{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T18:12:43Z","timestamp":1788286363836,"version":"build-2803163510"},"reference-count":74,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["HIT.DZJJ.2025050"],"award-info":[{"award-number":["HIT.DZJJ.2025050"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP20123-0005"],"award-info":[{"award-number":["MOE-T2EP20123-0005"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["PCL2025AS209"],"award-info":[{"award-number":["PCL2025AS209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176076"],"award-info":[{"award-number":["62176076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["625B2060"],"award-info":[{"award-number":["625B2060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.patcog.2026.113087","type":"journal-article","created":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T00:25:58Z","timestamp":1768609558000},"page":"113087","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["Is multimodal conversational emotion recognition satisfactory? Exploring the gaps in performance, generalization, and confidence"],"prefix":"10.1016","volume":"175","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8256-7049","authenticated-orcid":false,"given":"Geng","family":"Tu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4812-0493","authenticated-orcid":false,"given":"Ran","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2969-9858","authenticated-orcid":false,"given":"Xuan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3030-1280","authenticated-orcid":false,"given":"Erik","family":"Cambria","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-8864","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4009-5679","authenticated-orcid":false,"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113087_bib0001","series-title":"AAAI","first-page":"6818","article-title":"Dialoguernn: an attentive rnn for emotion detection in conversations","volume":"33","author":"Majumder","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0002","series-title":"Findings of EMNLP","first-page":"2470","article-title":"COSMIC: commonsense knowledge for emotion identification in conversations","author":"Ghosal","year":"2020"},{"key":"10.1016\/j.patcog.2026.113087_bib0003","series-title":"ACL-IJCNLP","first-page":"5666","article-title":"MMGCN: multimodal fusion via deep graph convolution network for emotion recognition in conversation","author":"Hu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113087_bib0004","series-title":"EMNLP","first-page":"15154","article-title":"Conversation understanding using relational temporal graph neural networks with auxiliary cross-modality interaction","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0005","series-title":"AAAI","first-page":"19089","article-title":"Adaptive graph learning for multimodal conversational emotion detection","volume":"38","author":"Tu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128532","article-title":"Fine-grained multimodal fusion for depression assisted recognition based on hierarchical knowledge-enhanced prompt learning","volume":"291","author":"Yang","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"10.1016\/j.patcog.2026.113087_bib0007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12559-025-10463-9","article-title":"Contrastive-based removal of negative information in multimodal emotion analysis","volume":"17","author":"Wang","year":"2025","journal-title":"Cognit. Comput."},{"key":"10.1016\/j.patcog.2026.113087_bib0008","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.patcog.2026.113087_bib0009","series-title":"WWW","first-page":"2915","article-title":"Supportplay: a multi-agent role-playing system for personalized and sustained multimodal emotional support conversation","author":"Tu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113087_bib0010","series-title":"CVPR","first-page":"10761","article-title":"Multivariate, multi-frequency and multimodal: rethinking graph neural networks for emotion recognition in conversation","author":"Chen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0011","series-title":"EMNLP-IJCNLP","first-page":"154","article-title":"DialogueGCN: a graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0012","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1109\/TMM.2023.3271019","article-title":"A transformer-based model with self-distillation for multimodal emotion recognition in conversations","volume":"26","author":"Ma","year":"2023","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.patcog.2026.113087_bib0013","series-title":"ACL","first-page":"14752","article-title":"MultiEMO: