{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:33:27Z","timestamp":1782574407622,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Research Projects of Zhejiang Lab","award":["NO. 2021KH0AB06"],"award-info":[{"award-number":["NO. 2021KH0AB06"]}]},{"name":"Beijing Municipal Science&Technology Commission,Administrative Commission of Zhongguancun Science Park","award":["No.Z211100004821013"],"award-info":[{"award-number":["No.Z211100004821013"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["No.61831022, No.62276259, No.62201572, No.U21B2010"],"award-info":[{"award-number":["No.61831022, No.62276259, No.62201572, No.U21B2010"]}]},{"name":"CCF- Baidu Open Fund","award":["No.OF2022025"],"award-info":[{"award-number":["No.OF2022025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612365","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"6110-6121","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":77,"title":["MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1529-1552","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, Vol. 33 (2020), 12449--12460."},{"key":"e_1_3_2_1_2_1","volume-title":"BEiT: BERT Pre-Training of Image Transformers. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=p-BhZSz59o4","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2022. BEiT: BERT Pre-Training of Image Transformers. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=p-BhZSz59o4"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3141400"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2014.051215"},{"key":"e_1_3_2_1_5_1","volume-title":"Crema-d: Crowd-sourced emotional multimodal actors dataset","author":"Cao Houwei","year":"2014","unstructured":"Houwei Cao, David G Cooper, Michael K Keutmann, Ruben C Gur, Ani Nenkova, and Ragini Verma. 2014. Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE transactions on affective computing, Vol. 5, 4 (2014), 377--390."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 1691--1703","author":"Chen Mark","year":"2020","unstructured":"Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative pretraining from pixels. In International conference on machine learning. PMLR, 1691--1703."},{"key":"e_1_3_2_1_8_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_1_9_1","first-page":"1086","article-title":"VoxCeleb2","volume":"2018","author":"Chung Joon Son","year":"2018","unstructured":"Joon Son Chung, Arsha Nagrani, and Andrew Zisserman. 2018. VoxCeleb2: Deep Speaker Recognition. Proc. Interspeech 2018 (2018), 1086--1090.","journal-title":"Deep Speaker Recognition. Proc. Interspeech"},{"key":"e_1_3_2_1_10_1","volume-title":"The expression of the emotions in man and animals","author":"Darwin Charles","unstructured":"Charles Darwin and Phillip Prodger. 1998. The expression of the emotions in man and animals. Oxford University Press, USA."},{"key":"e_1_3_2_1_11_1","volume-title":"Social Functions of Machine Emotional Expressions. Proc","author":"de Melo Celso M","year":"2023","unstructured":"Celso M de Melo, Jonathan Gratch, Stacy Marsella, and Catherine Pelachaud. 2023. Social Functions of Machine Emotional Expressions. Proc. IEEE (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_13_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 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_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"e_1_3_2_1_17_1","volume-title":"Masked Autoencoders As Spatiotemporal Learners. arXiv preprint arXiv:2205.09113","author":"Feichtenhofer Christoph","year":"2022","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Yanghao Li, and Kaiming He. 2022. Masked Autoencoders As Spatiotemporal Learners. arXiv preprint arXiv:2205.09113 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition. arXiv preprint arXiv:2111.02172","author":"Fu Ziwang","year":"2021","unstructured":"Ziwang Fu, Feng Liu, Hanyang Wang, Jiayin Qi, Xiangling Fu, Aimin Zhou, and Zhibin Li. 2021. A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition. arXiv preprint arXiv:2111.02172 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216993"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_24_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3014171"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00610"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3234777"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25077"},{"key":"e_1_3_2_1_30_1","unstructured":"Hanting Li Mingzhe Sui Zhaoqing Zhu et al. 2022. NR-DFERNet: Noise-Robust Network for Dynamic Facial Expression Recognition. arXiv preprint arXiv:2206.04975 (2022)."},{"key":"e_1_3_2_1_31_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, 3 (2020), 1195--1215."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.03.062"},{"key":"e_1_3_2_1_34_1","volume-title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition. arXiv preprint arXiv:2109.08409","author":"Liu Yuanyuan","year":"2021","unstructured":"Yuanyuan Liu, Wenbin Wang, Chuanxu Feng, Haoyu Zhang, Zhe Chen, and Yibing Zhan. 2021. Expression Snippet Transformer for Robust Video-based Facial Expression Recognition. arXiv preprint arXiv:2109.08409 (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109368"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"e_1_3_2_1_37_1","volume-title":"Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild. arXiv preprint arXiv:2205.04749","author":"Ma Fuyan","year":"2022","unstructured":"Fuyan Ma, Bin Sun, and Shutao Li. 2022. Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild. arXiv preprint arXiv:2205.04749 (2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"e_1_3_2_1_40_1","volume-title":"Facial-expression recognition from video using enhanced convolutional lstm. In 2019 Digital Image Computing: Techniques and Applications (DICTA)","author":"Miyoshi Ryo","unstructured":"Ryo Miyoshi, Noriko Nagata, and Manabu Hashimoto. 2019. Facial-expression recognition from video using enhanced convolutional lstm. In 2019 Digital Image Computing: Techniques and Applications (DICTA). IEEE, 1--6."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05557-4"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11010052"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2907271"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.895976"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/265013"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"e_1_3_2_1_47_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_48_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_49_1","volume-title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training. arXiv preprint arXiv:2210.05234","author":"Song Yuxin","year":"2022","unstructured":"Yuxin Song, Min Yang, Wenhao Wu, Dongliang He, Fu Li, and Jingdong Wang. 2022. It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training. arXiv preprint arXiv:2210.05234 (2022)."},{"key":"e_1_3_2_1_50_1","volume-title":"Msaf: Multimodal split attention fusion. arXiv preprint arXiv:2012.07175","author":"Su Lang","year":"2020","unstructured":"Lang Su, Chuqing Hu, Guofa Li, and Dongpu Cao. 2020. Msaf: Multimodal split attention fusion. arXiv preprint arXiv:2012.07175 (2020)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_125"},{"key":"e_1_3_2_1_54_1","unstructured":"Zhan Tong Yibing Song Jue Wang and Limin Wang. 2022. VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747278"},{"key":"e_1_3_2_1_58_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_59_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554810"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547865"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2316163"},{"key":"e_1_3_2_1_67_1","volume-title":"Kang Zhang, and In So Kweon.","author":"Zhang Chaoning","year":"2022","unstructured":"Chaoning Zhang, Chenshuang Zhang, Junha Song, John Seon Keun Yi, Kang Zhang, and In So Kweon. 2022. A survey on masked autoencoder for self-supervised learning in vision and beyond. arXiv preprint arXiv:2208.00173 (2022)."},{"key":"e_1_3_2_1_68_1","volume-title":"Daniel PK Lun, and Kin-Man Lam","author":"Zhao Rui","year":"2022","unstructured":"Rui Zhao, Tianshan Liu, Zixun Huang, Daniel PK Lun, and Kin-Man Lam. 2022. Spatial-Temporal Graphs Plus Transformers for Geometry-Guided Facial Expression Recognition. IEEE Transactions on Affective Computing (2022)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612365","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:56Z","timestamp":1755820976000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":69,"alternative-id":["10.1145\/3581783.3612365","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612365","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}