{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:40:32Z","timestamp":1781502032731,"version":"3.54.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"name":"National Social Science Fund of China","award":["19BYY076"],"award-info":[{"award-number":["19BYY076"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/taffc.2024.3430045","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T17:22:16Z","timestamp":1721236936000},"page":"250-263","source":"Crossref","is-referenced-by-count":22,"title":["Diversity and Balance: Multimodal Sentiment Analysis Using Multimodal-Prefixed and Cross-Modal Attention"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3407-6092","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7217-3109","authenticated-orcid":false,"given":"Zhenfang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8278-6454","authenticated-orcid":false,"given":"Kefeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9126-3799","authenticated-orcid":false,"given":"Hongli","family":"Pei","sequence":"additional","affiliation":[{"name":"School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3586075"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2575738"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103223"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref6","first-page":"6416","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Representation Learn.","author":"Tsai"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.175"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5202"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17534"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3183830"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109259"},{"key":"ref26","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref27","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref28","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref31","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arxiv 2020","author":"Dosovitskiy","year":"2010"},{"key":"ref32","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref34","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref38","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref41","first-page":"12113","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref45","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref46","article-title":"TEASEL: A transformer-based speech-prefixed language model.(2021)","author":"Arjmand","year":"2021"},{"key":"ref47","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref48","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.438"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.417"},{"key":"ref52","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref53","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref55","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"issue":"140","key":"ref60","first-page":"1","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":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.567"},{"issue":"2605","key":"ref62","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Laurens","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/10908445\/10601307.pdf?arnumber=10601307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:34:43Z","timestamp":1741026883000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10601307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3430045","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}