{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T14:17:54Z","timestamp":1794061074859,"version":"4.8.0"},"reference-count":69,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100021183","name":"Science Fund for Distinguished Young Scholars of Jiangxi Province","doi-asserted-by":"publisher","award":["242300421171"],"award-info":[{"award-number":["242300421171"]}],"id":[{"id":"10.13039\/501100021183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106066"],"award-info":[{"award-number":["62106066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1016\/j.neunet.2025.107483","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T11:52:40Z","timestamp":1745581960000},"page":"107483","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":10,"special_numbering":"C","title":["Multi-modal sentiment recognition with residual gating network and emotion intensity attention"],"prefix":"10.1016","volume":"188","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9073-9308","authenticated-orcid":false,"given":"Yadi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8466-6103","authenticated-orcid":false,"given":"Xiaoding","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianhong","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijun","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinkai","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/j.neunet.2025.107483_b1","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.3390\/electronics10091036","article-title":"Facial emotion recognition using transfer learning in the deep CNN","volume":"10","author":"Akhand","year":"2021","journal-title":"Electronics"},{"issue":"2","key":"10.1016\/j.neunet.2025.107483_b2","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1121\/1.1490365","article-title":"Normalized amplitude quotient for parametrization of the glottal flow","volume":"112","author":"Alku","year":"2002","journal-title":"Journal of the Acoustical Society of America"},{"issue":"2","key":"10.1016\/j.neunet.2025.107483_b3","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107483_b4","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.future.2020.08.005","article-title":"ABCDM: An attention-based bidirectional CNN-RNN deep model for sentiment analysis","volume":"115","author":"Basiri","year":"2021","journal-title":"Future Generation Computer Systems"},{"issue":"11","key":"10.1016\/j.neunet.2025.107483_b5","doi-asserted-by":"crossref","first-page":"550","DOI":"10.3390\/info13110550","article-title":"Multimodal EEG emotion recognition based on the attention recurrent graph convolutional network","volume":"13","author":"Chen","year":"2022","journal-title":"Information"},{"issue":"2","key":"10.1016\/j.neunet.2025.107483_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103193","article-title":"Joint multimodal sentiment analysis based on information relevance","volume":"60","author":"Chen","year":"2023","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.neunet.2025.107483_b7","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.neucom.2021.02.020","article-title":"A novel context-aware multimodal framework for persian sentiment analysis","volume":"457","author":"Dashtipour","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107483_b8","series-title":"2014 ieee international conference on acoustics, speech and signal processing","first-page":"960","article-title":"COVAREP\u2014A collaborative voice analysis repository for speech technologies","author":"Degottex","year":"2014"},{"key":"10.1016\/j.neunet.2025.107483_b9","series-title":"Joint robust voicing detection and pitch estimation based on residual harmonics","author":"Drugman","year":"2019"},{"issue":"3","key":"10.1016\/j.neunet.2025.107483_b10","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1109\/TAFFC.2020.3013711","article-title":"An efficient LSTM network for emotion recognition from multichannel eeg signals","volume":"13","author":"Du","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.neunet.2025.107483_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122731","article-title":"A multimodal fusion network with attention mechanisms for visual\u2013textual sentiment analysis","volume":"242","author":"Gan","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2025.107483_b12","series-title":"Compact bilinear pooling","author":"Gao","year":"2015"},{"key":"10.1016\/j.neunet.2025.107483_b13","doi-asserted-by":"crossref","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","article-title":"Deep multimodal representation learning: A survey","volume":"7","author":"Guo","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2025.107483_b14","series-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","author":"Han","year":"2021"},{"key":"10.1016\/j.neunet.2025.107483_b15","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., & Poria, S. (2020). Misa: Modality-invariant and-specific representations for