Rate My Professor Qiuhong Ke

Dr. Qiuhong Ke is an ARC DECRA Fellow and Senior Lecturer at the Faculty of Information Technology, Monash University, affiliated with the Department of Data Science & AI. She earned her PhD in Computer Science from the University of Western Australia in 2018, with her thesis titled “Deep Learning for Action Recognition and Prediction” receiving the Dean’s List – Honourable Mention. Her career includes a Postdoctoral Researcher position at the Max Planck Institute for Informatics from 2018 to 2019, Lecturer at the University of Melbourne from 2020 to 2022, and an ongoing Honorary Fellow role at the University of Western Australia. In April 2025, she was promoted to Level C Senior Lecturer, and her ARC DECRA Fellowship began in January 2025. Ke has received the Academic Exceptional Prize from Monash University in 2025, Women Leading Tech Awards (Education/Research) in 2024, IEEE Transactions on Multimedia Outstanding Reviewer Award in 2021, APRS Early Career Researcher Award in 2020, and the 1962 Medal from the Australian Computer Society in 2019. She holds editorial roles as Associate Editor for IEEE Transactions on Multimedia since 2025, ACM Computing Surveys since 2024, and Pattern Recognition since 2024. Ke has served as Area Chair for CVPR 2025 and 2026, ACM Multimedia 2024, and Asian Conference on Computer Vision 2022, and as co-organizer of the Workshop on Vision Datasets Understanding at CVPR 2022–2024 and ICCV 2025.

Her research interests center on human action understanding, video analysis, and multimodal large language models. Key publications include “A New Representation of Skeleton Sequences for 3D Action Recognition” (CVPR 2017), “Human action recognition from various data modalities: A review” (IEEE TPAMI 2022), “Learning clip representations for skeleton-based 3D action recognition” (IEEE TIP 2018), “DiffPose: Toward More Reliable 3D Pose Estimation” (CVPR 2023), “Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis” (CVPR 2025), “Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition” (CVPR 2025), “Part-aware unified representation of language and skeleton for zero-shot action recognition” (CVPR 2024), and “Progressive video summarization via multimodal self-supervised learning” (WACV 2023). With 57 research outputs, she supervises PhD, research assistant, and master students on topics including multimodal LLMs and human understanding.