My doctoral research focuses on automatic haptic generation for multimedia content. I aim to build haptic-centered multimodal datasets. Based on these datasets, I am interested in developing joint multimodal AI models for audiovisual content understanding and haptic rendering, with the goal of enabling practical haptic applications.
Psychophysics-based tactile rendering for realistic virtual environments
Time-frequency analysis, filtering, and feature extraction for haptic/audio signals
Utilizing multimodal models for audiovisual understanding and haptic content creation
Dataset construction, statistical analysis, and experimental data processing
User studies, psychophysical experiments, and subjective quality assessment
AI-integrated real-time systems and interactive application development