{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:12:52Z","timestamp":1775578372027,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB2808802"],"award-info":[{"award-number":["2024YFB2808802"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3578618","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:39:38Z","timestamp":1750253978000},"page":"17941-17952","source":"Crossref","is-referenced-by-count":4,"title":["DashFusion: Dual-Stream Alignment With Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7059-9196","authenticated-orcid":false,"given":"Yuhua","family":"Wen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5016-0094","authenticated-orcid":false,"given":"Qifei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingying","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5881-3723","authenticated-orcid":false,"given":"Yingming","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6284-5039","authenticated-orcid":false,"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3294810"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2867174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-023-04567-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213020400047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2444846"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-020-00811-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3656580"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3420239"},{"key":"ref11","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref12","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1462"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548137"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611974"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110819"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3265653"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref24","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366349"},{"key":"ref26","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Nagrani"},{"key":"ref27","first-page":"16049","article-title":"How does information bottleneck help deep learning?","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Kawaguchi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref37","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","volume":"33","author":"Khosla"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref39","first-page":"38032","article-title":"Long-form video-language pre-training with multimodal temporal contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Sun"},{"key":"ref40","first-page":"9564","article-title":"Multimodal contrastive learning with LIMoE: The language-image mixture of experts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Mustafa"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3423671"},{"key":"ref45","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref46","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282953"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref51","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"ref60","article-title":"MERBench: A unified evaluation benchmark for multimodal emotion recognition","author":"Lian","year":"2024","journal-title":"arXiv:2401.03429"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11040049.pdf?arnumber=11040049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:34Z","timestamp":1765219294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11040049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":60,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3578618","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}