Presentation / Installation
GestureDiffuCLIP: Gesture Diffusion Model With CLIP Latents
DescriptionWe introduce GestureDiffuCLIP, a CLIP-guided, co-speech gesture synthesis system that creates stylized gestures in harmony with speech semantics and rhythm using arbitrary style prompts. Our highly adaptable system supports style prompts in the form of short texts, motion sequences, or video clips and provides body part-specific style control.
Event Type
Technical Paper
TimeMonday, 7 August 20232pm - 2:11pm PDT
LocationPetree Hall C
ACM Digital Library
Technical Papers pdfs
Session Time & Location
Research & Education
Livestreamed
Recorded
Animation/Simulation
Artificial Intelligence/Machine Learning
FC
FCS
V
VS
EFC