{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:58:36Z","timestamp":1778255916128,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755036","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"5587-5596","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0454-940X","authenticated-orcid":false,"given":"Feng-Qi","family":"Cui","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0960-1497","authenticated-orcid":false,"given":"Anyang","family":"Tong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5483-2812","authenticated-orcid":false,"given":"Jinyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4230-1077","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"IHPC and CFAR, A*STAR, singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0537-4522","authenticated-orcid":false,"given":"Zhi","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]}],"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\/CVPR.2017.502"},{"key":"e_1_3_2_1_2_1","volume-title":"CFAN-SDA: Coarse-Fine Aware Network With Static-Dynamic Adaptation for Facial Expression Recognition in Videos","author":"Chen Dongliang","year":"2024","unstructured":"Dongliang Chen, GuihuaWen, Pei Yang, Huihui Li, Chuyun Chen, and BaoWang. 2024. CFAN-SDA: Coarse-Fine Aware Network With Static-Dynamic Adaptation for Facial Expression Recognition in Videos. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680827"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2593719"},{"key":"e_1_3_2_1_5_1","volume-title":"Christopher Thomas Ryan, and Teng Zhang","author":"Chen Xi","year":"2021","unstructured":"Xi Chen, Simai He, Bo Jiang, Christopher Thomas Ryan, and Teng Zhang. 2021. The Discrete Moment Problem with Nonconvex Shape Constraints. (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3021755"},{"key":"e_1_3_2_1_7_1","volume-title":"Variance-based regularization with convex objectives. Journal of Machine Learning Research","author":"Duchi John","year":"2019","unstructured":"John Duchi and Hongseok Namkoong. 2019. Variance-based regularization with convex objectives. Journal of Machine Learning Research (2019)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_9_1","volume-title":"Sharpness-aware Minimization for Efficiently Improving Generalization. In International Conference on Learning Representations.","author":"Foret Pierre","year":"2021","unstructured":"Pierre Foret, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. 2021. Sharpness-aware Minimization for Efficiently Improving Generalization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3285777"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12235"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","volume-title":"Unified static and dynamic network: efficient temporal filtering for video grounding","author":"Hu Jingjing","year":"2025","unstructured":"Jingjing Hu, Dan Guo, Kun Li, Zhan Si, Xun Yang, Xiaojun Chang, and Meng Wang. 2025. Unified static and dynamic network: efficient temporal filtering for video grounding. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_15_1","volume-title":"Keystrokesniffer: An off-the-shelf smartphone can eavesdrop on your privacy from anywhere","author":"Huang Jinyang","year":"2024","unstructured":"Jinyang Huang, Jia-Xuan Bai, Xiang Zhang, Zhi Liu, Yuanhao Feng, Jianchun Liu, Xiao Sun, Mianxiong Dong, and Meng Li. 2024. Keystrokesniffer: An off-the-shelf smartphone can eavesdrop on your privacy from anywhere. IEEE Transactions on Information Forensics and Security (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Phyfinatt: An undetectable attack framework against phy layer fingerprint-based wifi authentication","author":"Huang Jinyang","year":"2023","unstructured":"Jinyang Huang, Bin Liu, Chenglin Miao, Xiang Zhang, Jiancun Liu, Lu Su, Zhi Liu, and Yu Gu. 2023. Phyfinatt: An undetectable attack framework against phy layer fingerprint-based wifi authentication. IEEE Transactions on Mobile Computing (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Coresets for wasserstein distributionally robust optimization problems. Advances in Neural Information Processing Systems","author":"Huang Ruomin","year":"2022","unstructured":"Ruomin Huang, Jiawei Huang, Wenjie Liu, and Hu Ding. 2022. Coresets for wasserstein distributionally robust optimization problems. Advances in Neural Information Processing Systems (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"e_1_3_2_1_19_1","volume-title":"Sampling-decomposable generative adversarial recommender. Advances in Neural Information Processing Systems","author":"Jin Binbin","year":"2020","unstructured":"Binbin Jin, Defu Lian, Zheng Liu, Qi Liu, Jianhui Ma, Xing Xie, and Enhong Chen. 2020. Sampling-decomposable generative adversarial recommender. Advances in Neural Information Processing Systems (2020)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2996086"},{"key":"e_1_3_2_1_21_1","unstructured":"Hanting Li Hongjing Niu Zhaoqing Zhu and Feng Zhao. 2023. Intensity-aware loss for dynamic facial expression recognition in the wild. AAAI."