{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T20:18:55Z","timestamp":1783369135082,"version":"3.54.6"},"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573163"],"award-info":[{"award-number":["62573163"]}],"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":["62503139"],"award-info":[{"award-number":["62503139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515012028"],"award-info":[{"award-number":["2024A1515012028"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["GXWD20231129125006001"],"award-info":[{"award-number":["GXWD20231129125006001"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20250604145514019"],"award-info":[{"award-number":["JCYJ20250604145514019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668469","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"5288-5302","source":"Crossref","is-referenced-by-count":0,"title":["Context Modeling With Multimodal Prompts for Emotion Recognition in Conversation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0881-006X","authenticated-orcid":false,"given":"Qian","family":"Dong","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3839-0078","authenticated-orcid":false,"given":"Weihong","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5875-7626","authenticated-orcid":false,"given":"Yu","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2880-4698","authenticated-orcid":false,"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-020821-010855"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.70675\/0f15a36fzecf8z4cffz94e7z120e7d8fd39d"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3359436"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1280"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.370"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.229"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117062"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3118881"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354351"},{"key":"ref14","first-page":"105","article-title":"Acoustic concomitants of emotional dimensions: Judging affect from synthesized tone sequences","author":"Scherer","year":"1974","journal-title":"Nonverbal Commun. Readings Commentary"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.347"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611805"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260635"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102306"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126427"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01821"},{"key":"ref25","first-page":"397","article-title":"Higru: Hierarchical gated recurrent units for utterance-level emotion recognition","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol.","author":"Jiao","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6309"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.408"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3303"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref45","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2021"},{"key":"ref46","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096029"},{"key":"ref51","first-page":"1","article-title":"Weakly-supervised HOI detection via prior-guided bi-level representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wan","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/math11132908"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/fi16070247"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"ref60","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107751"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21348"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273577"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01421"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref71","article-title":"Qwen2-VL: Enhancing vision-language models perception of the world at any resolution","author":"Wang","year":"2024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11415712.pdf?arnumber=11415712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T19:47:36Z","timestamp":1783367256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11415712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668469","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}