{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T11:00:26Z","timestamp":1780225226864,"version":"3.54.0"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116079","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:07:49Z","timestamp":1777568869000},"page":"116079","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Tri-projection gated cross-modal fusion for robust multilingual emotion recognition"],"prefix":"10.1016","volume":"344","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4120-6375","authenticated-orcid":false,"given":"Suja C.","family":"Nair","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-3056","authenticated-orcid":false,"given":"Asha","family":"S.","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5552-0351","authenticated-orcid":false,"given":"Priya","family":"K.V.","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kavya Clare P.","family":"Shaji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2158-4896","authenticated-orcid":false,"given":"Balakrishnan","family":"C.","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-1017","authenticated-orcid":false,"given":"T.","family":"Kokilavani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116079_b1","article-title":"Survey on multimodal approaches to emotion recognition","volume":"556","author":"Gladys","year":"2023","journal-title":"Neurocomputing"},{"issue":"10","key":"10.1016\/j.knosys.2026.116079_b2","doi-asserted-by":"crossref","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","article-title":"Multimodal learning with transformers: A survey","volume":"45","author":"Xu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116079_b3","doi-asserted-by":"crossref","unstructured":"S. Lee, Z. Wang, Emotion in code-switching texts: Corpus construction and analysis, in: Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, 2015, pp. 91\u201399.","DOI":"10.18653\/v1\/W15-3116"},{"issue":"4","key":"10.1016\/j.knosys.2026.116079_b4","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1007\/s12559-023-10165-0","article-title":"Multidimensional affective analysis for low-resource languages: A use case with guarani-spanish code-switching language","volume":"15","author":"Ag\u00fcero-Torales","year":"2023","journal-title":"Cogn. Comput."},{"key":"10.1016\/j.knosys.2026.116079_b5","series-title":"Understanding and Explaining Affective Traits in English and Code-Mixed Conversations","author":"Kumar","year":"2024"},{"key":"10.1016\/j.knosys.2026.116079_b6","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.knosys.2026.116079_b7","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2026.3664257","article-title":"Bridging languages in healthcare: A comprehensive review of multilingual and code-switched chatbot interactions","author":"Tejasri","year":"2026","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116079_b8","series-title":"2024 International Conference on Advances in Computing, Communication and Materials","first-page":"1","article-title":"A comprehensive review on emotion detection in code-mixed social media posts","author":"Tripathi","year":"2024"},{"issue":"2","key":"10.1016\/j.knosys.2026.116079_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3786343","article-title":"A comprehensive survey on multi-modal conversational emotion recognition with deep learning","volume":"44","author":"Shou","year":"2026","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.knosys.2026.116079_b10","article-title":"HGTFM: Hierarchical gating-driven transformer fusion model for robust multimodal sentiment analysis","author":"Yang","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.knosys.2026.116079_b11","doi-asserted-by":"crossref","first-page":"36","DOI":"10.17694\/bajece.1372107","article-title":"Multimodal emotion recognition using bi-lg-gcn for meld dataset","volume":"12","author":"Alsaadaw\u0131","year":"2024","journal-title":"Balk. J. Electr. Comput. Eng."},{"key":"10.1016\/j.knosys.2026.116079_b12","series-title":"2024 MIT Art, Design and Technology School of Computing International Conference","first-page":"1","article-title":"Review of databases used for text based emotion detection","author":"Deshmukh","year":"2024"},{"key":"10.1016\/j.knosys.2026.116079_b13","doi-asserted-by":"crossref","first-page":"74539","DOI":"10.1109\/ACCESS.2021.3067460","article-title":"Head fusion: Improving the accuracy and robustness of speech emotion recognition on the IEMOCAP and RAVDESS dataset","volume":"9","author":"Xu","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116079_b14","series-title":"2024 International Joint Conference on Neural Networks","first-page":"1","article-title":"Multimodal fusion strategies for emotion recognition","author":"Ortiz-Perez","year":"2024"},{"key":"10.1016\/j.knosys.2026.116079_b15","doi-asserted-by":"crossref","unstructured":"Z. Chen, Y. Cao, X. Lu, Q. Mei, X. Liu, Sentimoji: an emoji-powered learning approach for sentiment analysis in software engineering, in: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2019, pp. 841\u2013852.","DOI":"10.1145\/3338906.3338977"},{"key":"10.1016\/j.knosys.2026.116079_b16","doi-asserted-by":"crossref","unstructured":"J. Ma, H. Tang, W.L. Zheng, B.L. Lu, Emotion recognition using multimodal residual LSTM network, in: Proceedings of the 27th ACM International Conference on Multimedia, 2019, pp. 176\u2013183.","DOI":"10.1145\/3343031.3350871"},{"key":"10.1016\/j.knosys.2026.116079_b17","doi-asserted-by":"crossref","first-page":"79861","DOI":"10.1109\/ACCESS.2020.2990405","article-title":"Clustering-based speech emotion recognition by incorporating learned features and deep BiLSTM","volume":"8","author":"Sajjad","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.knosys.2026.116079_b18","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s44163-025-00400-y","article-title":"A CNN-transformer framework for emotion recognition in code-mixed English\u2013Hindi data","volume":"5","author":"Patankar","year":"2025","journal-title":"Discov. Artif. Intell."},{"issue":"1","key":"10.1016\/j.knosys.2026.116079_b19","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."