Search Results for author: Shai Mazor

Found 12 papers, 4 papers with code

Towards Models that Can See and Read

no code implementations18 Jan 2023 Roy Ganz, Oren Nuriel, Aviad Aberdam, Yair Kittenplon, Shai Mazor, Ron Litman

Visual Question Answering (VQA) and Image Captioning (CAP), which are among the most popular vision-language tasks, have analogous scene-text versions that require reasoning from the text in the image.

Image Captioning Question Answering +1

Learning Multimodal Affinities for Textual Editing in Images

no code implementations18 Mar 2021 Or Perel, Oron Anschel, Omri Ben-Eliezer, Shai Mazor, Hadar Averbuch-Elor

Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent.

On Calibration of Scene-Text Recognition Models

no code implementations23 Dec 2020 Ron Slossberg, Oron Anschel, Amir Markovitz, Ron Litman, Aviad Aberdam, Shahar Tsiper, Shai Mazor, Jon Wu, R. Manmatha

Although the topic of confidence calibration has been an active research area for the last several decades, the case of structured and sequence prediction calibration has been scarcely explored.

Scene Text Recognition

Can You Read Me Now? Content Aware Rectification using Angle Supervision

no code implementations ECCV 2020 Amir Markovitz, Inbal Lavi, Or Perel, Shai Mazor, Roee Litman

We present CREASE: Content Aware Rectification using Angle Supervision, the first learned method for document rectification that relies on the document's content, the location of the words and specifically their orientation, as hints to assist in the rectification process.

Optical Character Recognition

SCATTER: Selective Context Attentional Scene Text Recognizer

2 code implementations CVPR 2020 Ron Litman, Oron Anschel, Shahar Tsiper, Roee Litman, Shai Mazor, R. Manmatha

The first attention step re-weights visual features from a CNN backbone together with contextual features computed by a BiLSTM layer.

Irregular Text Recognition Scene Text Recognition

ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation

3 code implementations CVPR 2020 Sharon Fogel, Hadar Averbuch-Elor, Sarel Cohen, Shai Mazor, Roee Litman

This is especially true for handwritten text recognition (HTR), where each author has a unique style, unlike printed text, where the variation is smaller by design.

Domain Adaptation Handwriting generation +3

Dynamic Time-Of-Flight

no code implementations CVPR 2017 Michael Schober, Amit Adam, Omer Yair, Shai Mazor, Sebastian Nowozin

Operating in this mode the camera essentially forgets all information previously captured - and performs depth inference from scratch for every frame.

Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo

no code implementations22 Jul 2015 Amit Adam, Christoph Dann, Omer Yair, Shai Mazor, Sebastian Nowozin

We propose a computational model for shape, illumination and albedo inference in a pulsed time-of-flight (TOF) camera.

Cannot find the paper you are looking for? You can Submit a new open access paper.