MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition | allainews.com

April 23, 2024, 4:46 a.m. | Felix M. Schmitt-Koopmann, Elaine M. Huang, Hans-Peter Hutter, Thilo Stadelmann, Alireza Darvishy

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.13667v1 Announce Type: new
Abstract: Printed mathematical expression recognition (MER) models are usually trained and tested using LaTeX-generated mathematical expressions (MEs) as input and the LaTeX source code as ground truth. As the same ME can be generated by various different LaTeX source codes, this leads to unwanted variations in the ground truth data that bias test performance results and hinder efficient learning. In addition, the use of only one font to generate the MEs heavily limits the generalization of …

abstract arxiv code cs.ai cs.cv data data-centric generated latex leads recognition truth type

More from arxiv.org / cs.CV updates on arXiv.org

Validating polyp and instrument segmentation methods in colonoscopy through Medico 2020 and MedAI 2021 Challenges an hour ago | arxiv.org

abstract analysis arxiv challenges +11

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder an hour ago | arxiv.org

abstract arxiv become challenge +17

Yuille-Poggio's Flow and Global Minimizer of Polynomials through Convexification by Heat Evolution an hour ago | arxiv.org

abstract algorithm arxiv cs.cv +9

Motion State: A New Benchmark Multiple Object Tracking an hour ago | arxiv.org

abstract analysis arxiv benchmark +18

Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering an hour ago | arxiv.org

arxiv convolutional cs.ai cs.cv +10

A Unified Approach for Text- and Image-guided 4D Scene Generation an hour ago | arxiv.org

3d scene generation abstract arxiv cs.cv +17

From Pixels to Titles: Video Game Identification by Screenshots using Convolutional Neural Networks an hour ago | arxiv.org

abstract architectures arxiv cnn +24

Amodal Optical Flow an hour ago | arxiv.org

arxiv cs.ai cs.cv cs.ro +4

Interpretable Geoscience Artificial Intelligence (XGeoS-AI): Application to Demystify Image Recognition an hour ago | arxiv.org

abstract ai models application artificial +21

Lead Developer (AI)

@ Cere Network | San Francisco, US

View on ai-jobs.net

Research Engineer

@ Allora Labs | Remote

View on ai-jobs.net

Ecosystem Manager

@ Allora Labs | Remote

View on ai-jobs.net

Founding AI Engineer, Agents

@ Occam AI | New York

View on ai-jobs.net

AI Engineer Intern, Agents

@ Occam AI | US

View on ai-jobs.net

AI Research Scientist

@ Vara | Berlin, Germany and Remote

View on ai-jobs.net