{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T16:01:35Z","timestamp":1784044895059,"version":"3.55.0"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100016692","name":"Key Research and Development Program of Ningxia","doi-asserted-by":"publisher","award":["2024Z123"],"award-info":[{"award-number":["2024Z123"]}],"id":[{"id":"10.13039\/100016692","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":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113445","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:43:48Z","timestamp":1772815428000},"page":"113445","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Beyond a single perspective: A multi-agent debate framework for affective computing"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0968-2269","authenticated-orcid":false,"given":"Yijie","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2273-6927","authenticated-orcid":false,"given":"Yuanchun","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2591-7993","authenticated-orcid":false,"given":"Chun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangzeng","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1642-0758","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nai\u2019an","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.patcog.2026.113445_bib0001","doi-asserted-by":"crossref","first-page":"2767","DOI":"10.11834\/jig.200498","article-title":"Agent affective computing in human-computer interaction","volume":"26","author":"Liu","year":"2021","journal-title":"J. Image Graph."},{"key":"10.1016\/j.patcog.2026.113445_bib0002","first-page":"57","article-title":"Understanding multimodal emotional expressions: recent advances in basic emotion theory","author":"Keltner","year":"2017"},{"key":"10.1016\/j.patcog.2026.113445_bib0003","series-title":"International Conference on Affective Computing and Intelligent Interaction","first-page":"981","article-title":"Affective computing: a review","author":"Tao","year":"2005"},{"issue":"10","key":"10.1016\/j.patcog.2026.113445_bib0004","doi-asserted-by":"crossref","first-page":"6729","DOI":"10.1109\/TPAMI.2021.3094362","article-title":"Affective image content analysis: two decades review and new perspectives","volume":"44","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.patcog.2026.113445_bib0005","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1109\/TAFFC.2016.2628787","article-title":"Predicting personalized image emotion perceptions in social networks","volume":"9","author":"Zhao","year":"2016","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113445_bib0006","doi-asserted-by":"crossref","first-page":"754","DOI":"10.3389\/fnhum.2013.00754","article-title":"Connecting multimodality in human communication","volume":"7","author":"Regenbogen","year":"2013","journal-title":"Front. Hum. Neurosci."},{"issue":"17","key":"10.1016\/j.patcog.2026.113445_bib0007","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.3390\/app11177962","article-title":"Deep multimodal emotion recognition on human speech: a review","volume":"11","author":"Koromilas","year":"2021","journal-title":"Appl. Sci."},{"issue":"10","key":"10.1016\/j.patcog.2026.113445_bib0008","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1109\/JPROC.2023.3309299","article-title":"Toward label-efficient emotion and sentiment analysis","volume":"111","author":"Zhao","year":"2023","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.patcog.2026.113445_bib0009","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.inffus.2022.03.009","article-title":"A systematic review on affective computing: emotion models, databases, and recent advances","volume":"83","author":"Wang","year":"2022","journal-title":"Inf. Fusion"},{"issue":"7","key":"10.1016\/j.patcog.2026.113445_bib0010","first-page":"1","article-title":"An effective data fusion methodology for multi-modal emotion recognition: a survey","volume":"12","author":"Sanku","year":"2024","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"issue":"2","key":"10.1016\/j.patcog.2026.113445_bib0011","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/MIS.2025.3544912","article-title":"A retrieval-augmented multiagent system for financial sentiment analysis","volume":"40","author":"Du","year":"2025","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.patcog.2026.113445_bib0012","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","article-title":"A review of affective computing: from unimodal analysis to multimodal fusion","volume":"37","author":"Poria","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113445_bib0013","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":"Zadeh","year":"2018"},{"issue":"4","key":"10.1016\/j.patcog.2026.113445_bib0014","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."},{"issue":"2","key":"10.1016\/j.patcog.2026.113445_bib0015","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 Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113445_bib0016","doi-asserted-by":"crossref","unstructured":"A. Zadeh, M. Chen, S. Poria, E. Cambria, L.-P. Morency, Tensor fusion network for multimodal sentiment analysis, (2017). arXiv: 1707.07250.","DOI":"10.18653\/v1\/D17-1115"},{"key":"10.1016\/j.patcog.2026.113445_bib0017","series-title":"Proc. Annu. Meeting Assoc. Comput. Linguist. (ACL)","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","author":"Tsai","year":"2019"},{"key":"10.1016\/j.patcog.2026.113445_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4761","article-title":"An effective ensemble learning framework for affective behaviour analysis","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113445_bib0019","doi-asserted-by":"crossref","unstructured":"D. Ghosal, N. Majumder, S. Poria, N. Chhaya, A. Gelbukh, DialogueGCN: a graph convolutional neural network for emotion recognition in conversation, (2019). arXiv: 1908.11540.","DOI":"10.18653\/v1\/D19-1015"},{"key":"10.1016\/j.patcog.2026.113445_bib0020","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"},{"issue":"2","key":"10.1016\/j.patcog.2026.113445_bib0021","first-page":"44","article-title":"DARPA\u2019s explainable artificial intelligence (XAI) program","volume":"40","author":"Gunning","year":"2019","journal-title":"AI Mag."