{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:59:43Z","timestamp":1772553583524,"version":"3.50.1"},"reference-count":29,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"publisher","award":["82071171"],"award-info":[{"award-number":["82071171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["L192026"],"award-info":[{"award-number":["L192026"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859836","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":28,"title":["NHFNET: A Non-Homogeneous Fusion Network for Multimodal Sentiment Analysis"],"prefix":"10.1109","author":[{"given":"Ziwang","family":"Fu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayin","family":"Qi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangling","family":"Fu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aimin","family":"Zhou","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2359","article-title":"Integrating multimodal information in large pre-trained transformers","volume":"2020","author":"rahman","year":"0","journal-title":"ACL"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"ref16","article-title":"Attention bottlenecks for multimodal fusion","volume":"34","author":"nagrani","year":"0","journal-title":"NeurIPS"},{"key":"ref17","first-page":"2236","article-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"zadeh","year":"0","journal-title":"ACL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref3","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.06.005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref7","first-page":"2554","article-title":"Progressive modality reinforcement for human multimodal emotion recognition from unaligned multi-modal sequences","author":"lv","year":"0","journal-title":"CVPR"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"10790","DOI":"10.1609\/aaai.v35i12.17289","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume":"35","author":"yu","year":"0","journal-title":"AAAI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3038167"},{"key":"ref20","article-title":"Learning factorized multimodal representations","author":"tsai","year":"0","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479931"},{"key":"ref24","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"ming-wei","year":"0","journal-title":"NAACL"},{"key":"ref26","first-page":"1","article-title":"Openface: an open source facial behavior analysis toolkit","author":"baltru?aitis","year":"2016","journal-title":"WACV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"}],"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\/09859836.pdf?arnumber=9859836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T17:38:22Z","timestamp":1727890702000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859836","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}