{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T10:56:51Z","timestamp":1784977011981,"version":"3.55.0"},"reference-count":92,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Korea Ministry of Science and ICT","doi-asserted-by":"publisher","award":["IITP-2025-RS-2023-00254529"],"award-info":[{"award-number":["IITP-2025-RS-2023-00254529"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Korea Ministry of Trade Industry and Energy","doi-asserted-by":"publisher","award":["RS-2024-00487049"],"award-info":[{"award-number":["RS-2024-00487049"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.133855","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T07:08:16Z","timestamp":1777964896000},"page":"133855","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Hierarchical transformer fusion with cross-modal attention and adaptive gating for audio-visual emotion recognition"],"prefix":"10.1016","volume":"693","author":[{"given":"Sathishkumar","family":"Moorthy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeon-Kug","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133855_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TAFFC.2026.3678321","article-title":"Graph-based representation learning with beta uncertainty for enhanced multimodal emotion recognition","author":"Mengara","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"7","key":"10.1016\/j.neucom.2026.133855_bib0010","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.3390\/math13071100","article-title":"Hybrid multi-attention network for audio\u2013visual emotion recognition through multimodal feature fusion","volume":"13","author":"Moorthy","year":"2025","journal-title":"Mathematics"},{"issue":"12","key":"10.1016\/j.neucom.2026.133855_bib0015","doi-asserted-by":"crossref","first-page":"1907","DOI":"10.3390\/math13121907","article-title":"CAG-MoE: multimodal emotion recognition with cross-attention gated mixture of experts","volume":"13","author":"Mengara Mengara","year":"2025","journal-title":"Mathematics"},{"issue":"1","key":"10.1016\/j.neucom.2026.133855_bib0020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13677-024-00718-5","article-title":"Building integrated assessment model for IoT technology deployment in the Industry 4.0","volume":"13","author":"Ali","year":"2024","journal-title":"J. Cloud Comput."},{"key":"10.1016\/j.neucom.2026.133855_bib0025","doi-asserted-by":"crossref","first-page":"168256","DOI":"10.1109\/ACCESS.2024.3498441","article-title":"Revolutionizing gaze-based human\u2013computer interaction using iris tracking: a webcam-based low-cost approach with calibration, regression and real-time re-calibration","volume":"12","author":"Chhimpa","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.133855_bib0030","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.cviu.2015.09.015","article-title":"Multi-modal emotion analysis from facial expressions and electroencephalogram","volume":"147","author":"Huang","year":"2016","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.neucom.2026.133855_bib0035","article-title":"Multimodal emotion recognition with deep learning: advancements, challenges, and future directions","volume":"105","author":"Geetha","year":"2024","journal-title":"Inf. Fusion"},{"issue":"2","key":"10.1016\/j.neucom.2026.133855_bib0040","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s00530-025-02204-7","article-title":"Exploring multi-transformer with fine-grained prompt-driven coupled with diffusion model for 3D human pose estimation","volume":"32","author":"Arthanari","year":"2026","journal-title":"Multimed. Syst."},{"key":"10.1016\/j.neucom.2026.133855_bib0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patrec.2021.03.007","article-title":"Leveraging recent advances in deep learning for audio-visual emotion recognition","volume":"146","author":"Schoneveld","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.133855_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2486","article-title":"A joint cross-attention model for audio-visual fusion in dimensional emotion recognition","author":"Praveen","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0055","series-title":"2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)","first-page":"600","article-title":"Two-stream aural-visual affect analysis in the wild","author":"Kuhnke","year":"2020"},{"key":"10.1016\/j.neucom.2026.133855_bib0060","article-title":"Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133855_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128646","article-title":"MFGCN: multimodal fusion graph convolutional network for speech emotion recognition","volume":"611","author":"Qi","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133855_bib0070","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Recursive joint attention for audio-visual fusion in regression based emotion recognition","author":"Praveen","year":"2023"},{"issue":"1","key":"10.1016\/j.neucom.2026.133855_bib0075","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1109\/TVCG.2021.3114794","article-title":"M2lens: visualizing and explaining multimodal models for sentiment analysis","volume":"28","author":"Wang","year":"2021","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"issue":"3","key":"10.1016\/j.neucom.2026.133855_bib0080","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.neucom.2026.133855_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.patrec.2026.01.008","article-title":"MER-CAPF: audio-text emotion recognition through cross-attention mechanism and multi-granularity pooling