{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:37:19Z","timestamp":1773157039192,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446825","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8145-8149","source":"Crossref","is-referenced-by-count":6,"title":["CLIP-MSA: Incorporating Inter-Modal Dynamics and Common Knowledge to Multimodal Sentiment Analysis With Clip"],"prefix":"10.1109","author":[{"given":"Qi","family":"Huang","sequence":"first","affiliation":[{"name":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingting","family":"Cai","sequence":"additional","affiliation":[{"name":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanyue","family":"Nie","sequence":"additional","affiliation":[{"name":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinshan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3038167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref8","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref9","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref10","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref18","article-title":"Learning factorized multimodal representations","author":"Tsai","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.209"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446825.pdf?arnumber=10446825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:23Z","timestamp":1722576383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446825","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}