Image

Xiao Gu

profile


About Me

I am now a Postdoctoral Researcher at the Computational Health Informatics Lab, University of Oxford, working with Prof David Clifton. Previously, I obtained my PhD degree in Computing and MRes degree (Distinction & Dean's Prize) in Medical Robotics and Image Guided Intervention, supervised by Dr Benny Lo and Prof Guang-Zhong Yang. Prior to that, I obtained BEng degree (Honors Student & National Scholarship) in Electronic Engineering from Fudan University in 2018, supervised by Prof Wei Chen. My research interests focus on integrating pervasive sensing (wearable and ambient sensors) and deep learning for healthcare, to address pressing generalization issues in real-world applications.



News


[2024-02-20]

   

One co-authored survey paper on lower-limb exoskeletons accepted to IEEE SMC.

[2024-02-06]

   

One paper on Motor Imagery EEG accepted to JBHI and selected as Front Cover.

[2024-01-15]

   

Our Workshop focusing on wearables and healthcare robotics will be hosted within ICRA24.

[2023-09-12]

   

Started as a postdoctoral researcher at Oxford.

[2023-08-23]

   

Passed my PhD viva! Many thanks to my supervisors, collaborators, and family!   Thesis

[2023-08-22]

   

One co-authored paper on semi-supervsied image segmentation accepted to BMVC23.

[2023-07-14]

   

One survey paper for AI in pervasive healthcare got accepted to IEEE R-BME.

[2023-05-30]

   

Co-Organize Workshop "AI in pervasive well-being and healthy ageing".

[2023-05-15]

   

Awarded ICRA student travel grant.

[2023-01-27]

   

One paper on egocentric image captioning got accepted to IEEE T-Cyber.

[2023-01-24]

   

One paper on egocentric pose estimation got accepted to IEEE T-MM.

[2023-01-16]

   

Two papers on intention recognition and egocentric pose estimation got accepted to ICRA 2023.

[2022-09-30]

   

One paper on self-supervised learning on facial expression recognition got accepted to BMVC 2022.

[2022-09-10]

   

One co-authored paper on annotation uncertainty got accepted to Medical Image Analysis.

[2022-07-15]

   

Gave a talk on our ECCV paper at University of Glasgow Healthcare Seminar.

[2022-07-03]

   

One paper on long-tailed classification under domain shifts got accepted to ECCV 2022.

[2022-07-01]

   

Won 2nd prize at Imperial Computing PhD Poster Competition.

[2022-06-30]

   

Two papers on egocentric behaviour understanding got accepted to IROS 2022.

[2022-06-19]

   

Won 3rd place for EPIC-Kitchens Action Anticipation CVPR 2022 Challenge.

[2022-01-31]

   

One paper on gait pose estimation got accepted to ICRA 2022.



Research

My research interests are mainly focused on three tracks in Machine Learning for Pervasive Healthcare
Generalization-Issue-Oriented   review paper
To examine and address real-world data learning issues, prompting generalizable and trustworthy solutions for digital health.
Dataset Scarcity (label scarcity / imbalanced /...),
Source Heterogeneity (cross-subject / position / modality / dataset /...),
Data&Annotation Quaility (noisy sensor data / annotation bias /...)
Sensing-Modality-Oriented
To harness the full potential of wearable and ambient sensing technologies for the development of healthcare solutions.
Ambient Camera / Egocentric Camera / EEG / EMG / IMU / ECG / Novel Sensing /...
Healthcare-Application-Oriented
To ultimately translate research advancements into tangible benefits for real-world health and wellbeing applications.
Rehabilitation Monitoring / Human Behaviour Understanding / Dietary Monitoring /...



Publications


Jianing Qiu, Frank P-W Lo, Xiao Gu, Modou L Jobarteh, Wenyan Jia, Tom Baranowski, Matilda Steiner-Asiedu, Alex K Anderson, Megan A McCrory, Edward Sazonov, Mingui Sun, Gary Frost, Benny Lo
Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring
IEEE Transactions on Cybernetics, 2023.   paper

Yuxuan Liu, Jianxin Yang, Xiao Gu, Yao Guo, Guang-Zhong Yang
EgoFish3D: Egocentric 3D Pose Estimation from a Fisheye Camera via Self-Supervised Learning
IEEE Transactions on Multimedia, 2023.   dataset   paper
Intractable to get ground truth of egocentric pose

