{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:50:17Z","timestamp":1772905817957,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":62,"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":"the Youth Innovation Promotion Association CAS and InnoHK program","award":["Y2021131"],"award-info":[{"award-number":["Y2021131"]}]},{"name":"Beijing Natural Science Foundation","award":["L221013"],"award-info":[{"award-number":["L221013"]}]},{"name":"Chinese National Natural Science Foundation Projects","award":["U2003111, 62276254, 62176256"],"award-info":[{"award-number":["U2003111, 62276254, 62176256"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611711","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"8076-8085","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Cross-Architecture Distillation for Face Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3957-8590","authenticated-orcid":false,"given":"Weisong","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, CAS & School of Cyber Security, UCAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4636-9677","authenticated-orcid":false,"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"MAIS, CASIA & School of Artificial Intelligence, UCAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9645-4586","authenticated-orcid":false,"given":"Zhixiang","family":"He","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Ltd. Data&AI Technology Company, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1630-6058","authenticated-orcid":false,"given":"Xiao-Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, CAS & School of Cyber Security, UCAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"MAIS, CASIA, School of Artificial Intelligence, UCAS, & CAIR, HKISI, CAS, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97909-0_46"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11783"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"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":"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_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","volume-title":"Distilling the Knowledge in a Neural Network. CoRR","author":"Hinton Geoffrey E.","year":"2015","unstructured":"Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. CoRR, Vol. abs\/1503.02531 (2015). [arXiv]1503.02531 http:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_13_1","volume-title":"Workshop on faces in'Real-Life'Images: detection, alignment, and recognition.","author":"Huang Gary B","year":"2008","unstructured":"Gary B Huang, Marwan Mattar, Tamara Berg, and Eric Learned-Miller. 2008. Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In Workshop on faces in'Real-Life'Images: detection, alignment, and recognition."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01818"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16969"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.527"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755843"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.112"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Stan Z. Li and Anil K. Jain (Eds.). 2011. Handbook of Face Recognition 2nd Edition. Springer. https:\/\/doi.org\/10.1007\/978-0-85729-932-1","DOI":"10.1007\/978-0-85729-932-1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00816"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"e_1_3_2_1_28_1","volume-title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. CoRR","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021b. P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. CoRR, Vol. abs\/2110.07602 (2021). showeprint[arXiv]2110.07602 https:\/\/arxiv.org\/abs\/2110.07602"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 3396--3411","author":"Liu Yufan","year":"2022","unstructured":"Yufan Liu, Jiajiong Cao, Bing Li, Weiming Hu, Jingting Ding, and Liang Li. 2022a. Cross-Architecture Knowledge Distillation. In Proceedings of the Asian Conference on Computer Vision. 3396--3411."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_32_1","volume-title":"Zemel","author":"Luo Wenjie","year":"2016","unstructured":"Wenjie Luo, Yujia Li, Raquel Urtasun, and Richard S. Zemel. 2016. Understanding the Effective Receptive Field in Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (Eds.). 4898--4906. https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/c8067ad1937f728f51288b3eb986afaa-Abstract.html"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01400"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.250"},{"key":"e_1_3_2_1_36_1","unstructured":"NVIDIA. 2007. CUDA. https:\/\/developer.nvidia.com\/cuda-zone"},{"key":"e_1_3_2_1_37_1","unstructured":"NVIDIA. 2022. TensorRT. https:\/\/developer.nvidia.com\/cuda-zone"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_27"},{"key":"e_1_3_2_1_42_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for Thin Deep Nets. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6550"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477558"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.13218"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"e_1_3_2_1_47_1","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Sun Yi","year":"2014","unstructured":"Yi Sun, Yuheng Chen, Xiaogang Wang, and Xiaoou Tang. 2014. Deep Learning Face Representation by Joint Identification-Verification. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8--13 2014, Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 1988--1996. https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/e5e63da79fcd2bebbd7cb8bf1c1d0274-Abstract.html"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9 gou. 2021. Training data-efficient image transformers & distillation through attention. 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, 10347--10357. http:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_1_50_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478324"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.87"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"e_1_3_2_1_56_1","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=Sks9_ajex","author":"Zagoruyko Sergey","year":"2017","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2017. Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=Sks9_ajex"},{"key":"e_1_3_2_1_57_1","volume-title":"Grouped Knowledge Distillation for Deep Face Recognition. In AAAI","author":"Zhao Weisong","year":"2023","unstructured":"Weisong Zhao, Xiangyu Zhu, Kaiwen Guo, Xiao-Yu Zhang, and Zhen Lei. 2023. Grouped Knowledge Distillation for Deep Face Recognition. In AAAI 2023."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3170246"},{"key":"e_1_3_2_1_59_1","first-page":"7","article-title":"Cross-pose lfw: A database for studying cross-pose face recognition in unconstrained environments. Beijing University of Posts and Telecommunications","volume":"5","author":"Zheng Tianyue","year":"2018","unstructured":"Tianyue Zheng and Weihong Deng. 2018. Cross-pose lfw: A database for studying cross-pose face recognition in unconstrained environments. Beijing University of Posts and Telecommunications, Tech. Rep, Vol. 5 (2018), 7.","journal-title":"Tech. Rep"},{"key":"e_1_3_2_1_60_1","volume-title":"Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments. CoRR","author":"Zheng Tianyue","year":"2017","unstructured":"Tianyue Zheng, Weihong Deng, and Jiani Hu. 2017. Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments. CoRR, Vol. abs\/1708.08197 (2017). [arXiv]1708.08197 http:\/\/arxiv.org\/abs\/1708.08197"},{"key":"e_1_3_2_1_61_1","volume-title":"Face transformer for recognition. arXiv preprint arXiv:2103.14803","author":"Zhong Yaoyao","year":"2021","unstructured":"Yaoyao Zhong and Weihong Deng. 2021a. Face transformer for recognition. arXiv preprint arXiv:2103.14803 (2021)."},{"key":"e_1_3_2_1_62_1","volume-title":"Face Transformer for Recognition. CoRR","author":"Zhong Yaoyao","year":"2021","unstructured":"Yaoyao Zhong and Weihong Deng. 2021b. Face Transformer for Recognition. CoRR, Vol. abs\/2103.14803 (2021). [arXiv]2103.14803 https:\/\/arxiv.org\/abs\/2103.14803"}],"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\/3581783.3611711","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:02Z","timestamp":1755821102000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":62,"alternative-id":["10.1145\/3581783.3611711","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611711","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"}}]}}