{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T19:59:38Z","timestamp":1790366378631,"version":"4.1.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC3303802"],"award-info":[{"award-number":["2023YFC3303802"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3673543","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:04Z","timestamp":1773347884000},"page":"7635-7646","source":"Crossref","is-referenced-by-count":0,"title":["Reinforced Context Augmentation for Multimodal Emotion Analysis"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1177-6203","authenticated-orcid":false,"given":"Ruyi","family":"Gan","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6841-2341","authenticated-orcid":false,"given":"Yuanhe","family":"Tian","sequence":"additional","affiliation":[{"name":"Zhongguancun Institute of Artificial Intelligence","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7640-4138","authenticated-orcid":false,"given":"Kunhao","family":"Pan","sequence":"additional","affiliation":[{"name":"International Digital Economics Academy","place":["Shenzhen, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2849-2962","authenticated-orcid":false,"given":"Yan","family":"Song","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.11.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.07.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08836-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/mti6040028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2022.3192533"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icip42928.2021.9506714"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484456"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214989"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CIC58953.2023.00027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073267"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4593-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612864"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"ref17","article-title":"AffectGPT: Dataset and framework for explainable multimodal emotion recognition","author":"Lian","year":"2024"},{"key":"ref18","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref25","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref28","article-title":"Qwen2.5-Vl technical report","author":"Bai","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0944"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref31","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli","year":"2021"},{"key":"ref32","article-title":"Generative pretraining in multimodality","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1782"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref35","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref38","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2798287"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2946477"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3211197"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260635"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338769"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3344358"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007352"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217414"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00043"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2018.8621129"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1190"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging7080157"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979932"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126427"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681403"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103724"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.63317\/2f3apkqkqukh"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.522"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref62","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.108"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref67","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref68","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref69","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129376"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3593583"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11433050.pdf?arnumber=11433050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T19:05:56Z","timestamp":1790363156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3673543","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}