{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T18:21:15Z","timestamp":1772043675860,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2333211"],"award-info":[{"award-number":["U2333211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2024Z004"],"award-info":[{"award-number":["ZYGX2024Z004"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of Sichuan Engineering Technology Research Center for Civil Aviation Flight Technology and Flight Safety","award":["GY2024-27D"],"award-info":[{"award-number":["GY2024-27D"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754978","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"5567-5576","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Rethinking Occlusion in FER: A Semantic-Aware Perspective and Go Beyond"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7498-8505","authenticated-orcid":false,"given":"Huiyu","family":"Zhai","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7171-1617","authenticated-orcid":false,"given":"Xingxing","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5974-1717","authenticated-orcid":false,"given":"Yalan","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1212-4476","authenticated-orcid":false,"given":"Chenyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7283-0983","authenticated-orcid":false,"given":"Bin","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1911-2061","authenticated-orcid":false,"given":"Changze","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMS.2011.20"},{"key":"e_1_3_2_1_2_1","volume-title":"Co-dance with Ambiguity: An Ambiguity-Aware Facial Expression Recognition Framework for More Robustness","author":"Cao Xinran","year":"2025","unstructured":"Xinran Cao, Liang Luo, Yu Gu, and Fuji Ren. 2025. Co-dance with Ambiguity: An Ambiguity-Aware Facial Expression Recognition Framework for More Robustness. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"PyTorch Face Landmark: A fast and accurate facial landmark detector. Opensource software","author":"Chen Cunjian","year":"2021","unstructured":"Cunjian Chen. 2021. PyTorch Face Landmark: A fast and accurate facial landmark detector. Opensource software available at https:\/\/github. com\/cunjian\/pytorchf acelandmark (2021), 27."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 357-366","author":"Richard Chen Chun-Fu","year":"2021","unstructured":"Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda. 2021a. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE\/CVF international conference on computer vision. 357-366."},{"key":"e_1_3_2_1_5_1","volume-title":"Cross-domain facial expression recognition: A unified evaluation benchmark and adversarial graph learning","author":"Chen Tianshui","year":"2021","unstructured":"Tianshui Chen, Tao Pu, Hefeng Wu, Yuan Xie, Lingbo Liu, and Liang Lin. 2021b. Cross-domain facial expression recognition: A unified evaluation benchmark and adversarial graph learning. IEEE transactions on pattern analysis and machine intelligence, Vol. 44 (2021), 9887-9903."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06012-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_8_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106621"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Jiuxiang Gu Zhenhua Wang Jason Kuen Lianyang Ma Amir Shahroudy Bing Shuai Ting Liu Xingxing Wang Gang Wang Jianfei Cai et al. 2018. Recent advances in convolutional neural networks. Pattern recognition Vol. 77 (2018) 354-377.","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12268"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3172371"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01521-4"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612040"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747717"},{"key":"e_1_3_2_1_18_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_19_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/info15030135"},{"key":"e_1_3_2_1_21_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12700"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00148"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687508"},{"key":"e_1_3_2_1_25_1","volume-title":"Deep facial expression recognition: A survey","author":"Li Shan","year":"2020","unstructured":"Shan Li and Weihong Deng. 2020. Deep facial expression recognition: A survey. IEEE transactions on affective computing, Vol. 13 (2020), 1195-1215."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681631"},{"key":"e_1_3_2_1_28_1","volume-title":"FER-former: Multimodal Transformer for Facial Expression Recognition","author":"Li Yande","year":"2024","unstructured":"Yande Li, Mingjie Wang, Minglun Gong, Yonggang Lu, and Li Liu. 2024c. FER-former: Multimodal Transformer for Facial Expression Recognition. IEEE Transactions on Multimedia (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104190"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611702"},{"key":"e_1_3_2_1_32_1","volume-title":"MMATrans: Muscle movement aware representation learning for facial expression recognition via transformers","author":"Liu Hai","year":"2024","unstructured":"Hai Liu, Qiyun Zhou, Cheng Zhang, Junyan Zhu, Tingting Liu, Zhaoli Zhang, and You-Fu Li. 2024. MMATrans: Muscle movement aware representation learning for facial expression recognition via transformers. IEEE Transactions on Industrial Informatics (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"e_1_3_2_1_35_1","volume-title":"Poster: A simpler and stronger facial expression recognition network. Pattern Recognition","author":"Mao Jiawei","year":"2024","unstructured":"Jiawei Mao, Rui Xu, Xuesong Yin, Yuanqi Chang, Binling Nie, Aibin Huang, and Yigang Wang. 2024. Poster: A simpler and stronger facial expression recognition network. Pattern Recognition (2024), 110951."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"e_1_3_2_1_37_1","volume-title":"Segface: Face segmentation of long-tail classes. arXiv preprint arXiv:2412.08647","author":"Narayan Kartik","year":"2024","unstructured":"Kartik Narayan, Vibashan VS, and Vishal M Patel. 2024. Segface: Face segmentation of long-tail classes. arXiv preprint arXiv:2412.08647 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351049"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612186"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_2_1_41_1","volume-title":"Global filter networks for image classification. Advances in neural information processing systems","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, and Jie Zhou. 2021. Global filter networks for image classification. Advances in neural information processing systems, Vol. 34 (2021), 980-993."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2018.09.002"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00757"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-017-0935-z"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2023.01.017"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MAPR.2018.8337514"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SISY52375.2021.9582508"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611972"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113780"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_16"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010018"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang et al. 2020c. Deep high-resolution representation learning for visual recognition. IEEE transactions on pattern analysis and machine intelligence Vol. 43 (2020) 3349-3364.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"e_1_3_2_1_56_1","volume-title":"evolve: A high-performance face recognition library. arXiv preprint arXiv:2107.08621","author":"Wang Qingzhong","year":"2021","unstructured":"Qingzhong Wang, Pengfei Zhang, Haoyi Xiong, and Jian Zhao. 2021. Face. evolve: A high-performance face recognition library. arXiv preprint arXiv:2107.08621 (2021)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680875"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00707"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01183"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612008"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28478"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2013.0171"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00492"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01965"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681407"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25393-0_25"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612546"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:02:43Z","timestamp":1765339363000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754978"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":72,"alternative-id":["10.1145\/3746027.3754978","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754978","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}