Kanglei Zhou

PhD Candidate

Beihang University

About Me

I am a final-year PhD candidate at the State Key Lab of VR Technology and Systems, SCSE, Beihang University. I am expected to graduate in June 2025. My research primarily focuses on utilizing structured human knowledge to enhance human motion analysis.

Announcement: I am actively seeking job opportunities and would be delighted to discuss how my expertise can benefit your team.

Interests

Human motion analysis
VR/AR/MR
Continual learning

Education

PhD in CS, 2020-Now

Beihang University
Visiting Student, 2024

Durham University
BSc in CS, 2016-2020

Henan Normal University
Exchange Student, 2019

Frankfurt University of Applied Science

Research

Human Motion Analysis

My Previous Work

This research tackles three key challenges in human motion analysis - motion perception anomalies, negative transfer due to limited samples, and catastrophic forgetting in non-stationary data distributions. By leveraging spatiotemporal graph models, domain adaptation, and continual learning, innovative methods were developed to address these issues, achieving significant advancements in aerospace training and medical rehabilitation applications.

Research Proposal

This proposal explores innovative solutions for Multi-Modal Action Quality Assessment, focusing on addressing challenges such as modality heterogeneity, missing data, and lack of interpretability in current methods.

Selected Publications

See the full publication list on my Scholar profile

Kanglei Zhou, Hubert P. H. Shum, Frederick W. B. Li, Xingxing Zhang, Xiaohui Liang (2025). PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction. TIP 2025.

PDF Cite DOI GitHub arXiv

Kanglei Zhou, Zikai Hao, Liyuan Wang, Xiaohui Liang (2025). Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in Virtual Reality. IEEE VR 2025 - TVCG.

PDF Cite DOI GitHub arXiv Bilibili Oral Presentation

Kanglei Zhou, Liyuan Wang, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Jianguo Li, Xiaohui Liang (2024). MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment. ECCV 2024.

PDF Cite Poster Slides DOI GitHub arXiv Oral Presentation (~2.3%)

Kanglei Zhou, Junlin Li, Ruizhi Cai, Liyuan Wang, Xinxing Zhang, Xiaohui Liang (2024). CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment. IJCAI 2024.

PDF Cite DOI GitHub arXiv

Kanglei Zhou, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang (2023). Multi-Task Spatial-Temporal Graph Auto-Encoder for Hand Motion Denoising. TVCG.

PDF Cite DOI GitHub Bilibili