Fiona Ryan

Fiona sitting on steps

Hi, I'm Fiona.

I am a Computer Science PhD student at the Georgia Institute of Technology, where I am advised by James Rehg and Judy Hoffman within the School of Interactive Computing. My research interests are in computer vision & perception for understanding human behavior. I am excited about developing video and multimodal recognition models that understand people and the way they interact with each other and the world around them. I am grateful to be supported by an NSF Graduate Research Fellowship.

I graduated from Indiana University in 2020 with a B.S. in Computer Science and a B.M. in Music Performance. At IU, I did research in the Music Informatics Lab and Computer Vision Lab and developed an interest in using AI for modeling naturalistic behaviors - from practicing an instrument (and making mistakes), to interacting and conversing with other people. Currently, I'm a research intern at Adobe working on multimodal video understanding. Previously, I interned at Meta working on multimodal models for conversation behavior, and Google (x2) working on medical imaging and scene understanding for Nest Cams.

News

July 2024 - Our paper on audiovisual gaze forecasting, led by my labmate Bolin Lai, was accepted to ECCV 2024!

May 2024 - Interning at Adobe Research this summer! 🌉 🎬

April 2024 - Modeling Multimodal Social Interactions (led by my labmate Sangmin Lee) and Ego-Exo4D were accepted to CVPR 2024 for oral presentation!

December 2023 - Check out Ego-Exo4D, a multi-institution dataset effort that captures simultaneous egocentric and exocentric views of human activities!

February 2023 - Our paper Egocentric Auditory Attention Localization in Conversations was accepted to CVPR 2023! Check out the project page.

May 2022 - Excited to be interning at Meta Reality Labs Research this summer!

April 2022 - I was awarded the National Science Foundation Graduate Research Fellowship!

February 2022 - Ego4D was accepted to CVPR 2022!

View all

October 2021 - Introducing Ego4D, a massive, international egocentric dataset and benchmark effort! Glad to have been a part of the social benchmark team and to have led the data collection effort at Georgia Tech.

July 2021 - Our paper Big Self-Supervised Models Advance Medical Image Classifications was accepted to ICCV 2021!

August 2020 - I started my PhD in Computer Science at Georgia Tech

May 2020 - I am interning at Google this summer on the Dermatology team

May 2020 - I graduated from Indiana University with my B.S. in Computer Science and B.M. in Clarinet Performance

Papers

Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation
Bolin Lai, Fiona Ryan, Wenqi Jia, Miao Liu*, James M. Rehg*
ECCV 2024
[paper] [website] [code]

Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations
Sangmin Lee, Bolin Lai, Fiona Ryan, Bikram Boote, James M. Rehg
CVPR 2024 (oral)
[paper]

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman et al. [including Fiona Ryan]
CVPR 2024 (oral)
[paper] [website]

Egocentric Auditory Attention Localization in Conversations
Fiona Ryan, Hao Jiang, Abhinav Shukla, James M. Rehg, Vamsi Krishna Ithapu
CVPR 2023
[paper] [website]

Robust and Data-Efficient Generalization of Self-Supervised Machine Learning for Diagnostic Imaging
Shekoofeh Azizi et al. [including Fiona Ryan]
Nature Biomedical Engineering 2023
[paper]

Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
Bolin Lai*, Hongxin Zhang*, Miao Liu*, Aryan Pariani*, Fiona Ryan, Wenqi Jia, Shirley Anugrah Hayati, James M. Rehg, Diyi Yang
ACL Findings 2023
[paper] [website]

In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
Bolin Lai, Miao Liu, Fiona Ryan, James M Rehg
BMVC 2022 (spotlight, Best Student Paper Award)
[paper] [website] [code]

Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman et al. [including Fiona Ryan*]
CVPR 2022 (Best Paper Award Finalist)
[paper] [website]

Big Self-Supervised Models Advance Medical Image Classification
Shekoofeh Azizi, Basil Mustafa, Fiona Ryan, Zachary Beaver, Jan Freyberg, Jonathan Deaton, Aaron Loh, Alan Karthikesalingam, Simon Kornblith, Ting Chen, Vivek Natarajan, Mohammad Norouzi
ICCV 2021
[paper]

Offline Score Alignment For Realistic Music Practice
Yucong Jiang, Fiona Ryan, David Cartledge, Christopher Raphael
Sound and Music Computing Conference (SMC) 2019
[paper]