Research archive / 2019–2026
Publications
and research.
Explore the methods, evidence, presentations, and citations behind each research output.
16 outputs
Published research
Through Van Gogh’s Eyes: Global Style Transfer with Diffusion Model
A broader artist style distribution guides diffusion image synthesis.
Read paper page
Expanding Multilingual Co-Speech Interaction: The Impact of Enhanced Gesture Units in Text-to-Gesture Synthesis for Digital Humans
More gesture variety supports multilingual digital-human interaction.
Read paper page
RIDGE: Rule‐Infused Deep Learning for Realistic Co‐Speech Gesture Generation
High-confidence rules and learned similarity retrieve semantically aligned gestures.
Read paper page
A Retrieval‐Augmented Generation System for Accurate and Contextual Historical Analysis: AI‐Agent for the Annals of the Joseon Dynasty
Article-aware retrieval grounds answers in the Annals of the Joseon Dynasty.
Read paper page
ASAP for multi-outputs: auto-generating storyboard and pre-visualization with virtual actors based on screenplay
A screenplay becomes storyboards, animated previsualization, and immersive scenes.
Read paper pageRAG based AI-Agent for Contextualized Analysis of High-Density Historical Records: Application to the Annals of the Joseon Dynasty
An embodied agent makes historical source retrieval conversational.
Read paper page
LUFA: Lightweight Upper-Face Animation for VR/MR Avatars
Lightweight upper-face animation for VR and MR avatars.
Read paper page
Enhancing doctor‐patient communication in surgical explanations: Designing effective facial expressions and gestures for animated physician characters
Expression and gesture support surgical explanations by animated physicians.
Read paper page
Improving Co-speech gesture rule-map generation via wild pose matching with gesture units.
Contrastive matching turns noisy video poses into a richer gesture rule map.
Read paper pageASAP: Auto-generating Storyboard and Previz
A live demonstration of screenplay-driven virtual actors.
Read paper page
No-code Digital Human for Conversational Behavior
No-code conversation flows coordinate digital-human behavior.
Read paper page
Silhouettes from Real Objects Enable Realistic Interactions with a Virtual Human in Mobile Augmented Reality
Real-object silhouettes give virtual humans spatial context in mobile AR.
Read paper pageASAP: Auto-generating Storyboard And Previz with Virtual Humans
An early ASAP tool turns script structure into animated previews.
Read paper page
Auto-generating Virtual Human Behavior by Understanding User Contexts
Natural-language context activates grounded virtual-human actions.
Read paper page
Automatic text‐to‐gesture rule generation for embodied conversational agents
Automatically mined rules reduce manual co-speech gesture authoring.
Read paper page
Design of Seamless Multi-modal Interaction Framework for Intelligent Virtual Agents in Wearable Mixed Reality Environment
A modular virtual guide combines speech, gaze, and spatial context in wearable MR.
Read paper page01 outputs