# ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX

arXiv: https://arxiv.org/abs/2105.14426 · HTML: https://mlsanity.com/paper/2105.14426/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 30 May 2021.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [Context Encoding for Semantic Segmentation](https://mlsanity.com/paper/1803.08904/) (2018)
- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [TableBank: A Benchmark Dataset for Table Detection and Recognition](https://mlsanity.com/paper/1903.01949/) (2019)
- [Gradient Centralization: A New Optimization Technique for Deep Neural Networks](https://mlsanity.com/paper/2004.01461/) (2020)
- [Image-to-Markup Generation with Coarse-to-Fine Attention](https://mlsanity.com/paper/1609.04938/) (2016)
- [MASTER: Multi-Aspect Non-local Network for Scene Text Recognition](https://mlsanity.com/paper/1910.02562/) (2019)
- [A Survey on Open Information Extraction](https://mlsanity.com/paper/1806.05599/) (2018)
- [Extracting Scientific Figures with Distantly Supervised Neural Networks](https://mlsanity.com/paper/1804.02445/) (2018)
- [2D Attentional Irregular Scene Text Recognizer](https://mlsanity.com/paper/1906.05708/) (2019)
- [PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex](https://mlsanity.com/paper/2105.01846/) (2021)
- [Automated Early Leaderboard Generation From Comparative Tables](https://mlsanity.com/paper/1802.04538/) (2018)
- [Scene Text Recognition via Transformer](https://mlsanity.com/paper/2003.08077/) (2020)
- [SkILL - a Stochastic Inductive Logic Learner](https://mlsanity.com/paper/1506.00893/) (2015)

## Built on by (most cited first, 9 of 9)

- [TableFormer: Table Structure Understanding with Transformers](https://mlsanity.com/paper/2203.01017/) (2022)
- [OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models](https://mlsanity.com/paper/2502.16161/) (2025)
- [An End-to-End Multi-Task Learning Model for Image-based Table Recognition](https://mlsanity.com/paper/2303.08648/) (2023)
- [Rethinking Image-based Table Recognition Using Weakly Supervised Methods](https://mlsanity.com/paper/2303.07641/) (2023)
- [PixT3: Pixel-based Table-To-Text Generation](https://mlsanity.com/paper/2311.09808/) (2023)
- [TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content](https://mlsanity.com/paper/2404.10305/) (2024)
- [Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition](https://mlsanity.com/paper/2404.13268/) (2024)
- [Hierarchical Modeling Approach to Fast and Accurate Table Recognition](https://mlsanity.com/paper/2512.21083/) (2025)
- [TableNet A Large-Scale Table Dataset with LLM-Powered Autonomous](https://mlsanity.com/paper/2604.13041/) (2026)

## Abstract (arXiv)

Tables present important information concisely in many scientific documents. Visual features like mathematical symbols, equations, and spanning cells make structure and content extraction from tables embedded in research documents difficult. This paper discusses the dataset, tasks, participants' methods, and results of the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX. Specifically, the task of the competition is to convert a tabular image to its corresponding LaTeX source code. We proposed two subtasks. In Subtask 1, we ask the participants to reconstruct the LaTeX structure code from an image. In Subtask 2, we ask the participants to reconstruct the LaTeX content code from an image. This report describes the datasets and ground truth specification, details the performance evaluation metrics used, presents the final results, and summarizes the participating methods. Submission by team VCGroup got the highest Exact Match accuracy score of 74% for Subtask 1 and 55% for Subtask 2, beating previous baselines by 5% and 12%, respectively. Although improvements can still be made to the recognition capabilities of models, this competition contributes to the development of fully automated table recognition systems by challenging practitioners to solve problems under specific constraints and sharing their approaches; the platform will remain available for post-challenge submissions at https://competitions.codalab.org/competitions/26979 .