Guangxun Zhu
- Pronouns: He/him/his
- Email: g.zhu.1@research.gla.ac.uk
- Personal Website
SAWB 502, Sir Alwyn Williams Building, University of Glasgow, Glasgow, Scotland, G12 8RZ
Research title: Multimodal Interaction Modeling for Pedestrian Behavior Prediction in Autonomous Driving
Research Summary
My research focuses on human behavior prediction in autonomous driving, using multimodal data to model human-environment interactions for improved predictions. This work sits at the intersection of machine learning, computer vision, and autonomous driving.
Publications
2025
Zhu, Guangxun, Fan, Shiyu, Dai, Hang and Ho, Edmond S.L. 
ORCID: https://orcid.org/0000-0001-5862-106X
(2025)
Waymo-3DSkelMo: A Multi-Agent 3D Skeletal Motion Dataset for Pedestrian Interaction Modeling in Autonomous Driving.
In: 33rd ACM International Conference on Multimedia (MM '25), Dublin, Ireland, 27-31 October 2025,
pp. 13184-13190.
ISBN 9798400720352
(doi: 10.1145/3746027.3758273)
Conference Proceedings
Zhu, Guangxun, Fan, Shiyu, Dai, Hang and Ho, Edmond S.L. ORCID: https://orcid.org/0000-0001-5862-106X
(2025)
Waymo-3DSkelMo: A Multi-Agent 3D Skeletal Motion Dataset for Pedestrian Interaction Modeling in Autonomous Driving.
In: 33rd ACM International Conference on Multimedia (MM '25), Dublin, Ireland, 27-31 October 2025,
pp. 13184-13190.
ISBN 9798400720352
(doi: 10.1145/3746027.3758273)
Grants
-
China Scholarship Council- University of Glasgow Scholarship (2024-2028), June. 2024.
