{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:04:02Z","timestamp":1780495442721,"version":"3.54.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["62476188"],"award-info":[{"award-number":["62476188"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113519","type":"journal-article","created":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:10:12Z","timestamp":1774051812000},"page":"113519","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Beyond action units: Towards multi-cue facial emotion analysis"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6718-4942","authenticated-orcid":false,"given":"Yucheng","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1635-3440","authenticated-orcid":false,"given":"Jiulong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1055-0660","authenticated-orcid":false,"given":"Yikai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6547-1984","authenticated-orcid":false,"given":"Lingyong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-0370","authenticated-orcid":false,"given":"Min","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113519_bib0001","series-title":"Proceedings of the Asian Conference on Computer Vision","article-title":"RAF-AU database: in-the-wild facial expressions with subjective emotion judgement and objective au annotations","author":"Yan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113519_bib0002","doi-asserted-by":"crossref","unstructured":"A. Chaubey, X. Guan, M. Soleymani, Face-LLaVA: facial expression and attribute understanding through instruction tuning, (2025). arXiv: 2504.07198.","DOI":"10.1109\/WACV61042.2026.00260"},{"issue":"2","key":"10.1016\/j.patcog.2026.113519_bib0003","doi-asserted-by":"crossref","first-page":"401","DOI":"10.3390\/s18020401","article-title":"A brief review of facial emotion recognition based on visual information","volume":"18","author":"Ko","year":"2018","journal-title":"Sensors"},{"issue":"12","key":"10.1016\/j.patcog.2026.113519_bib0004","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1145\/3186591","article-title":"Designing emotionally sentient agents","volume":"61","author":"McDuff","year":"2018","journal-title":"Commun. ACM"},{"issue":"4","key":"10.1016\/j.patcog.2026.113519_bib0005","first-page":"7061","article-title":"Mental health diagnosis of college students based on facial recognition and neural network","volume":"40","author":"Liu","year":"2021","journal-title":"J. Intell. Fuzzy Syst."},{"key":"10.1016\/j.patcog.2026.113519_bib0006","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113519_bib0007","doi-asserted-by":"crossref","first-page":"49250","DOI":"10.52202\/075280-2142","article-title":"Instructblip: towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113519_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26296","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113519_bib0009","series-title":"European Conference on Computer Vision","first-page":"165","article-title":"Facial affective behavior analysis with instruction tuning","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.113519_bib0010","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1109\/TMM.2025.3557704","article-title":"ExpLLM: towards chain of thought for facial expression recognition","volume":"27","author":"Lan","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113519_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111783","article-title":"Exp-VQA: fine-grained facial expression analysis via visual question answering","volume":"168","author":"Yuan","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113519_bib0012","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."},{"issue":"1","key":"10.1016\/j.patcog.2026.113519_bib0013","doi-asserted-by":"crossref","first-page":"83","DOI":"10.24425\/ppb.2021.136819","article-title":"Sex and age differences in facial emotions expressions measured by artificial intelligence","volume":"52","author":"Gabl\u00edkov\u00e1","year":"2021","journal-title":"Polish Psychol. Bull."},{"issue":"8","key":"10.1016\/j.patcog.2026.113519_bib0014","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0003022","article-title":"Culture shapes how we look at faces","volume":"3","author":"Blais","year":"2008","journal-title":"PLoS ONE"},{"issue":"1","key":"10.1016\/j.patcog.2026.113519_bib0015","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1037\/a0023463","article-title":"Internal representations reveal cultural diversity in expectations of facial expressions of emotion","volume":"141","author":"Jack","year":"2012","journal-title":"J. Exp. Psychol. Gen."},{"key":"10.1016\/j.patcog.2026.113519_bib0016","unstructured":"B. Xing, Z. Yu, X. Liu, K. Yuan, Q. Ye, W. Xie, H. Yue, J. Yang, H. K\u00e4lvi\u00e4inen, EMO-LLaMA: enhancing facial emotion understanding with instruction tuning, (2024). arXiv: 2408.11424."},{"key":"10.1016\/j.patcog.2026.113519_bib0017","unstructured":"A. Liu, A. Mei, B. Lin, B. Xue, B. Wang, B. Xu, B. Wu, B. Zhang, C. Lin, C. Dong, et al., DeepSeek-v3. 2: pushing the frontier of open large language models, (2025). arXiv: 2512.02556."},{"key":"10.1016\/j.patcog.2026.113519_bib0018","series-title":"International Conference on Neural Information Processing","first-page":"117","article-title":"Challenges in representation learning: a report on three machine learning contests","author":"Goodfellow","year":"2013"},{"issue":"1","key":"10.1016\/j.patcog.2026.113519_bib0019","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","article-title":"AffectNet: a database for facial expression, valence, and arousal computing in the wild","volume":"10","author":"Mollahosseini","year":"2017","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"2","key":"10.1016\/j.patcog.2026.113519_bib0020","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","article-title":"DISFA : a spontaneous facial action intensity database","volume":"4","author":"Mavadati","year":"2013","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"10","key":"10.1016\/j.patcog.2026.113519_bib0021","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1016\/j.imavis.2014.06.002","article-title":"BP4D-spontaneous: a high-resolution spontaneous 3D dynamic facial expression database","volume":"32","author":"Zhang","year":"2014","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.patcog.2026.113519_bib0022","series-title":"European Conference on Computer Vision","first-page":"144","article-title":"Emotion recognition for multiple context awareness","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113519_bib0023","unstructured":"G. Comanici, E. Bieber, M. Schaekermann, I. Pasupat, N. Sachdeva, I. Dhillon, M. Blistein, O. Ram, D. Zhang, E. Rosen, et al., Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities,(2025). arXiv: 2507.06261."