{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:02:30Z","timestamp":1775743350520,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095448","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":28,"title":["Logo-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition"],"prefix":"10.1109","author":[{"given":"Fuyan","family":"Ma","sequence":"first","affiliation":[{"name":"Hunan University,College of Electrical and Information Engineering,Changsha,China"}]},{"given":"Bin","family":"Sun","sequence":"additional","affiliation":[{"name":"Hunan University,College of Electrical and Information Engineering,Changsha,China"}]},{"given":"Shutao","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University,College of Electrical and Information Engineering,Changsha,China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"19594","article-title":"Space-time mixing attention for video transformer","volume":"34","author":"bulat","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"4","article-title":"Is space-time attention all you need for video understanding","volume":"2","author":"bertasius","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref11","article-title":"Spatio-temporal transformer for dynamic facial expression recognition in the wild","author":"ma","year":"2022"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref2","article-title":"Facial expression recognition with visual transformers and attentional selective fusion","author":"ma","year":"2021","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"ref24","first-page":"87","article-title":"Ms-celeb-1m: A dataset and benchmark for large-scale face recognition","author":"guo","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref23","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"foret","year":"2020"},{"key":"ref25","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"ref22","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01334"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.12.016"},{"key":"ref3","article-title":"Deep facial expression recognition: A survey","author":"li","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.patcog.2018.07.016","article-title":"Conditional convolution neural network enhanced random forest for facial expression recognition","volume":"84","author":"liu","year":"2018","journal-title":"Pattern Recognition"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00231"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095448.pdf?arnumber=10095448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:55:49Z","timestamp":1699883749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095448","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}