activity
20192026
most citedLearning to Listen: Modeling Non-Deterministic Dyadic Facial Motion

3 citations · 3 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2026

DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction

Yufu Wang, Evonne Ng, Soyong Shin +8

We present DuoMo, a generative method that recovers human motion in world-space coordinates from unconstrained videos with noisy or incomplete observations. Reconstructing such mot…

cs.CV2026

SARAH: Spatially Aware Real-time Agentic Humans

Evonne Ng, Siwei Zhang, Zhang Chen +2

As embodied agents become central to VR, telepresence, and digital human applications, their motion must go beyond speech-aligned gestures: agents should turn toward users, respond…

cs.CV20223 cited

Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion

Evonne Ng, Hanbyul Joo, Liwen Hu +4

We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of…

cs.CV2020

Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics

Evonne Ng, Shiry Ginosar, Trevor Darrell +1

We propose a novel learned deep prior of body motion for 3D hand shape synthesis and estimation in the domain of conversational gestures. Our model builds upon the insight that bod…

cs.CV2019

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

Evonne Ng, Donglai Xiang, Hanbyul Joo +1

The body pose of a person wearing a camera is of great interest for applications in augmented reality, healthcare, and robotics, yet much of the person's body is out of view for a…