Ramin Zabih

Google (United States) — United States

Computer Science · Physical Sciences

41h-index24.8kcitations165works2.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image and Video Retrieval Techniques(41), Advanced Vision and Imaging(40), Medical Image Segmentation Techniques(26), Advanced Neural Network Applications(17), Image Retrieval and Classification Techniques(17)

Publications165 total

Improving realistic semi-supervised learning with doubly robust estimation
arXiv (Cornell University)·2025· 1 citedOpen Access
DreamWalk: Style Space Exploration Using Diffusion Guidance
Lecture notes in computer science·2025
DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization
PubMed·2024· 1 citedOpen Access
Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
arXiv (Cornell University)·2024· 1 citedOpen Access
DreamWalk: Style Space Exploration using Diffusion Guidance
arXiv (Cornell University)·2024Open Access
MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection
arXiv (Cornell University)·2024· 7 citedOpen Access
Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
2024· 6 cited
A Stable and Efficient Covariate-Balancing Estimator for Causal Survival Effects
arXiv (Cornell University)·2023Open Access
Test-Time Distribution Normalization for Contrastively Learned Vision-language Models
arXiv (Cornell University)·2023· 1 citedOpen Access
Unsupervised Text Deidentification
arXiv (Cornell University)·2022Open Access
Dimensions of Motion: Monocular Prediction through Flow Subspaces
2022· 6 cited
Pyramid Adversarial Training Improves ViT Performance
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 38 cited
Unsupervised Text Deidentification
2022· 3 citedOpen Access
Dimensions of Motion: Learning to Predict a Subspace of Optical Flow from a Single Image.
arXiv (Cornell University)·2021Open Access
Dimensions of Motion: Monocular Prediction through Flow Subspaces
arXiv (Cornell University)·2021Open Access
Pyramid Adversarial Training Improves ViT Performance
arXiv (Cornell University)·2021· 4 citedOpen Access
Deep survival analysis with longitudinal X-rays for COVID-19
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 7 cited
Deep survival analysis with longitudinal X-rays for COVID-19
arXiv (Cornell University)·2021Open Access
AutoFlow: Learning a Better Training Set for Optical Flow
2021· 95 cited
OCONet: Image Extrapolation by Object Completion
2021· 20 cited
page 1 of 9Next →

Frequent Co-authors

Vladimir Kolmogorov(10), Olga Veksler(8), Charles Herrmann(5), Yuri Boykov(4), Jing Huang(4), Daniel Scharstein(3), Richard Szeliski(3), Greg Pass(3), Justin Miller(3), Ce Liu(3), Xian Wu(3), Licia K. Gaber-Baylis(3), Akshay U. Bhat(3), Peter Fleischut(3), Richard Strong Bowen(3), S. Ravi Kumar(2), Mandar Mitra(2), Carsten Rother(2), Kevin Mai(2), V. Kettnaker(2)