},{"key":"e_1_3_2_1_22_1","volume-title":"CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition. In 2024 IEEE International Conference on Multimedia and Expo (ICME).","author":"Li Hanting","year":"2024","unstructured":"Hanting Li, Hongjing Niu, Zhaoqing Zhu, and Feng Zhao. 2024. CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition. In 2024 IEEE International Conference on Multimedia and Expo (ICME)."},{"key":"e_1_3_2_1_23_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Li Mengke","year":"2024","unstructured":"Mengke Li, Ye Liu, Yang Lu, Yiqun Zhang, Yiu ming Cheung, and Hui Huang. 2024. Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_24_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 (2020)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2025.3546279"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611702"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681583"},{"key":"e_1_3_2_1_28_1","unstructured":"Fuyan Ma Bin Sun and Shutao Li. 2022. Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild. (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"e_1_3_2_1_30_1","volume-title":"Logo-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ma Fuyan","year":"2023","unstructured":"Fuyan Ma, Bin Sun, and Shutao Li. 2023. Logo-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Distributionally Robust Models with Parametric Likelihood Ratios. In International Conference on Learning Representations.","author":"Michel Paul","year":"2022","unstructured":"Paul Michel, Tatsunori Hashimoto, and Graham Neubig. 2022. Distributionally Robust Models with Parametric Likelihood Ratios. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_32_1","volume-title":"FcaNet: Frequency Channel Attention Networks. In IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Qin Zequn","year":"2021","unstructured":"Zequn Qin, Pengyi Zhang, Fei Wu, and Xi Li. 2021. FcaNet: Frequency Channel Attention Networks. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_33_1","volume-title":"Certifiable Distributional Robustness with Principled Adversarial Training. In International Conference on Learning Representations.","author":"Sinha Aman","year":"2018","unstructured":"Aman Sinha, Hongseok Namkoong, and John Duchi. 2018. Certifiable Distributional Robustness with Principled Adversarial Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_35_1","volume-title":"Joolekha Bibi Joolee, and Young-Koo Lee","author":"Uddin Md Azher","year":"2022","unstructured":"Md Azher Uddin, Joolekha Bibi Joolee, and Young-Koo Lee. 2022. Depression Level Prediction Using Deep Spatiotemporal Features and Multilayer Bi-LTSM. IEEE Transactions on Affective Computing (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Visualizing Data using t-SNE. Journal of Machine Learning Research","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research (2008)."},{"key":"e_1_3_2_1_37_1","volume-title":"Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wang Hanyang","year":"2023","unstructured":"Hanyang Wang, Bo Li, Shuang Wu, Siyuan Shen, Feng Liu, Shouhong Ding, and Aimin Zhou. 2023. Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681546"},{"key":"e_1_3_2_1_39_1","volume-title":"Dynamic Facial Expression Recognition Based on Vision Transformer with Deformable Module. In 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC).","author":"Wang Rui","year":"2023","unstructured":"Rui Wang and Xiao Sun. 2023. Dynamic Facial Expression Recognition Based on Vision Transformer with Deformable Module. In 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Multimodal Interaction.","author":"Wang Yanan","year":"2019","unstructured":"Yanan Wang, Jianming Wu, and Keiichiro Hoashi. 2019. Multi-attention fusion network for video-based emotion recognition. In International Conference on Multimodal Interaction."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274759"},{"key":"e_1_3_2_1_43_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Wu Junkang","year":"2023","unstructured":"Junkang Wu, Jiawei Chen, Jiancan Wu, Wentao Shi, Xiang Wang, and Xiangnan He. 2023. Understanding Contrastive Learning via Distributionally Robust Optimization. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612342"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2788081"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407693"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.013"}],"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\/3746027.3755036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:16:51Z","timestamp":1765307811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755036"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755036","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755036","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"}}]}}