an attention-based correlation-aware multimodal fusion framework for emotion recognition in conversations","author":"Shi","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0014","series-title":"ICASSP","first-page":"7037","article-title":"MM-DFN: multimodal dynamic fusion network for emotion recognition in conversations","author":"Hu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113087_bib0015","series-title":"EMNLP","first-page":"2594","article-title":"Icon: interactive conversational memory network for multimodal emotion detection","author":"Hazarika","year":"2018"},{"key":"10.1016\/j.patcog.2026.113087_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107598","article-title":"Exploration meets exploitation: multitask learning for emotion recognition based on discrete and dimensional models","volume":"235","author":"Tu","year":"2022","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.patcog.2026.113087_bib0017","series-title":"NAACL","first-page":"82","article-title":"TelME: teacher-leading multimodal fusion network for emotion recognition in conversation","author":"Yun","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0018","series-title":"Findings of EMNLP","first-page":"3861","article-title":"Multiple knowledge-enhanced interactive graph network for multimodal conversational emotion recognition","author":"Tu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0019","unstructured":"Z. Lian, L. Sun, Y. Ren, H. Gu, H. Sun, L. Chen, B. Liu, J. Tao, MERBench: a unified evaluation benchmark for multimodal emotion recognition, arXiv: 2401.03429(2024)."},{"key":"10.1016\/j.patcog.2026.113087_bib0020","series-title":"ACM MM","first-page":"9621","article-title":"Multimodal emotion recognition calibration in conversations","author":"Tu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0021","series-title":"ICLR","first-page":"23429","article-title":"Calibrating multimodal learning","author":"Ma","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0022","doi-asserted-by":"crossref","first-page":"1803","DOI":"10.1109\/TAFFC.2022.3223517","article-title":"Sentiment-emotion-and context-guided knowledge selection framework for emotion recognition in conversations","volume":"14","author":"Tu","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113087_bib0023","unstructured":"D. Hu, L. Wei, X. Huai, DialogueCRN: contextual reasoning networks for emotion recognition in conversations, arXiv: 2106.01978(2021)."},{"key":"10.1016\/j.patcog.2026.113087_bib0024","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.neucom.2021.09.057","article-title":"BiERU: bidirectional emotional recurrent unit for conversational sentiment analysis","volume":"467","author":"Li","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113087_bib0025","series-title":"AAAI","first-page":"13789","article-title":"DialogXL: all-in-one XLNet for multi-party conversation emotion recognition","volume":"35","author":"Shen","year":"2021"},{"issue":"3","key":"10.1016\/j.patcog.2026.113087_bib0026","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.1109\/TAFFC.2022.3232166","article-title":"AutoML-Emo: automatic knowledge selection using congruent effect for emotion identification in conversations","volume":"14","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113087_bib0027","series-title":"Findings of ACL","first-page":"14054","article-title":"Context or knowledge is not always necessary: a contrastive learning framework for emotion recognition in conversations","author":"Tu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0028","series-title":"EMNLP-IJCNLP","article-title":"DialogueGCN: a graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2020"},{"key":"10.1016\/j.patcog.2026.113087_bib0029","series-title":"ECAI","first-page":"2362","article-title":"Do topic and causal consistency affect emotion cognition? A graph interactive network for conversational emotion detection","author":"Tu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0030","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F.L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al., Gpt-4 technical report, arXiv: 2303.08774(2023)."},{"key":"10.1016\/j.patcog.2026.113087_bib0031","unstructured":"S. Lei, G. Dong, X. Wang, K. Wang, S. Wang, InstructERC: reforming emotion recognition in conversation with a retrieval multi-task llms framework, arXiv: 2309.11911(2023)."