},{"issue":"8","key":"10.1016\/j.patcog.2026.113445_bib0022","doi-asserted-by":"crossref","first-page":"7778","DOI":"10.1109\/TCSVT.2025.3544659","article-title":"Exploring rich subjective quality information for image quality assessment in the wild","volume":"35","author":"Min","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"10.1016\/j.patcog.2026.113445_bib0023","doi-asserted-by":"crossref","DOI":"10.1093\/nsr\/nwae403","article-title":"A survey on multimodal large language models","volume":"11","author":"Yin","year":"2024","journal-title":"Natl. Sci. Rev."},{"key":"10.1016\/j.patcog.2026.113445_bib0024","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, (2023). arXiv: 2303.08774."},{"key":"10.1016\/j.patcog.2026.113445_bib0025","unstructured":"J. Bai, S. Bai, Y. Chu, Z. Cui, K. Dang, X. Deng, Y. Fan, W. Ge, Y. Han, F. Huang, et al., Qwen technical report, (2023). arXiv: 2309.16609."},{"key":"10.1016\/j.patcog.2026.113445_bib0026","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113445_bib0027","unstructured":"X. Qiu, H. Wang, X. Tan, C. Qu, Y. Xiong, Y. Cheng, Y. Xu, W. Chu, Y. Qi, Towards collaborative intelligence: propagating intentions and reasoning for multi-agent coordination with large language models, (2024). arXiv: 2407.12532."},{"key":"10.1016\/j.patcog.2026.113445_bib0028","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"15174","article-title":"ChatDev: communicative agents for software development","author":"Qian","year":"2024"},{"key":"10.1016\/j.patcog.2026.113445_bib0029","series-title":"The Twelfth International Conference on Learning Representations","article-title":"MetaGPT: meta programming for a multi-agent collaborative framework","author":"Hong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113445_bib0030","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"17889","article-title":"Encouraging divergent thinking in large language models through multi-agent debate","author":"Liang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113445_bib0031","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track","first-page":"650","article-title":"Self-criticism: aligning large language models with their understanding of helpfulness, honesty, and harmlessness","author":"Tan","year":"2023"},{"key":"10.1016\/j.patcog.2026.113445_bib0032","series-title":"Forty-First International Conference on Machine Learning","first-page":"11733","article-title":"Improving factuality and reasoning in language models through multiagent debate","volume":"235","author":"Du","year":"2024"},{"key":"10.1016\/j.patcog.2026.113445_bib0033","unstructured":"A. Zadeh, R. Zellers, E. Pincus, L.-P. Morency, MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos, (2016). arXiv: 1606.06259."},{"key":"10.1016\/j.patcog.2026.113445_bib0034","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"3718","article-title":"CH-SIMS: a Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality","author":"Yu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113445_bib0035","series-title":"Proceedings of the 2022 International Conference on Multimodal Interaction","first-page":"247","article-title":"Make acoustic and visual cues matter: CH-SIMS v2. 0 dataset and AV-mixup consistent module","author":"Liu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113445_bib0036","unstructured":"Y. Yao, T. Yu, A. Zhang, C. Wang, J. Cui, H. Zhu, T. Cai, H. Li, W. Zhao, Z. He, et al., MiniCPM-V: a GPT-4V level MLLM on your phone, (2024). arXiv: 2408.01800."},{"key":"10.1016\/j.patcog.2026.113445_bib0037","unstructured":"Z. Liu, Y. Dong, J. Wang, Z. Liu, W. Hu, J. Lu, Y. Rao, Ola: Pushing the frontiers of omni-modal language model, (2025). arXiv: 2502.04328."},{"key":"10.1016\/j.patcog.2026.113445_bib0038","unstructured":"Y. Su, T. Lan, H. Li, J. Xu, Y. Wang, D. Cai, PandaGPT: one model to instruction-follow them all, (2023). arXiv: 2305.16355."},{"key":"10.1016\/j.patcog.2026.113445_bib0039","doi-asserted-by":"crossref","first-page":"4121","DOI":"10.1109\/TMM.2022.3171679","article-title":"Multimodal information bottleneck: learning minimal sufficient unimodal and multimodal representations","volume":"25","author":"Mai","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113445_bib0040","doi-asserted-by":"crossref","first-page":"110805","DOI":"10.52202\/079017-3518","article-title":"Emotion-LLaMA: multimodal emotion recognition and reasoning with instruction tuning","volume":"37","author":"Cheng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113445_bib0041","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"1997","article-title":"Towards explainable fusion and balanced learning in multimodal sentiment analysis","author":"Luo","year":"2025"},{"key":"10.1016\/j.patcog.2026.113445_bib0042","series-title":"Proceedings of the ACM on Web Conference 2025","first-page":"2120","article-title":"Learning by comparing: boosting multimodal affective computing through ordinal learning","author":"Mai","year":"2025"},{"key":"10.1016\/j.patcog.2026.113445_bib0043","unstructured":"Z. Cheng, S. Leng, H. Zhang, Y. Xin, X. Li, G. Chen, Y. Zhu, W. Zhang, Z. Luo, D. Zhao, et al., VideoLLaMA 2: advancing spatial-temporal modeling and audio understanding in video-LLMs, (2024). arXiv: 2406.07476."},{"issue":"3","key":"10.1016\/j.patcog.2026.113445_bib0044","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1109\/TAFFC.2025.3553149","article-title":"Injecting multimodal information into pre-trained language model for multimodal sentiment analysis","volume":"16","author":"Mai","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113445_bib0045","unstructured":"J. Xu, Z. Guo, J. He, H. Hu, T. He, S. Bai, K. Chen, J. Wang, Y. Fan, K. Dang, et al., Qwen2. 5-omni technical report, (2025). arXiv: 2503.20215."},{"key":"10.1016\/j.patcog.2026.113445_bib0046","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.knosys.2018.07.041","article-title":"Multimodal sentiment analysis using hierarchical fusion with context modeling","volume":"161","author":"Majumder","year":"2018","journal-title":"Knowl. Based Syst."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004115?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004115?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:58:32Z","timestamp":1779382712000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004115"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":46,"alternative-id":["S0031320326004115"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113445","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond a single perspective: A multi-agent debate framework for affective computing","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113445","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":"113445"}}