strategy","volume":"201","author":"Chen","year":"2026","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.133855_bib0090","series-title":"2024 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"Cross-attention is not always needed: dynamic cross-attention for audio-visual dimensional emotion recognition","author":"Praveen","year":"2024"},{"key":"10.1016\/j.neucom.2026.133855_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2026.114127","article-title":"Multimodal emotion recognition from complete modality to missing modality based on text, audio, and visual: a review","volume":"170","author":"Li","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133855_bib0100","author":"Lian"},{"key":"10.1016\/j.neucom.2026.133855_bib0105","article-title":"State-of-the-art multimodal emotion recognition: a comprehensive survey and taxonomy","author":"Yazici","year":"2026","journal-title":"Intell. Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133855_bib0110","author":"Lian"},{"key":"10.1016\/j.neucom.2026.133855_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104458","article-title":"Learning disruptor-suppressed response variation-aware multi-regularized correlation filter for visual tracking","volume":"110","author":"Moorthy","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.neucom.2026.133855_bib0120","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1109\/TMM.2021.3063612","article-title":"Deep auto-encoders with sequential learning for multimodal dimensional emotion recognition","volume":"24","author":"Nguyen","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.133855_bib0125","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4482","article-title":"Multitask learning and multistage fusion for dimensional audiovisual emotion recognition","author":"Atmaja","year":"2020"},{"key":"10.1016\/j.neucom.2026.133855_bib0130","article-title":"Multimodal emotion recognition based on temporal-spatio bidirectional dilated causal convolution multi-head attention network","author":"Yan","year":"2025","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133855_bib0135","series-title":"Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop","first-page":"19","article-title":"Efficient spatial temporal convolutional features for audiovisual continuous affect recognition","author":"Chen","year":"2019"},{"key":"10.1016\/j.neucom.2026.133855_bib0140","series-title":"Proceedings of the 21st ACM International Conference on Multimedia","first-page":"773","article-title":"Correlated-spaces regression for learning continuous emotion dimensions","author":"Nicolaou","year":"2013"},{"key":"10.1016\/j.neucom.2026.133855_bib0145","series-title":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","first-page":"366","article-title":"Joint discrete and continuous emotion prediction using ensemble and end-to-end approaches","author":"AlBadawy","year":"2018"},{"key":"10.1016\/j.neucom.2026.133855_bib0150","article-title":"Multimodal emotion recognition via unified granularity contrastive learning and similar negative discrimination","author":"Li","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133855_bib0155","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6339","article-title":"Multimodal emotion recognition with capsule graph convolutional based representation fusion","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133855_bib0160","doi-asserted-by":"crossref","first-page":"2617","DOI":"10.1109\/TASLP.2021.3096037","article-title":"Information fusion in attention networks using adaptive and multi-level factorized bilinear pooling for audio-visual emotion recognition","volume":"29","author":"Zhou","year":"2021","journal-title":"IEEE\/ACM Trans. audio speech lang. process."},{"key":"10.1016\/j.neucom.2026.133855_bib0165","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4693","article-title":"Is cross-attention preferable to self-attention for multi-modal emotion recognition?","author":"Rajan","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0170","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.inffus.2020.10.011","article-title":"End-to-end multimodal affect recognition in real-world environments","volume":"68","author":"Tzirakis","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133855_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2382","article-title":"Time-continuous audiovisual fusion with recurrence VS attention for in-the-wild affect recognition","author":"Karas","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0180","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3567","article-title":"Continuous emotion recognition with audio-visual leader-follower attentive fusion","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133855_bib0185","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"4901","article-title":"Robust multimodal emotion recognition from incomplete modalities via query-based unimodal and cross-modal learning","author":"Miyoshi","year":"2026"},{"key":"10.1016\/j.neucom.2026.133855_bib0190","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133855_bib0195","series-title":"2020 IEEE International Conference on Image Processing (ICIP)","first-page":"251","article-title":"Multimodal attention-mechanism for temporal emotion recognition","author":"Ghaleb","year":"2020"},{"issue":"4","key":"10.1016\/j.neucom.2026.133855_bib0200","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.1109\/TAFFC.2022.3216993","article-title":"Robust audiovisual emotion recognition: aligning modalities, capturing temporal information, and handling missing features","volume":"13","author":"Goncalves","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.133855_bib0205","series-title":"2022 