,

Tal Hassner

Tal is an Applied Research Lead at Facebook AI. Prior to that, he was a principal scientist at Amazon AWS. He is also affiliated with The Open University of Israel, Department of Mathematics and Computer Science. Tal's work is mainly related to computer vision, machine learning, statistical pattern recognition, and computer graphics. Much of his work relates to face images and videos, including face recognition, attribute prediction, face alignment, and 3D reconstruction of face shapes. Tal also worked on problems related to human action recognition in videos, dense correspondence estimation, feature representation and matching, and text image processing (OCR).

Tal's Publications

April 07, 2020

RESEARCH

COMPUTER VISION

Transferability and Hardness of Supervised Classification Tasks

We propose a novel approach for estimating the difficulty and transferability of supervised classification tasks. Unlike previous work, our approach is solution agnostic and does not require or assume trained models. Instead, we estimate these…

Anh T. Tran, Cuong V. Nguyen, Tal Hassner,

April 07, 2020