{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:10:24Z","timestamp":1780776624456,"version":"3.54.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236006"],"award-info":[{"award-number":["62236006"]}],"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":["62320106007"],"award-info":[{"award-number":["62320106007"]}],"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":["62032022"],"award-info":[{"award-number":["62032022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation","award":["4222040"],"award-info":[{"award-number":["4222040"]}]},{"name":"Scientific Research Program of the Beijing Municipal Education Commission","award":["KZ201911417048"],"award-info":[{"award-number":["KZ201911417048"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557704","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"3069-3081","source":"Crossref","is-referenced-by-count":18,"title":["ExpLLM: Towards Chain of Thought for Facial Expression Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3624-5926","authenticated-orcid":false,"given":"Xing","family":"Lan","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-802X","authenticated-orcid":false,"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Qi","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-997-0_19"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/\/0003-066X.48.4.384"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref4","article-title":"Face expression recognition and analysis: The state of the art","author":"Bettadapura","year":"2012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.102740"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIKE47802.2019.9004275"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5014\/ajot.2020.043463"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-019-01707-5"},{"key":"ref10","article-title":"Exploring the reasoning abilities of multimodal large language models (MLLMs): A comprehensive survey on emerging trends in multimodal reasoning","author":"Wang","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00065"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01456"},{"key":"ref13","article-title":"Hello GPT-4O","year":"2013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.414"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3131222"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3164798"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00177"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00148"},{"key":"ref26","first-page":"14414","article-title":"Leave no stone unturned: Mine extra knowledge for imbalanced facial expression recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687508"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01897"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.136"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2019.00011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00596"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00599"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3257542"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.0-104"},{"key":"ref42","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref43","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Li","year":"2023"},{"key":"ref44","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2022"},{"key":"ref45","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref46","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref47","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"key":"ref48","article-title":"mPLUG-OwL: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref49","article-title":"VLLMs provide better context for emotion understanding through common sense reasoning","author":"Xenos","year":"2024"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-industry.98","article-title":"Anymal: An efficient and scalable any-modality augmented language model","volume-title":"\"Proc. 2024 Conf. Emp. Methods Natural Lang. Process.: Industry Track","author":"Moon","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01313"},{"key":"ref52","first-page":"70757","article-title":"Towards revealing the mystery behind chain of thought: A theoretical perspective","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Feng","year":"2024"},{"key":"ref53","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref54","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"ref56","first-page":"25081","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mu","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1117\/12.2643588"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref61","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref63","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Proc. Trans. Mach. Learn. Res.","author":"Oquab","year":"2024"},{"key":"ref64","article-title":"VICUNA: An open-source chatbot impressing GPT-4 with 90 chatGPT quality","author":"Chiang","year":"2023"},{"key":"ref65","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00203"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3144439"},{"key":"ref70","article-title":"An image is worth 1616 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref71","article-title":"Sample and computation redistribution for efficient face detection","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Guo","year":"2022"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00937"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8020199"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097033"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00089"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref80","article-title":"EMO-LLaMA: Enhancing facial emotion understanding with instruction tuning","author":"Xing","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948346.pdf?arnumber=10948346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:50Z","timestamp":1748539850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557704","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}