About

Howdy!

I'm Evonne, a Research Scientist at Meta in Pittsburgh!

My current interests revolve around using computer vision, with an emphasis on multimodal and generative techniques to investigate how humans interact in social settings. I am excited about applying this insight towards enabling machines to engage in social interactions.


In my past, I spent 5 wonderful years as a Ph.D. student in UC Berkeley's EECS program, where I was co-advised by Prof. Trevor Darrell and Prof. Angjoo Kanazawa. And before all that jazz, I was fortunate to have Prof. Kristen Grauman as my research advisor at UT Austin, where I started off working on ego-centric video analysis for ego-pose prediction.


News:

* Graduated from UC Berkeley! Ph.D. in EECS (AI/CV)
* Another year, another round of ASI@ECCV 2024! Website and speaker list coming soon.
* The second annual Artificial Social Intelligence Workshop was accepted at ICCV 2023!
* I will be co-organizing the first Artificial Social Intelligence Workshop at CVPR 2022.
* My art piece 'Penny' has been selected for display on the 3rd floor of Sproul Hall at UC Berkeley!
* I had a fun feature in Women in Computer Vision for the CVPR Daily.
Research

Selected Publications

From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations
E. Ng, J. Romero, T. Bagautdinov, S.Bai,
T. Darrell, A. Kanazawa, A. Richard. 2024

In CVPR 2024

Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion
E. Ng, H. Joo, L. Hu, H. Li, T. Darrell, A. Kanazawa,
S. Ginosar. 2022

In CVPR 2022

Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics
E. Ng, S. Ginosar, T. Darrell, H. Joo. 2021

In CVPR 2021

Art

Gallery

In my free time I do style transfer of pictures irl. It's been a good way to commemorate all the places I've had the opportunity to visit. I've gotten asked if these pieces are AI generated, which I guess is a compliment in this day and age?