{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:18:12Z","timestamp":1772554692454,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the PKU-NTU Joint Research Institute (JRI) sponsored by a donation from the Ng Teng Fong Charitable Foundation"},{"name":"the Fundamental Research Funds for the Central Universities"},{"name":"the National Key R&D Program of China","award":["2020AAA0103901"],"award-info":[{"award-number":["2020AAA0103901"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548116","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:12Z","timestamp":1665416592000},"page":"111-119","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Pursuing Knowledge Consistency: Supervised Hierarchical Contrastive Learning for Facial Action Unit Recognition"],"prefix":"10.1145","author":[{"given":"Yingjie","family":"Chen","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Chong","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Xiao","family":"Luo","sequence":"additional","affiliation":[{"name":"Peking Univerisity, Beijing, China"}]},{"given":"Jianqiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen , Simon Kornblith , Mohammad Norouzi , and Geoffrey Hinton . 2020 . A simple framework for contrastive learning of visual representations . In International conference on machine learning. PMLR, 1597--1607 . Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_2_1","volume-title":"Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition. arXiv preprint arXiv:2204.07935","author":"Chen Yingjie","year":"2022","unstructured":"Yingjie Chen , Diqi Chen , Tao Wang , Yizhou Wang , and Yun Liang . 2022. Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition. arXiv preprint arXiv:2204.07935 ( 2022 ). Yingjie Chen, Diqi Chen, Tao Wang, Yizhou Wang, and Yun Liang. 2022. Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition. arXiv preprint arXiv:2204.07935 (2022)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475295"},{"key":"e_1_3_2_2_4_1","volume-title":"GeoConv: geodesic guided convolution for facial action unit recognition. Pattern Recognition","author":"Chen Yuedong","year":"2021","unstructured":"Yuedong Chen , Guoxian Song , Zhiwen Shao , Jianfei Cai , Tat-Jen Cham , and Jianmin Zheng . 2021b. GeoConv: geodesic guided convolution for facial action unit recognition. Pattern Recognition ( 2021 ), 108355. Yuedong Chen, Guoxian Song, Zhiwen Shao, Jianfei Cai, Tat-Jen Cham, and Jianmin Zheng. 2021b. GeoConv: geodesic guided convolution for facial action unit recognition. Pattern Recognition (2021), 108355."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3098944"},{"key":"e_1_3_2_2_6_1","volume-title":"AUPro: Multi-label Facial Action Unit Proposal Generation for Sequence-Level Analysis. In International Conference on Neural Information Processing. Springer, 88--99","author":"Chen Yingjie","year":"2021","unstructured":"Yingjie Chen , Jiarui Zhang , Diqi Chen , Tao Wang , Yizhou Wang , and Yun Liang . 2021 d. AUPro: Multi-label Facial Action Unit Proposal Generation for Sequence-Level Analysis. In International Conference on Neural Information Processing. Springer, 88--99 . Yingjie Chen, Jiarui Zhang, Diqi Chen, Tao Wang, Yizhou Wang, and Yun Liang. 2021d. AUPro: Multi-label Facial Action Unit Proposal Generation for Sequence-Level Analysis. In International Conference on Neural Information Processing. Springer, 88--99."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"e_1_3_2_2_8_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Cui Zijun","year":"2020","unstructured":"Zijun Cui , Tengfei Song , Yuru Wang , and Qiang Ji . 2020 . Knowledge augmented deep neural networks for joint facial expression and action unit recognition . Advances in Neural Information Processing Systems , Vol. 33 (2020). Zijun Cui, Tengfei Song, Yuru Wang, and Qiang Ji. 2020. Knowledge augmented deep neural networks for joint facial expression and action unit recognition. Advances in Neural Information Processing Systems, Vol. 33 (2020)."},{"key":"e_1_3_2_2_9_1","volume-title":"An argument for basic emotions. Cognition & emotion","author":"Ekman Paul","year":"1992","unstructured":"Paul Ekman . 1992. An argument for basic emotions. Cognition & emotion , Vol. 6 , 3--4 ( 1992 ), 169--200. Paul Ekman. 1992. An argument for basic emotions. Cognition & emotion, Vol. 6, 3--4 (1992), 169--200."},{"key":"e_1_3_2_2_10_1","first-page":"5","article-title":"Facial action coding system: a technique for the measurement of facial movement","volume":"3","author":"Friesen E","year":"1978","unstructured":"E Friesen and Paul Ekman . 1978 . Facial action coding system: a technique for the measurement of facial movement . Palo Alto , Vol. 3 , 2 (1978), 5 . E Friesen and Paul Ekman. 1978. Facial action coding system: a technique for the measurement of facial movement. Palo Alto, Vol. 3, 2 (1978), 5.","journal-title":"Palo Alto"},{"key":"e_1_3_2_2_11_1","volume-title":"International Conference on Machine Learning. PMLR, 3821--3830","author":"Graf Florian","year":"2021","unstructured":"Florian Graf , Christoph Hofer , Marc Niethammer , and Roland Kwitt . 