},{"key":"10.1016\/j.knosys.2026.116079_b20","series-title":"A transformer-based joint-encoding for emotion recognition and sentiment analysis","author":"Delbrouck","year":"2020"},{"key":"10.1016\/j.knosys.2026.116079_b21","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.cogsys.2022.10.012","article-title":"Unimodal approaches for emotion recognition: A systematic review","volume":"77","author":"Tomar","year":"2023","journal-title":"Cogn. Syst. Res."},{"key":"10.1016\/j.knosys.2026.116079_b22","series-title":"International Conference on Entrepreneurship, Innovation, and Leadership","first-page":"239","article-title":"Comparative analysis of deep learning techniques for suicidal ideation detection from social media text","author":"Malavade","year":"2024"},{"key":"10.1016\/j.knosys.2026.116079_b23","doi-asserted-by":"crossref","first-page":"10218","DOI":"10.1109\/ACCESS.2023.3240420","article-title":"A framework to evaluate fusion methods for multimodal emotion recognition","volume":"11","author":"Pe\u00f1a","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116079_b24","series-title":"2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing","first-page":"54","article-title":"A multimodal approach for emotion recognition in conversations using the MELD dataset","author":"He","year":"2025"},{"key":"10.1016\/j.knosys.2026.116079_b25","series-title":"2021 IEEE Spoken Language Technology Workshop","first-page":"636","article-title":"Detecting expressions with multimodal transformers","author":"Parthasarathy","year":"2021"},{"key":"10.1016\/j.knosys.2026.116079_b26","article-title":"Multimodal emotion recognition with temporal slicing encoder and attention-enhanced synergy integration","author":"Wang","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116079_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.109377","article-title":"MT-DFAN: A multi-task dynamic fusion attention network for multimodal emotion recognition in naturalistic conversations","volume":"115","author":"Song","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.knosys.2026.116079_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2026.109684","article-title":"SCAF-Net: A spiking cross-modal attention fusion network for multimodal emotion recognition","volume":"118","author":"Ma","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.knosys.2026.116079_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.115484","article-title":"Graph-prototype distillation with prototype-guided contrastive training for multimodal emotion recognition in conversations","author":"Yu","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116079_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108629","article-title":"EA-FUSION: A multimodal emotion recognition model using EEG and facial expression data","volume":"112","author":"Xu","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.knosys.2026.116079_b31","doi-asserted-by":"crossref","DOI":"10.1109\/TAFFC.2026.3663280","article-title":"TPFN: A text-guided progressive fusion network for multimodal sentiment analysis","author":"Ou","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.116079_b32","article-title":"Text-centric sparse interaction fusion network with a modality calibrating module for multimodal sentiment analysis","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.116079_b33","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."},{"issue":"6","key":"10.1016\/j.knosys.2026.116079_b34","doi-asserted-by":"crossref","first-page":"3599","DOI":"10.1007\/s00530-023-01133-7","article-title":"Hierarchical multiples self-attention mechanism for multi-modal analysis","volume":"29","author":"Jun","year":"2023","journal-title":"Multimedia Syst."},{"key":"10.1016\/j.knosys.2026.116079_b35","series-title":"Speech-Text Cross-Modal Learning through Self-Attention Mechanisms","author":"Bonaccorsi","year":"2023"},{"key":"10.1016\/j.knosys.2026.116079_b36","series-title":"2024 15th International Conference on Computing Communication and Networking Technologies","first-page":"1","article-title":"Enhancing medical VQA with self-attention based multi-model approach","author":"Sakthivel","year":"2024"},{"key":"10.1016\/j.knosys.2026.116079_b37","doi-asserted-by":"crossref","unstructured":"C. Yang, Y. Wang, J. Zhang, H. Zhang, Z. Wei, Z. Lin, A. Yuille, Lite vision transformer with enhanced self-attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11998\u201312008.","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"10.1016\/j.knosys.2026.116079_b38","series-title":"European Conference on Computer Vision","first-page":"251","article-title":"Attention prompting on image for large vision-language models","author":"Yu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116079_b39","doi-asserted-by":"crossref","DOI":"10.1109\/LGRS.2025.3532987","article-title":"Improving vision-language models with attention mechanisms for aerial video classification","author":"Tu","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.knosys.2026.116079_b40","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2026.3653457","article-title":"Merbench: A unified evaluation benchmark for multimodal emotion recognition","author":"Lian","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.knosys.2026.116079_b41","article-title":"Sentiment analysis and emotion detection using transformer models in multilingual social media data","volume":"16","author":"Almalki","year":"2025","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"10.1016\/j.knosys.2026.116079_b42","first-page":"1","article-title":"Optimized emotion classification in code-mixed hinglish text using an mBERT based hybrid neural network with attention mechanisms","author":"Khare","year":"2025","journal-title":"Int. J. Inf. Technol."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008051?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008051?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T10:01:33Z","timestamp":1780221693000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126008051"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":42,"alternative-id":["S0950705126008051"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116079","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Tri-projection gated cross-modal fusion for robust multilingual emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116079","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":"116079"}}