{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:57:42Z","timestamp":1781585862639,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":34,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]},{"name":"Shanghai Sailing Program","award":["22YF1420300"],"award-info":[{"award-number":["22YF1420300"]}]},{"name":"Beijing Natural Science Foundation","award":["L222117"],"award-info":[{"award-number":["L222117"]}]},{"name":"CCF-Tencent Open Research Fund","award":["RAGR20220121"],"award-info":[{"award-number":["RAGR20220121"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["YG2023QNB17"],"award-info":[{"award-number":["YG2023QNB17"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272447, 72192821"],"award-info":[{"award-number":["62272447, 72192821"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611999","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"5048-5058","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Toward High Quality Facial Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9494-9836","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1887-6406","authenticated-orcid":false,"given":"Jinlong","family":"Peng","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7910-810X","authenticated-orcid":false,"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6592-8411","authenticated-orcid":false,"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent & Zhejiang University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-8090","authenticated-orcid":false,"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University & Youtu Lab, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Hangbo Bao Li Dong and Furu Wei. 2021. BEiT: BERT Pre-Training of Image Transformers. arxiv: 2106.08254 https:\/\/arxiv.org\/abs\/2106.08254"},{"key":"e_1_3_2_1_2_1","unstructured":"Adrian Bulat Shiyang Cheng Jing Yang Andrew Garbett Enrique Sanchez and Georgios Tzimiropoulos. 2021. Pre-training strategies and datasets for facial representation learning. arxiv: 2103.16554"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00038"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19--1423"},{"key":"e_1_3_2_1_8_1","unstructured":"Xiaoyi Dong Jianmin Bao Ting Zhang Dongdong Chen Weiming Zhang Lu Yuan Dong Chen Fang Wen and Nenghai Yu. 2021. PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers. arxiv: 2111.12710 https:\/\/arxiv.org\/abs\/2111.12710"},{"key":"e_1_3_2_1_9_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","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. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_10_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, et al.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","volume":"2721","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks, Kimin Lee, and Mantas Mazeika. 2019. Using Pre-Training Can Improve Model Robustness and Uncertainty. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 2712--2721. http:\/\/proceedings.mlr.press\/v97\/hendrycks19a.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"e_1_3_2_1_16_1","volume-title":"MST: Masked Self-Supervised Transformer for Visual Representation. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Li Zhaowen","year":"2021","unstructured":"Zhaowen Li, Zhiyang Chen, Fan Yang, Wei Li, Yousong Zhu, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, and Jinqiao Wang. 2021. MST: Masked Self-Supervised Transformer for Visual Representation. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 13165--13176. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/6dbbe6abe5f14af882ff977fc3f35501-Abstract.html"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6832"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.59"},{"key":"e_1_3_2_1_20_1","unstructured":"Christoph Schuhmann Richard Vencu Romain Beaumont Robert Kaczmarczyk Clayton Mullis Aarush Katta Theo Coombes Jenia Jitsev and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arxiv: 2111.02114"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113780"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_16"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_1_26_1","volume-title":"Designing one unified framework for high-fidelity face reenactment and swapping","author":"Xu Chao","unstructured":"Chao Xu, Jiangning Zhang, Yue Han, Guanzhong Tian, Xianfang Zeng, Ying Tai, Yabiao Wang, Chengjie Wang, and Yong Liu. 2022. Designing one unified framework for high-fidelity face reenactment and swapping. In ECCV. Springer, 54--71."},{"key":"e_1_3_2_1_27_1","volume-title":"Rethinking Mobile Block for Efficient Neural Models. ICCV","author":"Zhang Jiangning","year":"2023","unstructured":"Jiangning Zhang, Xiangtai Li, Jian Li, Liang Liu, Zhucun Xue, Boshen Zhang, Zhengkai Jiang, Tianxin Huang, Yabiao Wang, and Chengjie Wang. 2023. Rethinking Mobile Block for Efficient Neural Models. ICCV (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Eatformer: Improving vision transformer inspired by evolutionary algorithm.","author":"Zhang Jiangning","year":"2022","unstructured":"Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong Liu, and Dacheng Tao. 2022. Eatformer: Improving vision transformer inspired by evolutionary algorithm. (2022). arxiv: 2206.09325"},{"key":"e_1_3_2_1_29_1","first-page":"26674","article-title":"Analogous to evolutionary algorithm: Designing a unified sequence model","volume":"34","author":"Zhang Jiangning","year":"2021","unstructured":"Jiangning Zhang, Chao Xu, Jian Li, Wenzhou Chen, Yabiao Wang, Ying Tai, Shuo Chen, Chengjie Wang, Feiyue Huang, and Yong Liu. 2021. Analogous to evolutionary algorithm: Designing a unified sequence model. NeurIPS, Vol. 34 (2021), 26674--26688.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_30_1","volume-title":"Freenet: Multi-identity face reenactment. In CVPR. 5326--5335.","author":"Zhang Jiangning","year":"2020","unstructured":"Jiangning Zhang, Xianfang Zeng, Mengmeng Wang, Yusu Pan, Liang Liu, Yong Liu, Yu Ding, and Changjie Fan. 2020. Freenet: Multi-identity face reenactment. In CVPR. 5326--5335."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"e_1_3_2_1_33_1","volume-title":"Image BERT Pre-training with Online Tokenizer. In International Conference on Learning Representations.","author":"Zhou Jinghao","year":"2021","unstructured":"Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, and Tao Kong. 2021. Image BERT Pre-training with Online Tokenizer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.371"}],"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\/3581783.3611999","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:14:08Z","timestamp":1755821648000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611999"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":34,"alternative-id":["10.1145\/3581783.3611999","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611999","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"}}]}}