26th International Conference on Pattern Recognition (ICPR)","first-page":"2582","article-title":"Audio and video-based emotion recognition using multimodal transformers","author":"John","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0210","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"3507","article-title":"Multimodal transformer fusion for continuous emotion recognition","author":"Huang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133855_bib0215","series-title":"2021 IEEE Spoken Language Technology Workshop (SLT)","first-page":"636","article-title":"Detecting expressions with multimodal transformers","author":"Parthasarathy","year":"2021"},{"key":"10.1016\/j.neucom.2026.133855_bib0220","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4698","article-title":"A pre-trained audio-visual transformer for emotion recognition","author":"Tran","year":"2022"},{"issue":"3","key":"10.1016\/j.neucom.2026.133855_bib0225","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/TBIOM.2022.3233083","article-title":"Audio\u2013visual fusion for emotion recognition in the Valence\u2013arousal space using joint cross-attention","volume":"5","author":"Praveen","year":"2023","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"10.1016\/j.neucom.2026.133855_bib0230","article-title":"Multimodal emotion recognition with temporal slicing encoder and attention-enhanced synergy integration","volume":"8","author":"Wang","year":"2026","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.neucom.2026.133855_bib0235","article-title":"Cross-modal gated feature enhancement for multimodal emotion recognition in conversations","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.neucom.2026.133855_bib0240","doi-asserted-by":"crossref","DOI":"10.1109\/TCE.2025.3599517","article-title":"Share token tensorized attention fusion: enhancing audio-visual emotion recognition for consumer electronics","volume":"71","author":"Lu","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.neucom.2026.133855_bib0245","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106764","article-title":"HiMul-LGG: a hierarchical decision fusion-based local\u2013global graph neural network for multimodal emotion recognition in conversation","volume":"181","author":"Fu","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.133855_bib0250","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"5667","article-title":"Grounding emotion recognition with visual prototypes: VEGA-revisiting CLIP in MERC","author":"Hu","year":"2025"},{"key":"10.1016\/j.neucom.2026.133855_bib0255","article-title":"Textualized multimodal priors and gated causal explanations for emotion recognition in conversations: a unified LLM framework","author":"Wang","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133855_bib0260","author":"Dosovitskiy"},{"key":"10.1016\/j.neucom.2026.133855_bib0265","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0270","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.133855_bib0275","series-title":"International Conference on Neural Information Processing","first-page":"117","article-title":"Challenges in representation learning: a report on three machine learning contests","author":"Goodfellow","year":"2013"},{"key":"10.1016\/j.neucom.2026.133855_bib0280","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5764","article-title":"Multimodal continuous emotion recognition: a technical report for abaw5","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133855_bib0285","series-title":"Proceedings of the 18th International Conference on Advances in Mobile Computing & Multimedia","first-page":"35","article-title":"Emotion recognition from speech using spectrograms and shallow neural networks","author":"Slimi","year":"2020"},{"issue":"11","key":"10.1016\/j.neucom.2026.133855_bib0290","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.neucom.2026.133855_bib0295","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"4013","article-title":"Audio-visual event localization via recursive fusion by joint co-attention","author":"Duan","year":"2021"},{"key":"10.1016\/j.neucom.2026.133855_bib0300","series-title":"2017 IEEE International Conference on Image Processing (ICIP)","first-page":"2851","article-title":"Contrastive-center loss for deep neural networks","author":"Qi","year":"2017"},{"key":"10.1016\/j.neucom.2026.133855_bib0305","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"10.1016\/j.neucom.2026.133855_bib0310","series-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"873","article-title":"Context-dependent sentiment analysis in user-generated videos","author":"Poria","year":"2017"},{"key":"10.1016\/j.neucom.2026.133855_bib0315","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6818","article-title":"Dialoguernn: an attentive RNN for emotion detection in conversations","volume":"vol. 33","author":"Majumder","year":"2019"},{"key":"10.1016\/j.neucom.2026.133855_bib0320","author":"Mao"},{"key":"10.1016\/j.neucom.2026.133855_bib0325","author":"Ghosal"},{"key":"10.1016\/j.neucom.2026.133855_bib0330","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1109\/TASLP.2021.3049898","article-title":"CTNet: conversational transformer network for emotion recognition","volume":"29","author":"Lian","year":"2021","journal-title":"IEEE\/ACM Trans. audio speech lang. process."