{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:15:11Z","timestamp":1725808511962},"reference-count":24,"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\/icme52920.2022.9859834","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":2,"title":["HGLNET: A Generic Hierarchical Global-Local Feature Fusion Network for Multi-Modal Classification"],"prefix":"10.1109","author":[{"given":"Jiesheng","family":"Wu","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Nankai University,Tianjin,China,300350"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junan","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University,Tianjin,China,300350"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University,Tianjin,China,300350"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301305"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102437"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.226"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137600"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617078"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5393"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210093"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Image-text multimodal emotion classification via multi-view attentional network","author":"yang","year":"2020","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462871"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_55"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01469"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref1","article-title":"Efficient large-scale multi-modal classification","author":"kiela","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3003648"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","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\/09859834.pdf?arnumber=9859834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:33Z","timestamp":1663619073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859834","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}