People

Tal Hassner

Applied Research Lead

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

Related Links

GitHub

Latest Publications

CVPR - June 22, 2021

A Multiplexed Network for End-to-End, Multilingual OCR

Jing Huang, Guan Pang, Rama Kovvuri, Mandy Toh, Kevin J Liang, Praveen Krishnan, Xi Yin, Tal Hassner

June 18, 2021

TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

Amanpreet Singh, Guan Pang, Mandy Toh, Jing Huang, Wojciech Galuba, Tal Hassner

ECCV - August 23, 2020

Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting

Minghui Liao, Guan Pang, Jing Huang, Tal Hassner, Xiang Bai

ICML - July 13, 2020

LEEP: A New Measure to Evaluate Transferability of Learned Representations

Cuong V. Nguyen, Tal Hassner, Matthias Seeger, Cedric Archambeau

ICCV - October 27, 2019

Transferability and Hardness of Supervised Classification Tasks

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