Ariel Ephrat

Software Engineer, Perception Team, Google Research
Email: arielephrat_at_google.com
Google Scholar   |    Linkedin   |    Github
About Me
I am a Software Engineer on the Perception Team at Google Research.

I completed my PhD in 2018, working with Prof. Shmuel Peleg as part of the HUJI Computer Vision Lab. My main research interests are applications of computer vision using deep learning, particularly in the area of sight and sound-based video analysis.
Publications
Lumiere: A Space-Time Diffusion Model for Video Generation
O. Bar-Tal, H. Chefer, O. Tov, C. Herrmann, R. Paiss, S. Zada,
A. Ephrat, J. Hur, Y. Li, T. Michaeli, O. Wang, D. Sun, T. Dekel, I. Mosseri
arXiv 2024
arXiv   |    webpage   |    video   
Teaching CLIP to Count to Ten
R. Paiss, A. Ephrat, O. Tov, S. Zada, I. Mosseri, M. Irani, T. Dekel
ICCV 2023
arXiv   |    webpage   
SpeedNet: Learning the Speediness in Videos
S. Benaim, A. Ephrat, O. Lang, I. Mosseri, W.T. Freeman, M. Rubinstein, M. Irani, T. Dekel
CVPR 2020, oral
arXiv   |    webpage   
Neural Separation of Observed and Unobserved Distributions
T. Halperin, A. Ephrat, Y. Hoshen
ICML 2019
arXiv   
Dynamic Temporal Alignment of Speech to Lips
T. Halperin*, A. Ephrat*, S. Peleg
[* equal contribution]
ICASSP 2019
arXiv   |    video   |    code  
Looking to Listen at the Cocktail Party:
A Speaker-Independent Audio-Visual Model for Speech Separation

A. Ephrat, I. Mosseri, O. Lang, T. Dekel, K. Wilson, A. Hassidim, W.T. Freeman, M. Rubinstein
SIGGRAPH 2018
arXiv   |    webpage   |    video   |    Google Research Blog   
Seeing Through Noise:
Visually Driven Speaker Separation and Enhancement

A. Gabbay, A. Ephrat, T. Halperin and S. Peleg
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
arXiv   |    webpage   |    video   |    code
Patient-specific and global convolutional neural networks
for robust automatic liver tumor delineation in follow-up CT studies

R. Vivanti, L. Joskowicz, N. Lev Cohain, A. Ephrat and J. Sosna
Medical & Biological Engineering & Computing, March 2018
article
Improved Speech Reconstruction from Silent Video
A. Ephrat*, T. Halperin* and S. Peleg
[* equal contribution]
ICCV 2017 Workshop on Computer Vision for Audio-Visual Media
arXiv   |    webpage   |    video   |    code
Vid2speech: Speech Reconstruction from Silent Video
A. Ephrat and S. Peleg
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017
pdf   |    webpage   |    code
Compact CNN for Indexing Egocentric Videos
Y. Poleg, A. Ephrat, C. Arora and S. Peleg
IEEE Winter Conference on Applications of Computer Vision (WACV), 2016
pdf   |    webpage
Automatic Liver Tumor Segmentation in Follow-Up CT Scans
R. Vivanti, A. Ephrat, L. Joskowicz, O.A. Karaaslan, N. Lev Cohain and J. Sosna
Proc. International Workshop on Patch-based Techniques in Medical Imaging, MICCAI, 2015
pdf
Teaching
HUJI — Teaching Assistant, Digital Image Processing, 2017-18
HUJI — Teaching Assistant, Undergraduate Engineering Projects and Workshop, 2015-18
Work
Google Research — Software Engineer, 2018 - Now
Google Research — Software Engineering Intern, 2017
Google — Software Engineering Intern, 2016
Here a Story — Co-founder and Web Developer, 2013–2014