Ngai‐Man Cheung

Hong Kong Polytechnic University — Hong Kong

Computer Science · Physical Sciences

39h-index5.5kcitations266works1.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Image and Video Retrieval Techniques(52), Video Coding and Compression Technologies(42), Advanced Data Compression Techniques(28), Video Surveillance and Tracking Methods(27), Generative Adversarial Networks and Image Synthesis(26)

Publications266 total

Token Compression Meets Compact Vision Transformers: a Survey and Comparative Evaluation for Edge AI
2025
The Reality of Silk: An AR Try-On System for Traditional Chinese Costumes
Lecture notes in computer science·2025
Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks
arXiv (Cornell University)·2025Open Access
Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI
arXiv (Cornell University)·2025Open Access
AIR: Zero-shot Generative Model Adaptation with Iterative Refinement
arXiv (Cornell University)·2025Open Access
Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment
arXiv (Cornell University)·2025Open Access
Text to Image Generation and Editing: A Survey
arXiv (Cornell University)·2025Open Access
Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
arXiv (Cornell University)·2025Open Access
Synth-Align: Improving Trustworthiness in Vision-Language Model with Synthetic Preference Data Alignment
arXiv (Cornell University)·2024Open Access
Urban Air Temperature Prediction using Conditional Diffusion Models
arXiv (Cornell University)·2024Open Access
Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection
arXiv (Cornell University)·2024Open Access
On the Vulnerability of Skip Connections to Model Inversion Attacks
Lecture notes in computer science·2024
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
arXiv (Cornell University)·2024Open Access
Masked Signal Modeling for Plastic Waste Resin Classification
2024· 1 cited
On the Vulnerability of Skip Connections to Model Inversion Attacks
arXiv (Cornell University)·2024Open Access
Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?
arXiv (Cornell University)·2024· 1 citedOpen Access
Model Inversion Robustness: Can Transfer Learning Help?
2024· 5 cited
Multispectral and hyperspectral infrared imaging for plastic waste sorting and recycling
2024
Uncertainty-Aware Pedestrian Crossing Prediction via Reinforcement Learning
IEEE Transactions on Circuits and Systems for Video Technology·2024· 8 cited
Model Inversion Robustness: Can Transfer Learning Help?
arXiv (Cornell University)·2024Open Access
page 1 of 14Next →

Frequent Co-authors

Thanh-Toan Do(11), Vijay Chandrasekhar(6), Antonio Ortega(6), Bernd Girod(5), Yiren Zhou(5), Chau Yuen(5), Tuan Hoang(5), Radek Grzeszczuk(4), Gabriel Takacs(4), Sam S. Tsai(4), Hossein Nejati(4), Jiyan Wu(4), Junliang Chen(4), Yuriy A. Reznik(3), Ramakrishna Vedantham(3), Victor Pomponiu(3), Ngoc-Trung Tran(3), Sibo Song(3), Caimu Tang(3), C.S. Raghavendra(3)