{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T17:14:46Z","timestamp":1782321286646,"version":"3.54.5"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018696","name":"Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,26]]},"DOI":"10.1109\/fg61629.2025.11099277","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:55:00Z","timestamp":1754502900000},"page":"1-11","source":"Crossref","is-referenced-by-count":13,"title":["OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis"],"prefix":"10.1109","author":[{"given":"Jiewen","family":"Hu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leena","family":"Mathur","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFSP59764.2023.10372944"},{"key":"ref2","article-title":"Openface: A general-purpose face recognition library with mobile applications","volume-title":"Technical report, CMU-CS-16-118","author":"Amos","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284869"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.54"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2930192"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/fg57933.2023.10042673"},{"key":"ref9","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv preprint arXiv:2108.07258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.10.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956687"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s42761-023-00191-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02866-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"issue":"1","key":"ref19","first-page":"2019","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","journal-title":"NAACL-HLT"},{"key":"ref20","article-title":"An image is worth 16 times 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0149-7634(00)00025-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/263593"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_21"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2009.0142"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3332569"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284873"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000909"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3138\/9781845537258"},{"key":"ref30","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304592"},{"key":"ref32","volume-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2735633"},{"key":"ref34","article-title":"Fiducial focus augmentation for facial landmark detection","author":"Kar","year":"2024","journal-title":"arXiv preprint arXiv:2402.15044"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00701"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.239"},{"key":"ref38","article-title":"Hih: Towards more accurate face alignment via heatmap in heatmap","author":"Lan","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481287"},{"key":"ref40","volume-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref41","volume-title":"High-modality multimodal transformer: Quantifying modality & interaction heterogeneity for highmodality representation learning","author":"Liang","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_17"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051403"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.233"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3478078"},{"key":"ref46","first-page":"13","article-title":"Vilbert: Pretraining taskagnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1143"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref51","article-title":"Facexformer: A unified transformer for facial analysis","author":"Narayan","year":"2024","journal-title":"arXiv preprint arXiv:2403.12960"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301687"},{"key":"ref53","article-title":"Shape preserving facial landmarks with graph attention networks","author":"Prados-Torreblanca","year":"2022","journal-title":"arXiv preprint arXiv:2210.07233"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304724"},{"key":"ref55","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"issue":"1","key":"ref56","first-page":"31","article-title":"Ensemble learning for facial expression recognition","volume":"2","author":"Raghav","year":"2021","journal-title":"Full Length Article"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2530043"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3188390"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531741"},{"key":"ref62","article-title":"Vl-bert: Pretraining of generic visual-linguistic representations","author":"Su","journal-title":"I C L R, 2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ACV.2002.1182180"},{"key":"ref64","article-title":"Efficientnet","author":"Tan","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59990-4_32"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00127"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00227"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2787130"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1097-z"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00402"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3024201"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.253"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_25"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284871"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12173595"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299081"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.284"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-019-01707-5"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.112"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01485"},{"key":"ref87","article-title":"Crosstask multi-branch vision transformer for facial expression and mask wearing classification","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv:2404.14606"}],"event":{"name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Tampa\/Clearwater, FL, USA","start":{"date-parts":[[2025,5,26]]},"end":{"date-parts":[[2025,5,30]]}},"container-title":["2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099084\/11099070\/11099277.pdf?arnumber=11099277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:02:53Z","timestamp":1754542973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/fg61629.2025.11099277","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}