{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:54:13Z","timestamp":1776128053694,"version":"3.50.1"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["61673052"],"award-info":[{"award-number":["61673052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.knosys.2026.115729","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T07:54:43Z","timestamp":1773302083000},"page":"115729","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DMIC2: A dynamic modality importance and cascaded cross-attention framework for multimodal sentiment analysis"],"prefix":"10.1016","volume":"340","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2725-9269","authenticated-orcid":false,"given":"Jinming","family":"Ping","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-4248","authenticated-orcid":false,"given":"Ruicong","family":"Zhi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1903-5638","authenticated-orcid":false,"given":"Shufan","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0953-7341","authenticated-orcid":false,"given":"Yuewu","family":"Hou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3066-1372","authenticated-orcid":false,"given":"Xiaoyuan","family":"Liang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8276-6357","authenticated-orcid":false,"given":"Fei","family":"Wan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115729_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102787","article-title":"Multimodal sentiment analysis with unimodal label generation and modality decomposition","volume":"116","author":"Zhu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.115729_bib0002","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"25642","article-title":"MSE-adapter: a lightweight plugin endowing LLMs with the capability to perform multimodal sentiment analysis and emotion recognition","volume":"39","author":"Yang","year":"2025"},{"issue":"9","key":"10.1016\/j.knosys.2026.115729_bib0003","first-page":"1","article-title":"Multimodal PEAR chain-of-thought reasoning for multimodal sentiment analysis","volume":"20","author":"Li","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.knosys.2026.115729_bib0004","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.future.2017.09.048","article-title":"Sentiment analysis of chinese micro-blog text based on extended sentiment dictionary","volume":"81","author":"Zhang","year":"2018","journal-title":"Fut. Gen. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.115729_bib0005","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"13597","article-title":"End-to-end aspect-based sentiment analysis with combinatory categorial grammar","author":"Tian","year":"2023"},{"key":"10.1016\/j.knosys.2026.115729_bib0006","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Robust image sentiment analysis using progressively trained and domain transferred deep networks","volume":"29","author":"You","year":"2015"},{"issue":"4","key":"10.1016\/j.knosys.2026.115729_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103749","article-title":"Enhancing image sentiment analysis: a user-centered approach through user emotions and visual features","volume":"61","author":"Liang","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.knosys.2026.115729_bib0008","series-title":"2024 Conference on AI, Science, Engineering, and Technology (AIxSET)","first-page":"149","article-title":"Audio sentiment analysis with spectrogram representations and transformer models","author":"Luitel","year":"2024"},{"issue":"3","key":"10.1016\/j.knosys.2026.115729_bib0009","article-title":"A review and meta-analysis of multimodal affect detection systems","volume":"47","author":"D\u2019mello","year":"2015","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"10.1016\/j.knosys.2026.115729_bib0010","article-title":"Dynamic dominant fusion multimodal sentiment analysis method based on autoencoder","volume":"60","author":"Xi","year":"2024","journal-title":"J. Comput. Eng. Appl."},{"key":"10.1016\/j.knosys.2026.115729_bib0011","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"14755","article-title":"Knowledge-guided dynamic modality attention fusion framework for multimodal sentiment analysis","author":"Feng","year":"2024"},{"key":"10.1016\/j.knosys.2026.115729_bib0012","doi-asserted-by":"crossref","first-page":"8383","DOI":"10.1109\/TMM.2023.3344358","article-title":"Dominant single-modal SUpplementary fusion (SIMSUF) for multimodal sentiment analysis","volume":"26","author":"Huang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.115729_bib0013","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume":"35","author":"Yu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115729_bib0014","series-title":"International Conference on Intelligent Human Computer Interaction","first-page":"689","article-title":"reSenseNet: ensemble early fusion deep learning architecture for multimodal sentiment analysis","author":"Ghosh","year":"2021"},{"key":"10.1016\/j.knosys.2026.115729_bib0015","series-title":"2016 IEEE 16th International Conference on Data Mining (ICDM)","first-page":"439","article-title":"Convolutional MKL based multimodal emotion recognition and sentiment analysis","author":"Poria","year":"2016"},{"key":"10.1016\/j.knosys.2026.115729_bib0016","series-title":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","first-page":"284","article-title":"Deep multimodal fusion for persuasiveness prediction","author":"Nojavanasghari","year":"2016"},{"key":"10.1016\/j.knosys.2026.115729_bib0017","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.eswa.2016.08.047","article-title":"Multimodal emotion recognition with evolutionary computation for human-robot interaction","volume":"66","author":"Perez-Gaspar","year":"2016","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"10.1016\/j.knosys.2026.115729_bib0018","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/TAFFC.2017.2713783","article-title":"Audio-visual emotion recognition in video clips","volume":"10","author":"Noroozi","year":"2017","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.115729_bib0019","series-title":"2017 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"949","article-title":"Select-additive learning: