{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:25:49Z","timestamp":1776489949976,"version":"3.51.2"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"European Union\u2019s Horizon 2020 research and innovation program","award":["957337"],"award-info":[{"award-number":["957337"]}]},{"name":"NextGenerationEU","award":["PE00000013"],"award-info":[{"award-number":["PE00000013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>The unprecedented development of deep learning approaches for video processing has caused growing privacy concerns. To ensure data analysis while maintaining privacy, it is essential to address how to protect individuals\u2019 identities. One solution is to anonymize data at the source, avoiding the transmission or storage of information that could lead to identification. This study introduces XimSwap, a novel deep learning technique for real-time video anonymization, which can remove facial identification features directly on edge devices with minimal computational resources. Our approach offers a comprehensive solution that guarantees privacy by design. This novel method for implementing face-swapping ensures that the pose and expression of a target face remain unchanged and can be used on embedded devices with very limited computational resources. By incorporating style transfer layers into convolutional ones and optimizing the network\u2019s operation, we achieved a reduction of over 98% in the required operations and parameters compared with state-of-the-art architectures. Our approach also significantly reduces RAM usage, making it possible to implement the anonymization process on tiny edge devices, including microcontrollers, such as the STM32H743.<\/jats:p>","DOI":"10.1145\/3603173","type":"journal-article","created":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T11:00:15Z","timestamp":1685617215000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["XimSwap: Many-to-Many Face Swapping for TinyML"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1396-3709","authenticated-orcid":false,"given":"Alberto","family":"Ancilotto","sequence":"first","affiliation":[{"name":"E3DA Unit, Digital Society Center - Fondazione Bruno Kessler (FBK), Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5553-7935","authenticated-orcid":false,"given":"Francesco","family":"Paissan","sequence":"additional","affiliation":[{"name":"E3DA Unit, Digital Society Center - Fondazione Bruno Kessler (FBK), Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9047-9868","authenticated-orcid":false,"given":"Elisabetta","family":"Farella","sequence":"additional","affiliation":[{"name":"E3DA Unit, Digital Society Center - Fondazione Bruno Kessler (FBK), Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops53856.2022.9767380"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956041"},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/BalkanCom53780.2021.9593258","article-title":"MARVEL: Multimodal extreme scale data analytics for smart cities environments","author":"Bajovi\u0107 Dragana","year":"2021","unstructured":"Dragana Bajovi\u0107, Arian Bakhtiarnia, George N. Bravos, Alessio Brutti, Felix Burkhardt, Daniel Cauchi, Antony Chazapis, Claire Cianco, Nicola Dall\u2019Asen, Vlado Deli\u0107, Christos Dimou, Djordje Djokic, Antonio Escobar-Molero, Lukas Esterle, Florian Eyben, Elisabetta Farella, Thomas Festi, Artemios Geromitsos, Giannis Giakoumakis, George Hatzivasilis, Sotiris Ioannidis, Alexandros Iosifidis, Theodora Kallipolitou, Grigorios Kalogiannis, Akrivi Kiousi, Despina Kopanaki, Manolis Marazakis, Stella Markopoulou, Adrian Muscat, Francesco Paissan, Tom\u00e1s Pariente Lobo, Duan Pavlovi\u0107, Theofanis P. Raptis, Elisa Ricci, Borja Saez, Farhan Sahito, Kenneth Scerri, Bj\u00f6rn Schuller, Nikola Simi\u0107, George Spanoudakis, Alex Tomasi, Andreas Triantafyllopoulos, Lorenzo Valerio, Javier Villaz\u00e1n, Yiming Wang, Andr\u00e9 Xuereb, and John David Zammit. 2021. MARVEL: Multimodal extreme scale data analytics for smart cities environments. 2021 International Balkan Conference on Communications and Networking (BalkanCom) (2021), 143\u2013147.","journal-title":"2021 International Balkan Conference on Communications and Networking (BalkanCom)"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.23919\/EUSIPCO55093.2022.9909572","volume-title":"2022 30th European Signal Processing Conference (EUSIPCO)","author":"Brutti Alessio","year":"2022","unstructured":"Alessio Brutti, Francesco Paissan, Alberto Ancilotto, and Elisabetta Farella. 2022. Optimizing PhiNet architectures for the detection of urban sounds on low-end devices. In 2022 30th European Signal Processing Conference (EUSIPCO). 1121\u20131125."},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","DOI":"10.1145\/3394171.3413630","article-title":"SimSwap: An efficient framework for high fidelity face swapping","author":"Chen Renwang","year":"2020","unstructured":"Renwang Chen, Xuanhong Chen, Bingbing Ni, and Yanhao Ge. 2020. SimSwap: An efficient framework for high fidelity face swapping. Proceedings of the 28th ACM International Conference on Multimedia (2020).","journal-title":"Proceedings of the 28th ACM International Conference on Multimedia"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107422"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/978-3-031-06430-2_42","article-title":"Graph-based generative face anonymisation with pose preservation","author":"Dall\u2019Asen Nicola","year":"2022","unstructured":"Nicola Dall\u2019Asen, Yiming Wang, Hao Tang, Luca Zanella, and Elisa Ricci. 2022. Graph-based generative face anonymisation with pose preservation. Image Analysis and Processing\u2013ICIAP 2022: 21st International Conference, Lecce, Italy, May 23\u201327, 2022, Proceedings, Part II, 503\u2013515.","journal-title":"Image Analysis and Processing\u2013ICIAP 2022: 21st International Conference, Lecce, Italy, May 23\u201327, 2022, Proceedings, Part II"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","first-page":"4685","DOI":"10.1109\/CVPR.2019.00482","article-title":"ArcFace: Additive angular margin loss for deep face recognition","author":"Deng Jiankang","year":"2019","unstructured":"Jiankang Deng, J. Guo, and Stefanos Zafeiriou. 2019. ArcFace: Additive angular margin loss for deep face recognition. