Qiuhong Ke

University of Western Australia — Australia

Computer Science · Physical Sciences

22h-index2.4kcitations106works1.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(44), Anomaly Detection Techniques and Applications(33), Multimodal Machine Learning Applications(22), Domain Adaptation and Few-Shot Learning(19), Advanced Neural Network Applications(15)

Publications106 total

Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review
International Journal of Computer Vision·2026· 1 cited
Unlabeled data assisted domain adaptation for cross-scene image classification
Advances in Space Research·2026
Towards Bidirectional Adaptability for Few-Shot Class-Incremental Learning With Forward-Backward Knowledge Transfer
IEEE Transactions on Multimedia·2026
Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence·2026
Admitting Ignorance Helps the Video Question Answering Models to Answer
IEEE Transactions on Multimedia·2026
AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis
IEEE Transactions on Neural Networks and Learning Systems·2026
DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition
arXiv (Cornell University)·2025Open Access
TSTMotion: Training-free Scene-aware Text-to-motion Generation
2025· 1 cited
Open-World Amodal Appearance Completion
2025· 2 cited
Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
2025
Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition
2025
LongDiff: Training-Free Long Video Generation in One Go
2025
LatentMove: Towards Complex Human Movement Video Generation
arXiv (Cornell University)·2025Open Access
TSTMotion: Training-free Scene-aware Text-to-motion Generation
arXiv (Cornell University)·2025Open Access
Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
arXiv (Cornell University)·2025Open Access
Unified Prompt Attack Against Text-to-Image Generation Models
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 1 cited
Unified Prompt Attack Against Text-to-Image Generation Models
arXiv (Cornell University)·2025Open Access
Admitting Ignorance Helps the Video Question Answering Models to Answer
arXiv (Cornell University)·2025Open Access
Skeleton-OOD: An end-to-end skeleton-based model for robust out-of-distribution human action detection
Neurocomputing·2024· 6 citedOpen Access
Open-World Amodal Appearance Completion
arXiv (Cornell University)·2024Open Access
page 1 of 6Next →

Frequent Co-authors

Jun Liu(19), Hossein Rahmani(17), Mohammed Bennamoun(11), Senjian An(8), Ferdous Sohel(8), Farid Boussaïd(8), James Bailey(8), Lin Geng Foo(6), Mingming Gong(6), Zhipeng Fan(5), Duo Peng(5), Tianjiao Li(5), Richard Sinnott(4), Haopeng Li(4), Anqi Zhu(4), Yinjie Lei(3), Rui Zhang(3), Jianhong Pan(3), Bernt Schiele(2), Zihan Yang(2)