{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:06Z","timestamp":1761898026006,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688078","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Dual-View Multimodal Interaction in Multimodal Sentiment Analysis"],"prefix":"10.1109","author":[{"given":"Kang","family":"Zhu","sequence":"first","affiliation":[{"name":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunhang","family":"Fan","sequence":"additional","affiliation":[{"name":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xue","sequence":"additional","affiliation":[{"name":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Xie","sequence":"additional","affiliation":[{"name":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwei","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Lv","sequence":"additional","affiliation":[{"name":"Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55394-8_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3097002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859747"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859836"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859902"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref10"},{"key":"ref11","first-page":"32 897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","author":"Kenton"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101958"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178204"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref18","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"article-title":"Coca: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00237"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282410"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref26","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688078.pdf?arnumber=10688078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:39:44Z","timestamp":1727764784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688078","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}