},{"key":"10.1016\/j.neucom.2026.133855_bib0335","doi-asserted-by":"crossref","first-page":"4422","DOI":"10.1109\/TMM.2021.3117062","article-title":"LR-GCN: latent relation-aware graph convolutional network for conversational emotion recognition","volume":"24","author":"Ren","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.133855_bib0340","author":"Hu"},{"key":"10.1016\/j.neucom.2026.133855_bib0345","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.2026.133855_bib0350","doi-asserted-by":"crossref","DOI":"10.1109\/TCE.2025.3532322","article-title":"Joint multi-scale multimodal transformer for emotion using consumer devices","volume":"71","author":"Khan","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"3","key":"10.1016\/j.neucom.2026.133855_bib0355","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104533","article-title":"Adaptive weighted temporal prototype network for multimodal emotion recognition","volume":"63","author":"Li","year":"2026","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.neucom.2026.133855_bib0360","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.2026.133855_bib0365","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."},{"issue":"5","key":"10.1016\/j.neucom.2026.133855_bib0370","doi-asserted-by":"crossref","first-page":"3583","DOI":"10.1109\/TCSS.2024.3523322","article-title":"Pgif: a personality-guided iterative feedback graph network for multimodal conversational emotion recognition","volume":"12","author":"Xie","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"issue":"3","key":"10.1016\/j.neucom.2026.133855_bib0375","doi-asserted-by":"crossref","first-page":"4908","DOI":"10.1109\/TNNLS.2024.3367940","article-title":"Der-gcn: dialog and event relation-aware graph convolutional neural network for multimodal dialog emotion recognition","volume":"36","author":"Ai","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133855_bib0380","series-title":"IJCAI","first-page":"5415","article-title":"Modeling both context-and speaker-sensitive dependence for emotion detection in multi-speaker conversations","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133855_bib0385","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.aej.2025.11.004","article-title":"AEFNet: an adaptive external attention-enhanced fusion network for multimodal emotion recognition","volume":"132","author":"Liu","year":"2025","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.neucom.2026.133855_bib0390","article-title":"ETCE-net: emotion transition and causal emotion entailment network for dialogue emotion recognition","author":"Mu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133855_bib0395","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2328","article-title":"Abaw: Valence-arousal estimation, expression recognition, action unit detection & multi-task learning challenges","author":"Kollias","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0400","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2428","article-title":"Transformer-based multimodal information fusion for facial expression analysis","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0405","author":"Karas"},{"key":"10.1016\/j.neucom.2026.133855_bib0410","author":"Savchenko"},{"key":"10.1016\/j.neucom.2026.133855_bib0415","author":"Nguyen"},{"key":"10.1016\/j.neucom.2026.133855_bib0420","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2376","article-title":"Continuous emotion recognition using visual-audio-linguistic information: a technical report for abaw3","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133855_bib0425","author":"Meng"},{"key":"10.1016\/j.neucom.2026.133855_bib0430","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4625","article-title":"Joint multimodal transformer for emotion recognition in the wild","author":"Waligora","year":"2024"},{"key":"10.1016\/j.neucom.2026.133855_bib0435","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"61","article-title":"Dynamic temporal gating networks for cross-modal Valence-arousal estimation","author":"Lee","year":"2025"},{"key":"10.1016\/j.neucom.2026.133855_bib0440","series-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.neucom.2026.133855_bib0445","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"1122","article-title":"Misa: modality-invariant and-specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2020"},{"issue":"2","key":"10.1016\/j.neucom.2026.133855_bib0450","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103229","article-title":"PS-mixer: a polar-vector and strength-vector mixer model for multimodal sentiment analysis","volume":"60","author":"Lin","year":"2023","journal-title":"Inf. Process. Manag."},{"issue":"3","key":"10.1016\/j.neucom.2026.133855_bib0455","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3380744","article-title":"A deep multi-task contextual attention framework for multi-modal affect analysis","volume":"14","author":"Akhtar","year":"2020","journal-title":"ACM Trans. Knowl. Discov. Data (TKDD)"},{"key":"10.1016\/j.neucom.2026.133855_bib0460","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"vol. 2019","author":"Tsai","year":"2019"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601252X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092523122601252X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T23:03:39Z","timestamp":1784934219000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S092523122601252X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":92,"alternative-id":["S092523122601252X"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133855","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical transformer fusion with cross-modal attention and adaptive gating for audio-visual emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133855","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":"133855"}}