{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T18:47:39Z","timestamp":1772563659630,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"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":[[2025,3,26]]},"DOI":"10.1109\/icit63637.2025.10965274","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T17:38:10Z","timestamp":1745343490000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Emotion Recognition Based on Multi-Scale Facial Features and Cross-Modal Attention"],"prefix":"10.1109","author":[{"given":"Chengao","family":"Bao","sequence":"first","affiliation":[{"name":"School of Automation, China University of Geosciences,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luefeng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, China University of Geosciences,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, China University of Geosciences,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation, China University of Geosciences,Wuhan,China,430074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Witold","family":"Pedrycz","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Canada,AB T6R 2G7"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaoru","family":"Hirota","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Yokohama,Japan,226-8502"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366127"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2625419"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02900-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165180"},{"key":"ref7","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst., USA"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"ref10","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale"},{"key":"ref11","first-page":"6824","article-title":"Multiscale vision transformers","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"H","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icdew.2006.145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119301"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178232"},{"key":"ref18","author":"Fu","year":"2021","journal-title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app11167217"}],"event":{"name":"2025 IEEE International Conference on Industrial Technology (ICIT)","location":"Wuhan, China","start":{"date-parts":[[2025,3,26]]},"end":{"date-parts":[[2025,3,28]]}},"container-title":["2025 IEEE International Conference on Industrial Technology (ICIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10965190\/10965119\/10965274.pdf?arnumber=10965274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T05:19:07Z","timestamp":1745385547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10965274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,26]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icit63637.2025.10965274","relation":{},"subject":[],"published":{"date-parts":[[2025,3,26]]}}}