},{"key":"10.1016\/j.patcog.2026.113519_bib0024","unstructured":"S. Bai, K. Chen, X. Liu, J. Wang, W. Ge, S. Song, K. Dang, P. Wang, S. Wang, J. Tang, et al., Qwen2. 5-VL technical report, (2025). arXiv: 2502.13923."},{"key":"10.1016\/j.patcog.2026.113519_bib0025","unstructured":"Q. Team, Qwen3 Technical Report, 2025. arXiv: 2505.09388."},{"key":"10.1016\/j.patcog.2026.113519_bib0026","unstructured":"xAI, Grok 4, 2025. Accessed: 2025-12-26, https:\/\/x.ai\/blog\/grok-4."},{"issue":"10","key":"10.1016\/j.patcog.2026.113519_bib0027","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"},{"issue":"10","key":"10.1016\/j.patcog.2026.113519_bib0028","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":"1","key":"10.1016\/j.patcog.2026.113519_bib0029","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1109\/TAFFC.2024.3423671","article-title":"Multi-level contrastive learning: hierarchical alleviation of heterogeneity in multimodal sentiment analysis","volume":"16","author":"Fan","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113519_bib0030","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1109\/TASLPRO.2025.3533359","article-title":"Cross-modal knowledge distillation with multi-stage adaptive feature fusion for speech separation","volume":"33","author":"Fan","year":"2025","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113519_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102522","article-title":"Light-weight residual convolution-based capsule network for EEG emotion recognition","volume":"61","author":"Fan","year":"2024","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.patcog.2026.113519_bib0032","series-title":"2015 14th IAPR International Conference on Machine Vision Applications (MVA)","first-page":"279","article-title":"A deep-learning approach to facial expression recognition with candid images","author":"Li","year":"2015"},{"issue":"5","key":"10.1016\/j.patcog.2026.113519_bib0033","doi-asserted-by":"crossref","first-page":"3192","DOI":"10.1109\/TCSVT.2023.3312858","article-title":"Transformer-based multimodal emotional perception for dynamic facial expression recognition in the wild","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113519_bib0034","first-page":"159","article-title":"Facial action coding system","volume":"2","author":"Ekman","year":"1978","journal-title":"Environ. Psychol. Nonverbal Behav."},{"key":"10.1016\/j.patcog.2026.113519_bib0035","doi-asserted-by":"crossref","unstructured":"J. Wu, Y. Shen, L. Yan, H. Sun, D. Xia, J. Huang, M. Cao, Facial-R1: aligning reasoning and recognition for facial emotion analysis, (2025). arXiv: 2511.10254.","DOI":"10.1609\/aaai.v40i32.39906"},{"issue":"5","key":"10.1016\/j.patcog.2026.113519_bib0036","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1007\/s11263-017-1055-1","article-title":"From facial expression recognition to interpersonal relation prediction","volume":"126","author":"Zhang","year":"2018","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113519_bib0037","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2852","article-title":"Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2026.113519_bib0038","series-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-workshops","first-page":"94","article-title":"The Extended Cohn-Kanade Dataset (CK+): a complete dataset for action unit and emotion-specified expression","author":"Lucey","year":"2010"},{"key":"10.1016\/j.patcog.2026.113519_bib0039","series-title":"Psychology Section, Department of Clinical Neuroscience","article-title":"Karolinska directed emotional faces [database of standardized facial images]","author":"Lundqvist","year":"1998"},{"key":"10.1016\/j.patcog.2026.113519_bib0040","unstructured":"S. Vaidya, Natural human face images for emotion recognition, 2020."},{"issue":"3","key":"10.1016\/j.patcog.2026.113519_bib0041","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1002\/mpr.343","article-title":"The NIMH child emotional faces picture set (NIMH-ChEFS): a new set of children\u2019s facial emotion stimuli","volume":"20","author":"Egger","year":"2011","journal-title":"Int. J. Methods Psychiatr. Res."},{"key":"10.1016\/j.patcog.2026.113519_bib0042","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.3389\/fpsyg.2014.01516","article-title":"Warsaw set of emotional facial expression pictures: a validation study of facial display photographs","volume":"5","author":"Olszanowski","year":"2015","journal-title":"Front. Psychol."},{"key":"10.1016\/j.patcog.2026.113519_bib0043","series-title":"International Conference on Analysis of Images, Social Networks and Texts","first-page":"212","article-title":"MiVOLO : multi-input transformer for age and gender estimation","author":"Kuprashevich","year":"2023"},{"key":"10.1016\/j.patcog.2026.113519_bib0044","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"11369","article-title":"FaceXFormer: a unified transformer for facial analysis","author":"Narayan","year":"2025"},{"key":"10.1016\/j.patcog.2026.113519_bib0045","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.2026.113519_bib0046","unstructured":"W. Wang, Z. Gao, L. Gu, H. Pu, L. Cui, X. Wei, Z. Liu, L. Jing, S. Ye, J. Shao, et al., InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency, (2025). arXiv: 2508.18265."},{"key":"10.1016\/j.patcog.2026.113519_bib0047","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004851?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004851?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:03:28Z","timestamp":1780491808000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":47,"alternative-id":["S0031320326004851"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113519","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond action units: Towards multi-cue facial emotion analysis","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113519","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":"113519"}}