},{"key":"10.1016\/j.patcog.2026.113087_bib0032","series-title":"ACL","first-page":"2359","article-title":"Integrating multimodal information in large pretrained transformers","volume":"2020","author":"Rahman","year":"2020"},{"key":"10.1016\/j.patcog.2026.113087_bib0033","series-title":"AAAI","first-page":"7216","article-title":"Words can shift: dynamically adjusting word representations using nonverbal behaviors","volume":"33","author":"Wang","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0034","series-title":"ICASSP","first-page":"7037","article-title":"MM-DFN: multimodal dynamic fusion network for emotion recognition in conversations","author":"Hu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113087_bib0035","doi-asserted-by":"crossref","unstructured":"Z. Cheng, Z.-Q. Cheng, J.-Y. He, J. Sun, K. Wang, Y. Lin, Z. Lian, X. Peng, A. Hauptmann, Emotion-LLaMA: multimodal emotion recognition and reasoning with instruction tuning, arXiv: 2406.11161(2024).","DOI":"10.52202\/079017-3518"},{"key":"10.1016\/j.patcog.2026.113087_bib0036","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.patcog.2026.113087_bib0037","series-title":"ACL","first-page":"527","article-title":"MELD: a multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0038","series-title":"ACL","first-page":"6345","article-title":"Topic modeling with wasserstein autoencoders","author":"Nan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0039","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, et al., Llama 2: open foundation and fine-tuned chat models, arXiv: 2307.09288(2023)."},{"key":"10.1016\/j.patcog.2026.113087_bib0040","series-title":"Forty-second International Conference on Machine Learning","article-title":"AffectGPT: a new dataset, model, and benchmark for emotion understanding with multimodal large language models","author":"Lian","year":"2025"},{"key":"10.1016\/j.patcog.2026.113087_bib0041","unstructured":"P. Wang, S. Bai, S. Tan, S. Wang, Z. Fan, J. Bai, K. Chen, X. Liu, J. Wang, W. Ge, et al., Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution, arXiv: 2409.12191(2024)."},{"key":"10.1016\/j.patcog.2026.113087_bib0042","unstructured":"H. Lu, W. Liu, B. Zhang, B. Wang, K. Dong, B. Liu, J. Sun, T. Ren, Z. Li, H. Yang, et al., DeepSeek-VL: towards real-world vision-language understanding, arXiv: 2403.05525(2024)."},{"key":"10.1016\/j.patcog.2026.113087_bib0043","series-title":"EMNLP","first-page":"5971","article-title":"Video-LLaVA: learning united visual representation by alignment before projection","author":"Lin","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0044","series-title":"CVPR","first-page":"26689","article-title":"Vila: on pre-training for visual language models","author":"Lin","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0045","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.patcog.2026.113087_bib0046","series-title":"ICML","first-page":"1321","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"10.1016\/j.patcog.2026.113087_bib0047","series-title":"CVPR","first-page":"2686","article-title":"Improving confidence estimates for unfamiliar examples","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113087_bib0048","series-title":"ICML","first-page":"7034","article-title":"Confidence-aware learning for deep neural networks","author":"Moon","year":"2020"},{"key":"10.1016\/j.patcog.2026.113087_bib0049","series-title":"ECCV","first-page":"518","article-title":"Rethinking confidence calibration for failure prediction","author":"Zhu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113087_bib0050","series-title":"Findings of ACL","first-page":"8702","article-title":"Fact-and-reflection (FaR) improves confidence calibration of large language models","author":"Zhao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113087_bib0051","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patcog.2026.113087_bib0052","first-page":"10078","article-title":"VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113087_bib0053","series-title":"CVPR","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.patcog.2026.113087_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105171","article-title":"Eva-02: a visual representation for neon genesis","volume":"149","author":"Fang","year":"2024","journal-title":"Image Vis. Comput."