Yuxuan Liu, Jianxin Yang, Xiao Gu, Yao Guo, Guang-Zhong Yang
EgoHMR: Egocentric Human Mesh Recovery via Hierarchical Latent Diffusion Model
IEEE International Conference on Robotics and Automation (ICRA), 2023.   project   paper

Xiao Gu, Jinpei Han, Guang-Zhong Yang, Benny Lo
Generalizable Movement Intention Recognition with Multiple Heterogeneous EEG Datasets
IEEE International Conference on Robotics and Automation (ICRA), 2023.   paper
Cross-dataset configuration changes, cross-subject heterogeneity
Limited diversity (subject number) of single dataset

Yuxuan Shu, Xiao Gu, Guang-Zhong Yang, Benny Lo
Revisiting Self-Supervised Contrastive Learning for Facial Expression Recognition
British Machine Vision Conference (BMVC), 2022.   project   paper
Annotation difficulty of large-scale affective datasets
Cross-subject heterogeneity

Hanxiao Zhang, Liang Chen, Xiao Gu, Minghui Zhang, Yulei Qin, Feng Yao, Zhexin Wang, Yun Gu, Guang-Zhong Yang
Trustworthy Learning with (Un)sure Annotation for Lung Nodule Diagnosis with CT
Medicial Image Analysis, 2022.   paper
Annotation quality of the lung nodule diagnosis

Xiao Gu, Yao Guo, Zeju Li, Jianing Qiu, Qi Dou, Yuxuan Liu, Benny Lo, Guang-Zhong Yang
Tackling Long-Tailed Category Distribution Under Domain Shifts
European Conference on Computer Vision (ECCV), 2022.   project  dataset   paper
Imbalanced distribution
General cross-domain shifts

Xiao Gu, Jianxin Yang, Hanxiao Zhang, Jianing Qiu, Frank Lo, Yao Guo, Guang-Zhong Yang, Benny Lo
Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimation
Preprint 2021.   dataset   paper
Time-consuming and expensive to acuqire ground truth from Mocap
Cross-viewpoint and sim2real heterogneity

Xiao Gu, Yao Guo, Guang-Zhong Yang, Benny Lo
Cross-Domain Self-Supervised Complete Geometric Representation Learning for Real-Scanned Point Cloud Based Pathological Gait Analysis
IEEE Journal of Biomedical and Health Informatics, 2021.   paper
Time-consuming and expensive to acuqire ground truth from Mocap
Noise from depth sensing
Cross-viewpoint and sim2real heterogneity

Yao Guo, Xiao Gu, Guang-Zhong Yang
MCDCD: Multi-Source Unsupervised Domain Adaptation for Abnormal Human Gait Detection
IEEE Journal of Biomedical and Health Informatics, 2021.   paper
Cross-subject heterogneity

Xiao Gu, Yao Guo, Fani Deligianni, Benny Lo, Guang-Zhong Yang
Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition
IEEE Transactions on Neural Networks and Learning Systems, 2020.   project  paper
Cross-subject heterogneity
Noisy sensory representations from wearable sensors

Xiao Gu, Yao Guo, Fani Deligianni, Guang-Zhong Yang
Coupled Real-Synthetic Domain Adaptation for Real-World Deep Depth Enhancement
IEEE Transactions on Image Processing, 2020.   project paper
Difficult to acquire clean depth maps
Noisy depth maps from RGBD cameras

Yuxuan Liu, Jianxin Yang, Xiao Gu, Yao Guo, Guang-Zhong Yang
Ego+X: An Egocentric Vision System for Global 3D Human Pose Estimation and Social Interaction Characterization
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.   project paper

Jianxin Yang, Yuxuan Liu, Xiao Gu, Gaung-Zhong Yang, Yao Guo
PoseSDF: Simultaneous 3D Human Shape Reconstruction and Gait Pose Estimation Using Signed Distance Functions
IEEE International Conference on Robotics and Automation (ICRA), 2022.  paper

Jianing Qiu, Lipeng Chen, Xiao Gu, Frank P-W Lo, Ya-Yen Tsai, Jiankai Sun, Jiaqi Liu, Benny Lo
Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion
IEEE Robotics and Automation Letters, 2022.   dataset  paper

Jianing Qiu, Frank Lo, Xiao Gu, Yingnan Sun, Shuo Jiang, Benny Lo
Indoor Future Person Localization from an Egocentric Wearable Camera
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.  paper

