|
Di Duan I am a Postdoctoral Fellow in the Department of Information Engineering at The Chinese University of Hong Kong (CUHK), advised by Prof. Guoliang Xing (IEEE Fellow). Before join CUHK AIOT lab, I obtained my Ph.D. degree from the Department of Computer Science at City University of Hong Kong (CityU), 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. Prior to 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.
Email: duandiacademic [AT] gmail [DOT] com Email / CV (Updated: 2024-11) / Google Scholar / LinkedIn |
|
News
Publications[C] Conference; [J] Journal; [W] Workshop; [P] Poster; [D] Demo (*co-first authors)
The underlined first author is under my guidance.
Main Publications
Other Publications
|
![[link]](award/PerCom23_Best.jpg){kind=link}
![[link]](award/MobileHCI24_Honorable.jpg){kind=link}
Selected Projects |
|
|
[arXiv] Argus: Multi-View Egocentric Human Mesh Reconstruction Based on Stripped-Down Wearable mmWave Add-on
Di Duan, Shengzhe Lyu, Mu Yuan, Hongfei Xue, Tianxing Li, Weitao Xu, Kaishun Wu, Guoliang Xing [paper] [cite] Argus is the first to investigate multi-view egocentric HMR based on stripped-down mmWave radars in a multi-view configuration. Compared to conventional frontal-view solutions, it addresses several pain points, such as restricted sensing range and occlusion issues. |
|
[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] [slide] 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. |
Professional Services
|
Teaching Experience
|