improving generalization in multimodal sentiment analysis","author":"Wang","year":"2017"},{"key":"10.1016\/j.knosys.2026.115729_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113496","article-title":"Discrepancy learning guided hierarchical fusion network for multi-modal recommendation","volume":"317","author":"Dang","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115729_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119240","article-title":"Heterogeneous graph convolution based on in-domain self-supervision for multimodal sentiment analysis","volume":"213","author":"Zeng","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115729_bib0022","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8992","article-title":"Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis","volume":"34","author":"Sun","year":"2020"},{"key":"10.1016\/j.knosys.2026.115729_bib0023","series-title":"Proceedings of the 29th International Conference on Computational Linguistics","first-page":"7124","article-title":"Modeling intra-and inter-modal relations: hierarchical graph contrastive learning for multimodal sentiment analysis","volume":"29","author":"Lin","year":"2022"},{"key":"10.1016\/j.knosys.2026.115729_bib0024","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TMM.2023.3303711","article-title":"Dynamically shifting multimodal representations via hybrid-Modal attention for multimodal sentiment analysis","volume":"26","author":"Lin","year":"2024","journal-title":"Trans. Multi."},{"issue":"1","key":"10.1016\/j.knosys.2026.115729_bib0025","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 Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.115729_bib0026","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.knosys.2026.115729_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111346","article-title":"TMBL: transformer-based multimodal binding learning model for multimodal sentiment analysis","volume":"285","author":"Huang","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115729_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125817","article-title":"Towards bias-aware visual question answering: rectifying and mitigating comprehension biases","volume":"264","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115729_bib0029","series-title":"Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence","article-title":"Semi-IIN: semi-supervised intra-inter modal interaction learning network for multimodal sentiment analysis","author":"Lin","year":"2025"},{"key":"10.1016\/j.knosys.2026.115729_bib0030","first-page":"1","article-title":"Learning frequency-domain fusion for multimodal remote sensing semantic segmentation","volume":"63","author":"Chen","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.115729_bib0031","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"7837","article-title":"UniMSE: towards unified multimodal sentiment analysis and emotion recognition","author":"Hu","year":"2022"},{"key":"10.1016\/j.knosys.2026.115729_bib0032","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"756","article-title":"Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.115729_bib0033","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","article-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","author":"Han","year":"2021"},{"key":"10.1016\/j.knosys.2026.115729_bib0034","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","article-title":"A text-centered shared-private framework via cross-modal prediction for multimodal sentiment analysis","author":"Wu","year":"2021"},{"issue":"2","key":"10.1016\/j.knosys.2026.115729_bib0035","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/TAFFC.2023.3282410","article-title":"Multi-task momentum distillation for multimodal sentiment analysis","volume":"15","author":"Lin","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.115729_bib0036","series-title":"2023 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1367","article-title":"Multimodal sentiment analysis with preferential fusion and distance-aware contrastive learning","author":"Ma","year":"2023"},{"issue":"7","key":"10.1016\/j.knosys.2026.115729_bib0037","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1049\/iet-cvi.2020.0013","article-title":"Deep emotion recognition based on audio\u2013visual correlation","volume":"14","author":"Hajarolasvadi","year":"2020","journal-title":"IET Comput. Vision"},{"key":"10.1016\/j.knosys.2026.115729_bib0038","series-title":"Proceedings of the 4th International Conference on Machine Learning and Soft Computing","first-page":"34-39","article-title":"Multimodal sentiment analysis based on multi-head attention mechanism","author":"Xi","year":"2020"},{"issue":"11","key":"10.1016\/j.knosys.2026.115729_bib0039","doi-asserted-by":"crossref","first-page":"15467","DOI":"10.1109\/JIOT.2025.3527864","article-title":"Privacy-preserving multimodal sentiment analysis","volume":"12","author":"Xu","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"8","key":"10.1016\/j.knosys.2026.115729_bib0040","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1007\/s11227-025-07474-6","article-title":"Triaxial modality attention fusion with top-down mask generation for enhanced multimodal sentiment analysis","volume":"81","author":"Feng","year":"2025","journal-title":"J. Supercomput."},{"key":"10.1016\/j.knosys.2026.115729_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110706","article-title":"CLVIN: complete language-vision interaction network for visual question answering","volume":"275","author":"Chen","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115729_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110084","article-title":"MPCCT: multimodal vision-language learning paradigm with context-based compact transformer","volume":"147","author":"Chen","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.115729_bib0043","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25","first-page":"1802","article-title":"Multimodal cancer survival analysis via hypergraph learning with cross-modality rebalance","author":"Qu","year":"2025"},{"issue":"3","key":"10.1016\/j.knosys.2026.115729_bib0044","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1111\/1467-9868.00196","article-title":"Probabilistic principal component analysis","volume":"61","author":"Tipping","year":"1999","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.knosys.2026.115729_bib0045","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.knosys.2026.115729_bib0046","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.knosys.2026.115729_bib0047","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"06","key":"10.1016\/j.knosys.2026.115729_bib0048","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 Intell. Syst."