{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:15:29Z","timestamp":1775326529747,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209184","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["AU-TTT: Vision Test-Time Training model for Facial Action Unit Detection"],"prefix":"10.1109","author":[{"given":"Bohao","family":"Xing","sequence":"first","affiliation":[{"name":"Lappeenranta-Lahti University of Technology LUT,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaishen","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zitong","family":"Yu","sequence":"additional","affiliation":[{"name":"Great Bay University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Lappeenranta-Lahti University of Technology LUT,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heikki","family":"K\u00e4lvi\u00e4inen","sequence":"additional","affiliation":[{"name":"Lappeenranta-Lahti University of Technology LUT,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2731763"},{"key":"ref2","author":"Xing","year":"2024","journal-title":"Emo-llama: Enhancing facial emotion understanding with instruction tuning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3396656"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00063-w"},{"key":"ref5","author":"Li","year":"2024","journal-title":"Eald-mllm: Emotion analysis in long-sequential and de-identity videos with multi-modal large language model"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00759"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3460538"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3166133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00596"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_25"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00127"},{"key":"ref15","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01378-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00599"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01219"},{"key":"ref20","author":"Bresson","year":"2017","journal-title":"Residual gated graph convnets"},{"key":"ref21","author":"Sun","year":"2024","journal-title":"Learning to (learn at test time): Rnns with expressive hidden states"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756543"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2020.2977225"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756631"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667048"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACII55700.2022.9953868"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford"},{"key":"ref30","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.6.888"},{"key":"ref33","author":"Gammerman","year":"2013","journal-title":"Learning by transduction"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref35","first-page":"29374","article-title":"Test-time training with masked autoencoders","volume":"35","author":"Gandelsman","year":"2022","journal-title":"Advances in NeurIPS"},{"key":"ref36","author":"Meng","year":"2024","journal-title":"scfusionttt: Single-cell transcriptomics and proteomics fusion with test-time training layers"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01266"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01977"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00840"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01918"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209184.pdf?arnumber=11209184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:49Z","timestamp":1761888649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209184","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}