multimodal sentiment analysis. In Proceedings of the 28th ACM international conference on multimedia (pp. 1122\u20131131).","DOI":"10.1145\/3394171.3413678"},{"key":"10.1016\/j.neunet.2025.107483_b16","doi-asserted-by":"crossref","unstructured":"Huang, J., Ji, Y., Yang, Y., & Shen, H. T. (2023). Cross-modality Representation Interactive Learning for Multimodal Sentiment Analysis. In Proceedings of the 31st ACM international conference on multimedia (pp. 426\u2013434).","DOI":"10.1145\/3581783.3612295"},{"key":"10.1016\/j.neunet.2025.107483_b17","series-title":"Social, cultural, and behavioral modeling: 11th international conference, SBP-BRiMS 2018, Washington, DC, USA, July 10\u201313, 2018, proceedings 11","first-page":"197","article-title":"Aspect level sentiment classification with attention-over-attention neural networks","author":"Huang","year":"2018"},{"key":"10.1016\/j.neunet.2025.107483_b18","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.knosys.2019.01.019","article-title":"Image\u2013text sentiment analysis via deep multimodal attentive fusion","volume":"167","author":"Huang","year":"2019","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2025.107483_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2020.101894","article-title":"Speech emotion recognition with deep convolutional neural networks","volume":"59","author":"Issa","year":"2020","journal-title":"Biomedical Signal Processing and Control"},{"issue":"4","key":"10.1016\/j.neunet.2025.107483_b20","doi-asserted-by":"crossref","first-page":"1564","DOI":"10.1109\/TCDS.2021.3123979","article-title":"Convolutional-recurrent neural networks with multiple attention mechanisms for speech emotion recognition","volume":"14","author":"Jiang","year":"2021","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"6","key":"10.1016\/j.neunet.2025.107483_b21","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TASL.2013.2245653","article-title":"Wavelet maxima dispersion for breathy to tense voice discrimination","volume":"21","author":"Kane","year":"2013","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.neunet.2025.107483_b22","series-title":"5th international conference on learning representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, conference track proceedings","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2017"},{"key":"10.1016\/j.neunet.2025.107483_b23","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1016\/j.neunet.2022.03.017","article-title":"A BERT based dual-channel explainable text emotion recognition system","volume":"150","author":"Kumar","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107483_b24","series-title":"ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing","first-page":"4477","article-title":"Gated mechanism for attention based multi modal sentiment analysis","author":"Kumar","year":"2020"},{"issue":"1","key":"10.1016\/j.neunet.2025.107483_b25","doi-asserted-by":"crossref","first-page":"183","DOI":"10.3390\/s20010183","article-title":"A CNN-assisted enhanced audio signal processing for speech emotion recognition","volume":"20","author":"Kwon","year":"2019","journal-title":"Sensors"},{"issue":"2","key":"10.1016\/j.neunet.2025.107483_b26","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1109\/TAFFC.2018.2880201","article-title":"Facial expression recognition with identity and emotion joint learning","volume":"12","author":"Li","year":"2018","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.neunet.2025.107483_b27","series-title":"2022 32nd international conference radioelektronika","first-page":"1","article-title":"RNN with improved temporal modeling for speech emotion recognition","author":"Lieskovska","year":"2022"},{"key":"10.1016\/j.neunet.2025.107483_b28","series-title":"Efficient low-rank multimodal fusion with modality-specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2025.107483_b29","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.patrec.2017.06.004","article-title":"Reinforcement online learning for emotion prediction by using physiological signals","volume":"107","author":"Liu","year":"2018","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2025.107483_b30","first-page":"1","article-title":"Investigating fairness in machine learning-based audio sentiment analysis","author":"Luitel","year":"2024","journal-title":"AI and Ethics"},{"key":"10.1016\/j.neunet.2025.107483_b31","unstructured":"Maas, A., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011). Learning word vectors for sentiment analysis. In Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies (pp. 142\u2013150)."