{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:19:54Z","timestamp":1780636794415,"version":"3.54.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859747","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["HMAI-BERT: Hierarchical Multimodal Alignment and Interaction Network-Enhanced BERT for Multimodal Sentiment Analysis"],"prefix":"10.1109","author":[{"given":"Xianbing","family":"Zhao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiting","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicen","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Buzhou","family":"Tang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Cobra: Contrastive bi-modal representation algorithm","author":"udandarao","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref19","article-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"zadeh","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.4"},{"key":"ref5","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.29007\/9qvn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859747.pdf?arnumber=9859747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:25:01Z","timestamp":1663619101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859747","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}