals","volume":"3","author":"Koelstra","year":"2011","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"3","key":"10.1016\/j.inffus.2026.104368_bib0035","doi-asserted-by":"crossref","first-page":"1110","DOI":"10.1109\/TCYB.2018.2797176","article-title":"Emotionmeter: a multimodal framework for recognizing human emotions","volume":"49","author":"Zheng","year":"2018","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"10.1016\/j.inffus.2026.104368_bib0036","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1109\/TCDS.2021.3071170","article-title":"Comparing recognition performance and robustness of multimodal deep learning models for multimodal emotion recognition","volume":"14","author":"Liu","year":"2021","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.inffus.2026.104368_bib0037","article-title":"Comprehensive multisource learning network for cross-subject multimodal emotion recognition","author":"Chen","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.inffus.2026.104368_bib0038","first-page":"1","article-title":"Fusing frequency-domain features and brain connectivity features for cross-subject emotion recognition","volume":"71","author":"Chen","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"10.1016\/j.inffus.2026.104368_bib0039","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/ac49a7","article-title":"Investigating EEG-based functional connectivity patterns for multimodal emotion recognition","volume":"19","author":"Wu","year":"2022","journal-title":"J. Neural Eng."},{"issue":"10","key":"10.1016\/j.inffus.2026.104368_bib0040","doi-asserted-by":"crossref","first-page":"5865","DOI":"10.1109\/JBHI.2024.3419043","article-title":"Cross-modal guiding neural network for multimodal emotion recognition from EEG and eye movement signals","volume":"28","author":"Fu","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.inffus.2026.104368_bib0041","series-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1926","article-title":"Multimodal multi-view spectral-spatial-temporal masked autoencoder for self-supervised emotion recognition","author":"Gao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104368_bib0042","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.inffus.2026.104368_bib0043","first-page":"62108","article-title":"Facilitating multimodal classification via dynamically learning modality gap","volume":"37","author":"Yang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104368_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127181","article-title":"Multimodal transformer with adaptive modality weighting for multimodal sentiment analysis","volume":"572","author":"Wang","year":"2024","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.inffus.2026.104368_bib0045","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/TPAMI.2024.3468315","article-title":"On-the-fly modulation for balanced multimodal learning","volume":"47","author":"Wei","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002472?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002472?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:42:41Z","timestamp":1779190961000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S1566253526002472"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104368","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Modality-aware fusion with alignment and balancing for robust multimodal emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104368","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104368"}}