},{"issue":"1","key":"10.1016\/j.neunet.2025.107483_b32","first-page":"107","article-title":"CLSA-CapsNet: Dependency based concept level sentiment analysis for text","volume":"43","author":"Mahendhiran","year":"2022","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"1","key":"10.1016\/j.neunet.2025.107483_b33","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1109\/TAFFC.2020.3000510","article-title":"Multi-fusion residual memory network for multimodal human sentiment comprehension","volume":"13","author":"Mai","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.neunet.2025.107483_b34","series-title":"2021 IEEE automatic speech recognition and understanding workshop","first-page":"350","article-title":"Multimodal emotion recognition with high-level speech and text features","author":"Makiuchi","year":"2021"},{"key":"10.1016\/j.neunet.2025.107483_b35","doi-asserted-by":"crossref","first-page":"1640","DOI":"10.1016\/j.procs.2023.01.142","article-title":"Sentiment analysis on images using different transfer learning models","volume":"218","author":"Meena","year":"2023","journal-title":"Procedia Computer Science"},{"issue":"3","key":"10.1016\/j.neunet.2025.107483_b36","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1007\/s42452-020-2234-1","article-title":"Facial emotion recognition using convolutional neural networks (FERC)","volume":"2","author":"Mehendale","year":"2020","journal-title":"SN Applied Sciences"},{"key":"10.1016\/j.neunet.2025.107483_b37","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 Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107483_b38","series-title":"Multi-modal attention for speech emotion recognition","author":"Pan","year":"2020"},{"issue":"18","key":"10.1016\/j.neunet.2025.107483_b39","first-page":"54249","article-title":"A context-sensitive multi-tier deep learning framework for multimodal sentiment analysis","volume":"83","author":"Paul","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2025.107483_b40","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.neucom.2016.09.117","article-title":"Ensemble application of convolutional neural networks and multiple kernel learning for multimodal sentiment analysis","volume":"261","author":"Poria","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107483_b41","doi-asserted-by":"crossref","unstructured":"Praveen, R. G., de Melo, W. C., Ullah, N., Aslam, H., Zeeshan, O., Denorme, T., Pedersoli, M., Koerich, A. L., Bacon, S., Cardinal, P., et al. (2022). A joint cross-attention model for audio-visual fusion in dimensional emotion recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2486\u20132495).","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"10.1016\/j.neunet.2025.107483_b42","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.neunet.2025.107483_b43","first-page":"2359","article-title":"Integrating multimodal information in large pretrained transformers","volume":"vol. 2020","author":"Rahman","year":"2020"},{"key":"10.1016\/j.neunet.2025.107483_b44","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1016\/j.procs.2023.01.098","article-title":"LyEmoBERT: Classification of lyrics\u2019 emotion and recommendation using a pre-trained model","volume":"218","author":"Revathy","year":"2023","journal-title":"Procedia Computer Science"},{"key":"10.1016\/j.neunet.2025.107483_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.105572","article-title":"SACPC: A framework based on probabilistic linguistic terms for short text sentiment analysis","volume":"194","author":"Song","year":"2020","journal-title":"Knowledge-Based Systems"},{"issue":"1","key":"10.1016\/j.neunet.2025.107483_b46","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/TAFFC.2023.3274829","article-title":"Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis","volume":"15","author":"Sun","year":"2023","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.neunet.2025.107483_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102129","article-title":"Hierarchical multimodal-fusion of physiological signals for emotion recognition with scenario adaption and contrastive alignment","volume":"103","author":"Tang","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.107483_b48","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"vol. 2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.neunet.2025.107483_b49","series-title":"Learning factorized multimodal representations","author":"Tsai","year":"2018"},{"key":"10.1016\/j.neunet.2025.107483_b50","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":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.107483_b51","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.neunet.2025.107483_b52","first-page":"80","article-title":"A bimodal approach for speech emotion recognition using audio and text","volume":"11","author":"Verkholyak","year":"2021","journal-title":"Journal of Internet Services and Information Security"},{"key":"10.1016\/j.neunet.2025.107483_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109259","article-title":"TETFN: A text enhanced transformer fusion network for multimodal sentiment analysis","volume":"136","author":"Wang","year":"2023","journal-title":"Pattern