Skip to main content Skip to navigation

Prospective PhD Students

Warwick Scholarships

In 25/26, I am looking for 1-2 bright students with strong maths/CS background, and if you want to do a PhD with me, please send me your CV. Warwick has some PhD scholarship schemes, which are open to UK/EU/International applicants.

1. China Scholarship Council Scholarship (30 CSC scholarships for Chinese Applicants, deadline: 13th Jan. 2025)

2. Chancellor's International Scholarship (42 CIS scholarships for EU/International Applicants, deadline: 9th Dec. 2024)

3. More Scholarships can be found here

PhD Project [Closed]

Title: WiFi-Vision Cross-modality learning for Human Activity Recognition

Supervisor: Dr. Yu Guan, Department of Computer Science, University of Warwick

Eligibility: This project is open to UK/EU/International applicants. The studentship covers fees at home rate. EU/International applicants are welcome to apply but will be required to cover the difference between home and EU/international fees.

Project Description: Human activity recognition (HAR) is a compelling topic in the fields of ubiquitous computing, with numerous applications including human behaviour understanding, smart healthcare, human-computer-interaction (HCI), and more. Among various sensing technologies, Radio Frequency (RF) signals such as WiFi can be applied in a less intrusive manner, offering significant potential in smart home environments. However, due to multipath propagation, WiFi signals often contain a high level of noise from physical environments that need to suppressed before developing HAR models.

In this PhD project, the student will investigate the following three main directions:

1) Designing effective WiFi feature templates (e.g., angle of arrival[1], Doppler frequency shift[4]) to capture human behaviour information while suppressing noise caused by various factors such as multipath effect.

2) Developing state-of-the-art cross-modality learning algorithms that can leverage other potential sensing modalities (e.g., 3D skeleton extracted from videos[2]) to provide supervision information for representation learning.

3) Developing practical WiFi(-vision) based HAR systems that can be generalised to different environments in real-world scenarios. The student can begin with existing public datasets (e.g., the MM-FI dataset[3], mRI dataset[6]), but will later need to collect their own dataset that includes real-world challenges (with multiple subjects, in less controlled environments). Additional new RF sensing modalities (such as mmWave [5][6][3]) can also be collected and incorporated into modelling.

Please contact Dr. Yu Guan (Yu.Guan@warwick.ac.uk) if you have any informal enquiries.

 

Reference

[1] Ren et al. GoPose: 3D Human Pose estimation using WiFi. ACM IMWUT 2022

[2]Zhao et al. PoseFormerV2: Exploring Frequency Domain for efficient and robust 3D Human Pose estimation, CVPR 2023.

[3] Yang, et al. MM-Fi: Multimodal Non-Intrusive 4D human dataset, NeurIPS, 2023.

[4] Liu et al. UniFi: A Unified Framework for Generalisable Gesture Recognition with Wi-Fi Signals using Consistency-guided multi-view Networks, ACM IMWUT 2024

[5] https://github.com/Intelligent-Perception-Lab/HIBER

[6] mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors, NeurIPS, 2022