I obtained my Ph.D. degree from the Department of Computer Science at City University of Hong Kong, supervised by Dr. Weitao Xu (IEEE Senior Member) and co-supervised by Prof. Xiaohua Jia (IEEE Fellow), I also work closely with Dr. Tianxing Li. Before that, I obtained my M.Sc. degree from the Hong Kong University of Science and Technology (HKUST) in 2019, and my B.E. degree from the Harbin Engineering University (HEU) in 2018, respectively.
My research lies at the intersection of Mobile Computing and Human-Computer Interaction — with a special focus on system-enabled novel applications, wearable sensing, and deep learning. I received the IEEE PerCom 2023 Mark Weiser Best Paper Award.
I'm focusing on system-enabled novel applications and human-computer interaction.
[C] F2Key: Dynamically Converting Your Face into a Private Key Based on COTS Headphones for Reliable Voice Interaction Di Duan, Zehua Sun, Tao Ni, Shuaicheng Li, Xiaohua Jia, Weitao Xu, Tianxing Li [MobiSys'24]The 22nd ACM International Conference on Mobile Systems, Applications, and Services
CCF BCORE A
[C] EarSE: Bringing Robust Speech Enhancement to COTS Headphones Di Duan, Yongliang Chen, Weitao Xu, Tianxing Li [IMWUT/UbiComp'24]ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
CCF ACORE A*
[C] EMGSense: A Low-Effort Self-Supervised Domain Adaptation Framework for EMG Sensing Di Duan, Huanqi Yang, Guohao Lan, Tianxing Li, Xiaohua Jia, Weitao Xu [PerCom'23]The 21st International Conference on Pervasive Computing and Communications accpetance rate: 16.9%🏆 Mark Weiser Best Paper Award (1/159)
CCF BCORE A*
[C] Medusa3D: The Watchful Eye Freezing Illegitimate Users in Virtual Reality Interactions Aochen Jiao*, Di Duan* (*co-first authors), Weitao Xu [MobileHCI'24]The ACM International Conference on Mobile Human-Computer Interaction
CCF BCORE B
Other Publications
[J] Scenario-Adaptive Key Establishment Scheme for LoRa-enabled IoV Communications
Huanqi Yang, Di Duan, Hongbo Liu, Chengwen Luo, Yuezhong Wu, Wei Li, Albert Y. Zomaya, Linqi Song, Weitao Xu [TMC]IEEE Transactions on Mobile Computing
[C] RF-Egg: An RF Solution for Fine-Grained Multi-Target and Multi-Task Egg Incubation Sensing
Zehua Sun, Tao Ni, Yongliang Chen, Di Duan, Kai Liu, Weitao Xu [MobiCom'24]The 30th Annual International Conference On Mobile Computing And Networking
[J] mmSign: mmWave-based Few-Shot Online Handwritten Signature Verification
Mingda Han, Huanqi Yang, Tao Ni, Di Duan, Mengzhe Ruan, Yongliang Chen, Jia Zhang, Weitao Xu [TOSN]ACM Transactions on Sensor Networks
[W] EarDA: Towards Accurate and Data-Efficient Earable Activity Sensing
Shengzhe Lyu, Yongliang Chen, Di Duan, Renqi Jia, Weitao Xu [CSCAIoTSys]CPS-IoT Week 2024 Workshop on Coupling of Sensing & Computing in AIoT Systems
Selected Projects
[MobiSys'24] F2Key: Dynamically Converting Your Face into a Private Key Based on COTS Headphones for Reliable Voice Interaction Di Duan,
Zehua Sun,
Tao Ni,
Shuaicheng Li,
Xiaohua Jia,
Weitao Xu,
Tianxing Li
[paper] [cite] [slide]
F2Key is the first earable physical security system based on COTS headphones that enables several security-related applications, such as artifacts anti-counterfeiting, speech manipulation/deepfake detection, defence against voiceprint-based attacks.
[IMWUT/UbiComp'24] EarSE: Bringing Robust Speech Enhancement to COTS Headphones Di Duan,
Yongliang Chen,
Weitao Xu,
Tianxing Li
[paper] [cite]
EarSE is a pioneer in exploring boom mic sensing, for the first time utilizing COTS headphones and boom/modular microphones to establish a stable acoustic sensing field across the user's face. It filters out ambient noise to obtain the wearer's clean speech in a multi-modality manner.
[PerCom'23] EMGSense: A Low-Effort Self-Supervised Domain Adaptation Framework for EMG Sensing Di Duan,
Huanqi Yang,
Guohao Lan,
Tianxing Li,
Xiaohua Jia,
Weitao Xu
[paper] [cite]
🏆 Mark Weiser Best Paper Award (1/159)
EMGSense framework addresses the biological heterogeneity problem in cross-domain deployment of EMG-based applications in a low-effort manner, combining domain adaptation and self-supervised learning techniques.