2021 . Dissecting supervised constrastive learning . In International Conference on Machine Learning. PMLR, 3821--3830 . Florian Graf, Christoph Hofer, Marc Niethammer, and Roland Kwitt. 2021. Dissecting supervised constrastive learning. In International Conference on Machine Learning. PMLR, 3821--3830."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00532"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7680--7689","author":"Jacob Geethu Miriam","year":"2021","unstructured":"Geethu Miriam Jacob and Bjorn Stenger . 2021 . Facial Action Unit Detection With Transformers . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7680--7689 . Geethu Miriam Jacob and Bjorn Stenger. 2021. Facial Action Unit Detection With Transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7680--7689."},{"key":"e_1_3_2_2_15_1","volume-title":"Supervised contrastive learning. arXiv preprint arXiv:2004.11362","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla , Piotr Teterwak , Chen Wang , Aaron Sarna , Yonglong Tian , Phillip Isola , Aaron Maschinot , Ce Liu , and Dilip Krishnan . 2020. Supervised contrastive learning. arXiv preprint arXiv:2004.11362 ( 2020 ). Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. arXiv preprint arXiv:2004.11362 (2020)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755843"},{"key":"e_1_3_2_2_17_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems , Vol. 25 ( 2012 ), 1097--1105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, Vol. 25 (2012), 1097--1105."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.716"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.136"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475686"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00398"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"e_1_3_2_2_25_1","volume-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV)","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari , Nassir Navab , and Seyed-Ahmad Ahmadi . 2016 . V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV) . IEEE , 565--571. Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). IEEE, 565--571."},{"key":"e_1_3_2_2_26_1","volume-title":"Multi-label co-regularization for semi-supervised facial action unit recognition. arXiv preprint arXiv:1910.11012","author":"Niu Xuesong","year":"2019","unstructured":"Xuesong Niu , Hu Han , Shiguang Shan , and Xilin Chen . 2019a. Multi-label co-regularization for semi-supervised facial action unit recognition. arXiv preprint arXiv:1910.11012 ( 2019 ). Xuesong Niu, Hu Han, Shiguang Shan, and Xilin Chen. 2019a. Multi-label co-regularization for semi-supervised facial action unit recognition. arXiv preprint arXiv:1910.11012 (2019)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01219"},{"key":"e_1_3_2_2_28_1","volume-title":"D-PAttNet: Dynamic patch-attentive deep network for action unit detection. Frontiers in computer science","author":"Ertugrul Itir Onal","year":"2019","unstructured":"Itir Onal Ertugrul , Le Yang , L\u00e1szl\u00f3 A Jeni , and Jeffrey F Cohn . 2019. D-PAttNet: Dynamic patch-attentive deep network for action unit detection. Frontiers in computer science , Vol. 1 ( 2019 ), 11. Itir Onal Ertugrul, Le Yang, L\u00e1szl\u00f3 A Jeni, and Jeffrey F Cohn. 2019. D-PAttNet: Dynamic patch-attentive deep network for action unit detection. Frontiers in computer science, Vol. 1 (2019), 11."},{"key":"e_1_3_2_2_29_1","volume-title":"NIPS Workshop.","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke , Sam Gross , Soumith Chintala , Gregory Chanan , Edward Yang , Zachary DeVito , Zeming Lin , Alban Desmaison , Luca Antiga , and Adam Lerer . 2017 . Automatic differentiation in PyTorch . In NIPS Workshop. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. In NIPS Workshop."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16748"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240613"},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the Asian Conference on Computer Vision.","author":"Yang Huiyuan","year":"2020","unstructured":"Huiyuan Yang and Lijun Yin . 2020 . RE-Net: A Relation Embedded Deep Model for AU Occurrence and Intensity Estimation . In Proceedings of the Asian Conference on Computer Vision. Huiyuan Yang and Lijun Yin. 2020. RE-Net: A Relation Embedded Deep Model for AU Occurrence and Intensity Estimation. In Proceedings of the Asian Conference on Computer Vision."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Ting Zhao and Xiangqian Wu. 2019. Pyramid feature attention network for saliency detection. In CVPR. 3085--3094.  Ting Zhao and Xiangqian Wu. 2019. Pyramid feature attention network for saliency detection. In CVPR. 3085--3094.","DOI":"10.1109\/CVPR.2019.00320"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548116","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:19Z","timestamp":1750186819000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":37,"alternative-id":["10.1145\/3503161.3548116","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548116","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}