},{"issue":"2","key":"10.1016\/j.patcog.2026.113087_bib0055","doi-asserted-by":"crossref","first-page":"199","DOI":"10.3390\/biomimetics8020199","article-title":"Distract your attention: multi-head cross attention network for facial expression recognition","volume":"8","author":"Wen","year":"2023","journal-title":"Biomimetics"},{"key":"10.1016\/j.patcog.2026.113087_bib0056","series-title":"ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113087_bib0057","series-title":"SLaTE","first-page":"48","article-title":"Acoustic correlates of speech intelligibility: the usability of the eGeMAPS feature set for atypical speech","author":"Xue","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0058","first-page":"312","article-title":"The Interspeech 2009 emotion challenge","author":"SCHULLER","year":"2009","journal-title":"Interspeech"},{"key":"10.1016\/j.patcog.2026.113087_bib0059","series-title":"Interspeech","first-page":"3465","article-title":"wav2vec: unsupervised pre-training for speech recognition","author":"Schneider","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0060","series-title":"ICML","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0061","unstructured":"T. GLM, A. Zeng, B. Xu, B. Wang, C. Zhang, D. Yin, D. Zhang, D. Rojas, G. Feng, H. Zhao, et al., ChatGLM: a family of large language models from GLM-130b to GLM-4 all tools, arXiv: 2406.12793(2024)."},{"key":"10.1016\/j.patcog.2026.113087_bib0062","series-title":"EMNLP-IJCNLP","first-page":"3982","article-title":"Sentence-BERT: sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.patcog.2026.113087_bib0063","unstructured":"B. Workshop, T.L. Scao, A. Fan, C. Akiki, E. Pavlick, S. Ili\u0107, D. Hesslow, R. Castagn\u00e9, A.S. Luccioni, F. Yvon, et al., BLOOM: a 176b-parameter open-access multilingual language model, arXiv: 2211.05100(2022)."},{"key":"10.1016\/j.patcog.2026.113087_bib0064","unstructured":"Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, V. Stoyanov, RoBERTa: a robustly optimized bert pretraining approach, arXiv: 1907.11692(2019)."},{"key":"10.1016\/j.patcog.2026.113087_bib0065","unstructured":"A. Yang, B. Xiao, B. Wang, B. Zhang, C. Bian, C. Yin, C. Lv, D. Pan, D. Wang, D. Yan, et al., Baichuan 2: open large-scale language models, arXiv: 2309.10305(2023)."},{"key":"10.1016\/j.patcog.2026.113087_bib0066","series-title":"EMNLP","first-page":"1532","article-title":"Glove: global vectors for word representation","author":"Pennington","year":"2014"},{"key":"10.1016\/j.patcog.2026.113087_bib0067","series-title":"EMNLP","first-page":"15639","article-title":"A training-free debiasing framework with counterfactual reasoning for conversational emotion detection","author":"Tu","year":"2023"},{"issue":"6","key":"10.1016\/j.patcog.2026.113087_bib0068","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.patcog.2026.113087_bib0069","unstructured":"A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan, et al., The Llama 3 herd of models, arXiv e-prints (2024) arXiv:2407.21783."},{"key":"10.1016\/j.patcog.2026.113087_bib0070","unstructured":"A. Yang, A. Li, B. Yang, B. Zhang, B. Hui, B. Zheng, B. Yu, C. Gao, C. Huang, C. Lv, et al., Qwen3 technical report, arXiv: 2505.09388(2025)."},{"key":"10.1016\/j.patcog.2026.113087_bib0071","series-title":"EMNLP","first-page":"16051","article-title":"Joyful: joint modality fusion and graph contrastive learning for multimoda emotion recognition","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113087_bib0072","unstructured":"H. Liu, J.Z. HaoChen, A. Gaidon, T. Ma, Self-supervised learning is more robust to dataset imbalance, in: NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications."},{"key":"10.1016\/j.patcog.2026.113087_bib0073","doi-asserted-by":"crossref","unstructured":"T. Yue, R. Mao, H. Wang, Z. Hu, E. Cambria, KnowleNet: Knowledge fusion network for multimodal sarcasm detection, Information Fusion 100, (2023), 101921. 10.1016\/j.inffus.2023.101921.","DOI":"10.1016\/j.inffus.2023.101921"},{"key":"10.1016\/j.patcog.2026.113087_bib0074","doi-asserted-by":"crossref","unstructured":"L. Wei, Z. Luyao, M. Rui, C. Erik, SKIER: A symbolic knowledge integrated model for conversational emotion recognition, in: AAAI, 37, (11), 2023, pp. 13121\u201313129.","DOI":"10.1609\/aaai.v37i11.26541"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326000506?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326000506?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T17:12:53Z","timestamp":1788282773000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326000506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":74,"alternative-id":["S0031320326000506"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113087","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Is multimodal conversational emotion recognition satisfactory? Exploring the gaps in performance, generalization, and confidence","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113087","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113087"}}