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 4685\u20134694.","journal-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.01.027"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00947"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2012.12.007"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3196668"},{"key":"e_1_3_1_14_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume":"1704","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. CoRR abs\/1704.04861 (2017). arXiv:1704.04861http:\/\/arxiv.org\/abs\/1704.04861.","journal-title":"CoRR"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","author":"Huang Gao","year":"2017","unstructured":"Gao Huang, Zhuang Liu, and Kilian Q. Weinberger. 2017. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017), 2261\u20132269.","journal-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33720-9_44"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Glenn Jocher Ayush Chaurasia Alex Stoken Jirka Borovec NanoCode012 Yonghye Kwon TaoXie Kalen Michael Jiacong Fang imyhxy Lorna Colin Wong (Zeng Yifu) Abhiram V Diego Montes Zhiqiang Wang Cristi Fati Jebastin Nadar Laughing UnglvKitDe tkianai yxNONG Piotr Skalski Adam Hogan Max Strobel Mrinal Jain Lorenzo Mammana and xylieong. 2022. ultralytics\/yolov5: v6.2 - YOLOv5 Classification Models Apple M1 Reproducibility ClearML and Deci.ai integrations. DOI:10.5281\/zenodo.7002879","DOI":"10.5281\/zenodo.7002879"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","first-page":"4396","DOI":"10.1109\/CVPR.2019.00453","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras Tero","year":"2019","unstructured":"Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 4396\u20134405.","journal-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755843"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2949614"},{"key":"e_1_3_1_22_2","volume-title":"AAAI Conference on Artificial Intelligence","author":"Xu Zhi Liang","year":"2021","unstructured":"Zhi Liang Xu, Xiyu Yu, Zhibin Hong, Zhen Zhu, Junyu Han, Jingtuo Liu, Errui Ding, and Xiang Bai. 2021. FaceController: Controllable attribute editing for face in the wild. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_1_23_2","volume-title":"Neural Information Processing Systems","author":"Lin Ji","year":"2021","unstructured":"Ji Lin, Wei-Ming Chen, Han Cai, Chuang Gan, and Song Han. 2021. MCUNetV2: Memory-efficient patch-based inference for tiny deep learning. In Neural Information Processing Systems."},{"key":"e_1_3_1_24_2","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS\u201920)","author":"Lin Ji","year":"2020","unstructured":"Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, and Song Han. 2020. MCUNet: Tiny deep learning on IoT devices. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS\u201920). Curran Associates Inc., Red Hook, NY, USA, Article 982, 12 pages."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00549"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746093"},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1109\/ICASSP43922.2022.9746093","article-title":"Scalable neural architectures for end-to-end environmental sound classification","author":"Paissan Francesco","year":"2022","unstructured":"Francesco Paissan, Alberto Ancilotto, Alessio Brutti, and Elisabetta Farella. 2022. Scalable neural architectures for end-to-end environmental sound classification. ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2022), 641\u2013645.","journal-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510832"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWASI.2019.8791337"},{"key":"e_1_3_1_30_2","article-title":"Enabling energy efficient machine learning on an ultra-low-power vision sensor for IoT","volume":"2102","author":"Paissan Francesco","year":"2021","unstructured":"Francesco Paissan, Massimo Gottardi, and Elisabetta Farella. 2021. Enabling energy efficient machine learning on an ultra-low-power vision sensor for IoT. ArXiv abs\/2102.01340 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_1_31_2","first-page":"1","volume-title":"BMVC 2015 - Proceedings of the British Machine Vision Conference 2015","author":"Parkhi Omkar M.","year":"2015","unstructured":"Omkar M. Parkhi, Andrea Vedaldi, and Andrew Zisserman. 2015. Deep face recognition. In BMVC 2015 - Proceedings of the British Machine Vision Conference 2015. British Machine Vision Association, 1\u201312."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2731301"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"issue":"2","key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s12394-010-0055-x","article-title":"Privacy by design","volume":"3","author":"Schaar Peter","year":"2010","unstructured":"Peter Schaar. 2010. Privacy by design. Identity in the Information Society 3, 2 (2010), 267\u2013274.","journal-title":"Identity in the Information Society"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_34"},{"key":"e_1_3_1_36_2","article-title":"Bipartite graph reasoning GANs for person image generation","author":"Tang Hao","year":"2020","unstructured":"Hao Tang, Song Bai, Philip H. S. Torr, and N. Sebe. 2020. Bipartite graph reasoning GANs for person image generation. Proceedings of the 31st British Machine Vision Virtual Conference, 7th\u201310th September 2020 (2020).","journal-title":"Proceedings of the 31st British Machine Vision Virtual Conference, 7th\u201310th September 2020"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Chien-Yao Wang Alexey Bochkovskiy and Hong-yuan Liao. 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. DOI:10.48550\/arXiv.2207.02696","DOI":"10.48550\/arXiv.2207.02696"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/157"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20203"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Zbigniew Wojna Jasper Uijlings Sergio Guadarrama Nathan Silberman Liang-Chieh Chen Alireza Fathi and Vittorio Ferrari. 2017. The devil is in the decoder. In Proceedings of the British Machine Vision Conference (BMVC) Tae-Kyun Kim Stefanos Zafeiriou Gabriel Brostow and Krystian Mikolajczyk (Eds.). BMVA Press 10.1\u201310.13. 10.5244\/C.31.10","DOI":"10.5244\/C.31.10"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603173","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:10Z","timestamp":1750286950000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3603173"],"URL":"https:\/\/doi.org\/10.1145\/3603173","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2022-11-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}