{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:45:29Z","timestamp":1784454329733,"version":"3.55.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["62076262"],"award-info":[{"award-number":["62076262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/taffc.2025.3553149","type":"journal-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T15:19:18Z","timestamp":1742570358000},"page":"2074-2089","source":"Crossref","is-referenced-by-count":12,"title":["Injecting Multimodal Information Into Pre-Trained Language Model for Multimodal Sentiment Analysis"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-375X","authenticated-orcid":false,"given":"Sijie","family":"Mai","sequence":"first","affiliation":[{"name":"School of Computer Science, South China Normal University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8842-2045","authenticated-orcid":false,"given":"Ying","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2301-7897","authenticated-orcid":false,"given":"Aolin","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3155290"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1115"},{"key":"ref9","first-page":"12113","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213589"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"1","key":"ref14","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"ref20","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"},{"key":"ref21","first-page":"1","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3068598"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.135"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3423671"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.003"},{"issue":"2","key":"ref29","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"Weinberger","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612295"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref33","first-page":"17117","article-title":"Incomplete multimodality-diffused emotion recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3178231"},{"key":"ref36","first-page":"1","article-title":"Neuro-inspired information-theoretic hierarchical perception for multimodal learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xiao"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00062"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101958"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref40","first-page":"1","article-title":"Learning sparse neural networks through l_0 regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Louizos"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.109"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350987"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1152"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3306489"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.83"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101920"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref52","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref54","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref56","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651971"},{"issue":"8","key":"ref58","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref60","article-title":"LLaVAC: Fine-tuning LLaVA as a multimodal sentiment classifier","author":"Chay-intr","year":"2025"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548306"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612181"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref68","first-page":"18433","article-title":"CoMIR: Contrastive multimodal image representation for registration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pielawski"},{"key":"ref69","first-page":"9180","article-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Han"},{"key":"ref70","first-page":"527","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Poria"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref77","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref78","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3309"},{"key":"ref80","first-page":"1","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tsai"},{"key":"ref81","first-page":"1","article-title":"DeBERTa: Ddecoding-enhanced bert with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He"},{"issue":"11","key":"ref82","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171679"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref85","first-page":"2978","article-title":"Transformer-XL: Attentive language models beyond a fixed-length context","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Dai"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11152495\/10935629.pdf?arnumber=10935629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T05:59:39Z","timestamp":1757138379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10935629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":85,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3553149","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}