{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:55:47Z","timestamp":1775325347568,"version":"3.50.1"},"reference-count":83,"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":["U24A20335"],"award-info":[{"award-number":["U24A20335"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3590929","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T18:06:10Z","timestamp":1753207570000},"page":"6766-6779","source":"Crossref","is-referenced-by-count":3,"title":["ROSA: A Robust Self-Adaptive Model for Multimodal Emotion Recognition With Uncertain Missing Modalities"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6709-5238","authenticated-orcid":false,"given":"Ziming","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4111-5798","authenticated-orcid":false,"given":"Yaxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Chuanpeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9468-3257","authenticated-orcid":false,"given":"Yan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7170-3809","authenticated-orcid":false,"given":"Songlin","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"ref3","first-page":"17117","article-title":"Incomplete multimodality-diffused emotion recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3267882"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29474"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref13","first-page":"7136","article-title":"AMOA: Global acoustic feature enhanced modal-order-aware network for multimodal sentiment analysis","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Li","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.772"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144885"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.417"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238314"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554813"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3316458"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3303711"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3635311"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.291"},{"key":"ref34","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16165"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101973"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3378570"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.528"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3640343"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338769"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.900"},{"key":"ref46","article-title":"ITEACH-net: Inverted teacher-student search network for emotion recognition in conversation","author":"Sun","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28871"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101869"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref54","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1017\/S1471068419000371"},{"key":"ref56","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref58","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref59","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref60","article-title":"ChatGPT: The GPT-4 model","year":"2023"},{"key":"ref61","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":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref63","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref64","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref65","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref66","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref68","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref69","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref70","article-title":"Videochat: Chat-centric video understanding","author":"Li","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref73","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref75","article-title":"MiniGPT4-video: Advancing multimodal LLMs for video understanding with interleaved visual-textual tokens","author":"Ataallah","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref79","article-title":"AffectGPT: Dataset and framework for explainable multimodal emotion recognition","author":"Lian","year":"2024"},{"key":"ref80","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref82","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew","year":"2013"},{"key":"ref83","first-page":"1083","article-title":"On deep multi-view representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2015"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11086418.pdf?arnumber=11086418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:29:18Z","timestamp":1759238958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11086418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3590929","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}