},{"key":"10.1016\/j.knosys.2026.115729_bib0049","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"Bagher Zadeh","year":"2018"},{"key":"10.1016\/j.knosys.2026.115729_bib0050","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"527","article-title":"MELD: a multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"key":"10.1016\/j.knosys.2026.115729_bib0051","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.knosys.2026.115729_bib0052","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2247","article-title":"Efficient low-rank multimodal fusion with modality-specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.knosys.2026.115729_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119240","article-title":"Heterogeneous graph convolution based on in-domain self-supervision for multimodal sentiment analysis","volume":"213","author":"Zeng","year":"2023","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"10.1016\/j.knosys.2026.115729_bib0054","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1109\/TAFFC.2024.3456117","article-title":"Hierarchical knowledge stripping for multimodal sentiment analysis","volume":"16","author":"Xiong","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.knosys.2026.115729_bib0055","series-title":"Proceedings of the 57Th Annual Meeting of the Association for Computational Linguistics","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","author":"Tsai","year":"2019"},{"key":"10.1016\/j.knosys.2026.115729_bib0056","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.aej.2024.12.117","article-title":"Temporal text-guided feedback-based progressive fusion network for multimodal sentiment analysis","volume":"116","author":"Yang","year":"2025","journal-title":"Alexandr. Eng. J."},{"issue":"1","key":"10.1016\/j.knosys.2026.115729_bib0057","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1109\/TAFFC.2024.3430045","article-title":"Diversity and balance: multimodal sentiment analysis using multimodal-prefixed and cross-modal attention","volume":"16","author":"Li","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"10.1016\/j.knosys.2026.115729_bib0058","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s11227-024-06729-y","article-title":"MECG: modality-enhanced convolutional graph for unbalanced multimodal representations","volume":"81","author":"Tang","year":"2025","journal-title":"J. Supercomput."},{"key":"10.1016\/j.knosys.2026.115729_bib0059","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.112346","article-title":"Reconstructing representations using diffusion models for multimodal sentiment analysis through reading comprehension","volume":"167","author":"Zhang","year":"2024","journal-title":"Appl. Soft. Comput."},{"key":"10.1016\/j.knosys.2026.115729_bib0060","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"2506","article-title":"Multi-modal sarcasm detection in twitter with hierarchical fusion model","author":"Cai","year":"2019"},{"key":"10.1016\/j.knosys.2026.115729_bib0061","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"4351","article-title":"Sentiment and emotion help sarcasm? a multi-task learning framework for multi-modal sarcasm, sentiment and emotion analysis","author":"Chauhan","year":"2020"},{"key":"10.1016\/j.knosys.2026.115729_bib0062","series-title":"Proceedings of the Web Conference 2020","first-page":"2514","article-title":"Transmodality: an end2end fusion method with transformer for multimodal sentiment analysis","author":"Wang","year":"2020"},{"key":"10.1016\/j.knosys.2026.115729_bib0063","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"2608","article-title":"Missing modality imagination network for emotion recognition with uncertain missing modalities","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2026.115729_bib0064","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.inffus.2023.01.005","article-title":"A multitask learning model for multimodal sarcasm, sentiment and emotion recognition in conversations","volume":"93","author":"Zhang","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.115729_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101973","article-title":"Modality translation-based multimodal sentiment analysis under uncertain missing modalities","volume":"101","author":"Liu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2026.115729_bib0066","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114287","article-title":"Personalized multimodal sentiment analysis under uncertain modalities missing via pretraining and online learning","author":"Sun","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115729_bib0067","unstructured":"THUIAR, MMSA: a unified multimodal sentiment analysis toolkit, 2023, (https:\/\/github.com\/thuiar\/MMSA). Accessed: 2026-02-23."},{"key":"10.1016\/j.knosys.2026.115729_bib0068","series-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2188","article-title":"Multimodal transformers are hierarchical modal-wise heterogeneous graphs","author":"Jin","year":"2025"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126004697?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126004697?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:06:24Z","timestamp":1776125184000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126004697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":68,"alternative-id":["S0950705126004697"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115729","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DMIC2: A dynamic modality importance and cascaded cross-attention framework for multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115729","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":"115729"}}