|
Shalom!I am a Postdoctoral Researcher at Meta AI (FAIR), working with Yann LeCun. Prior to this, I was a Ph.D. candidate at Tel Aviv University and UC Berkeley, where I was advised by Amir Globerson and Trevor Darrell. My goal is to teach computers to perceive, reason, and act in the world from visual data, using little to no supervision. I've pioneered AI for medical imaging as an AI Research Lead at Zebra Medical Vision (acquired). My research team developed multiple FDA cleared algorithms for automatic analysis of medical images (e.g, [1, 2]). If you are a student interested in collaborating on research projects or looking for advice, please reach out. I am on the 2024-2025 academic job market |
|
|
|
- I was a guest on the TWIML AI podcast where I talked about my recent research.
- I organized the first workshop on Prompting in Vision at CVPR 24'.
- I served as an Assistant Program Chair at NeurIPS 2023.
|
|
|
|
We present EgoPet, a new egocentric video dataset of animals. |
|
We find "Task Vectors", latent activations that can guide models to perform computer vision tasks. |
|
Modeling location uncertainties via stochastic positional embeddings (StoP) improve masked image modeling. |
|
IMProv performs multimodal in-context learning to solve computer vision tasks. |
|
Large Vision Model trained on 420B tokens; exhibits interesting in-context learning capabilities. |
|
Adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification. * Equally contributed. |
|
Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson NeurIPS, 2022 Project Page | Code
Incorporating image level scene structure during training improves video transformers.
Winner of the Ego4D CVPR'22 PNR Temporal Localization Challenge
|
|
Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson CVPR, 2022 Project Page | Code Incorporating objects into transformer layers improves video transformers. |
|
Pretraining transformers to localize potential objects improves object detection. |
|
We introduce Action Graphs, a structure that can better capture the compositional and hierrchical nature of actions. We propose a goal-oriented video synthesis task of *Action Graph to Video* * Equally contributed. |
|
We present a model for Scene Graph to Image generation which is more robust to complex input scene graphs. * Equally contributed. |
|
We predict plausible gestures to go along with someone's speech. * Equally contributed. |
|
We show that recurrent neural networks can be trained to generate text with GANs from scratch and vastly improve the quality of generated sequences compared to a convolutional baseline. * Equally contributed. |
|
|
|
We present a novel architecture used to detect vertebral compression fractures in Chest and Abdomen CT. * Equally advised. |
|
Methods for identifying patients at high risk for osteoporotic fractures are underutilized. We demonstrate it is feasibile to automatically evaluate risk based on routine abdomen or chest computed tomography (CT) scan. |
|
Intracranial hemorrhage (ICH) is among the most critical and timesensitive findings to be detected on Head CT. We present a new architecture designed for optimal triaging of Head CTs, with the goal of decreasing the time from CT acquisition to accurate ICH detection. These results are comparable to previously reported results with smaller number of tagged studies. |
|
Osteoporosis is an underdiagnosed condition despite effective screening modalities. The purpose of this study was to describe a method to simulate lumbar DEXA scores from routinely acquired CT studies using a machine-learning algorithm. |
|
Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality worldwide. We apply deep learning algorithm to detect those at risk. |
|
|
The presence of a vertebral compression fracture is highly indicative of osteoporosis and represents the single most robust predictor for development of a second osteoporotic fracture in the spine or elsewhere. We present an automated method for detecting spine compression fractures in Computed Tomography (CT) scans. |
|
|
|
Systems and methods for automated detection of visual objects in medical images. US Patent 11,776,243 Cross modality training of machine learning models. US Patent 11,587,228. Identification of a contrast phase depicted in a medical image. US Patent 11,727,087 |
|
|
|
Danny Tran Arya Bakhtiar Alberto Hojel |