Recognition"},{"issue":"4","key":"10.1016\/j.neunet.2025.107483_b54","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1109\/TMM.2019.2934824","article-title":"Knowledge-augmented multimodal deep regression bayesian networks for emotion video tagging","volume":"22","author":"Wang","year":"2019","journal-title":"IEEE Transactions on Multimedia"},{"issue":"20","key":"10.1016\/j.neunet.2025.107483_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e38913","article-title":"Introducing a novel dataset for facial emotion recognition and demonstrating significant enhancements in deep learning performance through pre-processing techniques","volume":"10","author":"Yal\u00e7in","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.neunet.2025.107483_b56","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume":"vol. 35","author":"Yu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107483_b57","series-title":"IEEE international conference on computer vision, ICCV 2017, Venice, Italy, October 22\u201329, 2017","first-page":"1839","article-title":"Multi-modal factorized bilinear pooling with co-attention learning for visual question answering","author":"Yu","year":"2017"},{"key":"10.1016\/j.neunet.2025.107483_b58","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Li, W., Xu, H., & Yu, W. (2021). Transformer-based feature reconstruction network for robust multimodal sentiment analysis. In Proceedings of the 29th ACM international conference on multimedia (pp. 4400\u20134407).","DOI":"10.1145\/3474085.3475585"},{"key":"10.1016\/j.neunet.2025.107483_b59","series-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.neunet.2025.107483_b60","article-title":"Memory fusion network for multi-view sequential learning","volume":"vol. 32","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.neunet.2025.107483_b61","doi-asserted-by":"crossref","unstructured":"Zadeh, A. B., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018). Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph. In Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long papers) (pp. 2236\u20132246).","DOI":"10.18653\/v1\/P18-1208"},{"issue":"6","key":"10.1016\/j.neunet.2025.107483_b62","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MIS.2016.94","article-title":"Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages","volume":"31","author":"Zadeh","year":"2016","journal-title":"IEEE Intelligent Systems"},{"key":"10.1016\/j.neunet.2025.107483_b63","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102031","article-title":"Disentanglement translation network for multimodal sentiment analysis","volume":"102","author":"Zeng","year":"2024","journal-title":"Information Fusion"},{"issue":"3","key":"10.1016\/j.neunet.2025.107483_b64","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1109\/TCSVT.2021.3072412","article-title":"Real-time video emotion recognition based on reinforcement learning and domain knowledge","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"9","key":"10.1016\/j.neunet.2025.107483_b65","doi-asserted-by":"crossref","first-page":"4386","DOI":"10.1109\/TCYB.2020.2987575","article-title":"Emotion recognition from multimodal physiological signals using a regularized deep fusion of kernel machine","volume":"51","author":"Zhang","year":"2020","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.neunet.2025.107483_b66","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.inffus.2020.04.003","article-title":"A quantum-like multimodal network framework for modeling interaction dynamics in multiparty conversational sentiment analysis","volume":"62","author":"Zhang","year":"2020","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.107483_b67","series-title":"Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2025.107483_b68","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.neunet.2021.03.013","article-title":"Combining a parallel 2D CNN with a self-attention dilated residual network for CTC-based discrete speech emotion recognition","volume":"141","author":"Zhao","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107483_b69","doi-asserted-by":"crossref","unstructured":"Zhou, W., Lu, J., Xiong, Z., & Wang, W. (2023). Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5756\u20135763).","DOI":"10.1109\/CVPRW59228.2023.00610"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025003624?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025003624?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:11:31Z","timestamp":1762315891000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025003624"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":69,"alternative-id":["S0893608025003624"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107483","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-modal sentiment recognition with residual gating network and emotion intensity attention","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107483","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107483"}}