Jinpei Han, Xiao Gu, Benny Lo
Semi-Supervised Contrastive Learning for Generalizable Motor Imagery EEG Classification
2021 IEEE 17th International Conference on Wearable and Implantable Body Sensor Networks (BSN), 2021.  paper
Annotation uncertainty
Cross-subject/session heterogeneity

Fangzhi Mu, Xiao Gu, Yao Guo, Benny Lo
Unsupervised Domain Adaptation for Position-Independent IMU based Gait Analysis
2020 IEEE Sensors, 2020.   paper
Cross-position/subject heterogeneity

Yao Guo, Fani Deligianni, Xiao Gu, Guang-Zhong Yang
3D Canonical Pose Estimation and Abnormal Gait Recognition with a Single RGB-D Camera
IEEE Robotics and Automation Letters, 2019.  paper

Xiao Gu, Fani Deligianni, Benny Lo, Wei Chen, Guang-Zhong Yang
Markerless Gait Analysis based on a Single RGB Camera
2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN), 2018.   paper   slides

Saeed Akbarzadeh, Xiao Gu, Zhipeng Wu, Benny Lo
A Novel Active Human Echolocation Device
2022 IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN), 2022.  paper

Hongyu Chen, Xiao Gu, Zhenning Mei, Ke Xu, Kai Yan, Chunmei Lu, Laishuan Wang, Feng Shu, Qixin Xu, Sidarto Bambang Oetomo, Wei Chen
A Wearable Sensor System for Neonatal Seizure Monitoring
2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks (BSN), 2017.  paper





Academic Activities


Journal: IEEE TNNLS, IEEE TII, IEEE JBHI, IEEE TNSRE, IEEE Sensors Journal, IEEE JTEHM, IEEE RAL, Frontiers in Medicine, Frontiers in Neurorobotics, Neuroscience Letter, etc.
Conference: WACV 20, ICRA 21-23, IROS 21, EPIC-ICCVW 21, ML4H 21-22, IPCAI 22, NeurIPS-TS4H 22, ECCV 22, CVPR 23, ICCV 23, BMVC 23.



2023 Jan 17, "Towards Data-Efficient and Generalizable Learning for Sensing Informatics".
Oxford Wearables Group, University of Oxford.
2022 July 15, "Tackling Long-Tailed Category Distribution Under Domain Shifts for Egocentric Action Anticipation".
Healthcare Seminar, University of Glasgow.
2021 Jan 21, "Generalizable Deep Learning in Pervasive Healthcare: Case Study in Gait Analysis".
CIME Seminar, Fudan University.
2020 May 20, "Learning from Synthetic Data for Real-World Tasks".
ML in Science Colloquium, University of Glasgow.





Honours and Awards


2023 IEEE ICRA Student Travel Grant.
2020 Dean's Prize for Medical Robotics and Image Guided Intervention, Imperial College London.
2018 Outstanding Graduates of Shanghai (1% of all students, Highest honour for undergraduates).
2018 Honours Student Award in Electronic Engineering (Less than 1% of all students), Fudan University.
2018 Xiyuan Scholar (Excellence), Fudan’s Undergraduate Research Opportunities Program (No.16486).
2017 Outstanding Student, Fudan University.
2016 Outstanding Student Leader, Fudan University.
2015 Outstanding Student, Fudan University.



2019-2023 Hamlyn PhD Scholarship.
2017 National Scholarship (1% of all students, Highest honour).
2016 1st Prize, Joel & Ruth Spira Scholarship (Only 1 in all engineering departments), Fudan University.
2016 ELITE, LIU YONG LING Scholar (1st Prize, Scholarship for Outstanding Students), Fudan University.



2022 2nd Place, 3rd Imperial Computing Conference PhD Poster Competition.
2022 3rd Place, EPIC-Kitchens Action Anticipation CVPR Challenge 2022. [Report]
2021 3rd Place, EPIC-Kitchens Action Anticipation CVPR Challenge 2021. [Report]
2018 Silver Prize, Geneva International Exhibition of Inventions, Geneva, Switzerland. [News]
2016 1st Prize (Team Leader), National Biomedical Engineering Innovation Contest, China. [Video][Photo]







CONTACT

Email
xiao.gu@eng.ox.ac.uk
xiao.gu17@imperial.ac.uk
shawngu0822@gmail.com

SOCIAL LINKS

Last Updated : Feb 26 2024 by Xiao (Shawn)