# Table Structure Recognition with Conditional Attention

arXiv: https://arxiv.org/abs/2203.03819 · HTML: https://mlsanity.com/paper/2203.03819/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 8 Mar 2022.

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

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [MultiModalQA: Complex Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2104.06039/) (2021)
- [Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context](https://mlsanity.com/paper/2005.00589/) (2020)
- [TUTA: Tree-based Transformers for Generally Structured Table Pre-training](https://mlsanity.com/paper/2010.12537/) (2020)
- [CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents](https://mlsanity.com/paper/2004.12629/) (2020)
- [Complicated Table Structure Recognition](https://mlsanity.com/paper/1908.04729/) (2019)
- [TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images](https://mlsanity.com/paper/2001.01469/) (2020)
- [Table Structure Recognition using Top-Down and Bottom-Up Cues](https://mlsanity.com/paper/2010.04565/) (2020)
- [LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment](https://mlsanity.com/paper/2105.06224/) (2021)
- [PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System](https://mlsanity.com/paper/2109.03144/) (2021)
- [CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images](https://mlsanity.com/paper/2008.10831/) (2020)
- [GFTE: Graph-based Financial Table Extraction](https://mlsanity.com/paper/2003.07560/) (2020)
- [TableQA: Question Answering on Tabular Data](https://mlsanity.com/paper/1705.06504/) (2017)

## Built on by (most cited first, 6 of 6)

- [Deep learning for table detection and structure recognition: A survey](https://mlsanity.com/paper/2211.08469/) (2022)
- [SEMv3: A Fast and Robust Approach to Table Separation Line Detection](https://mlsanity.com/paper/2405.11862/) (2024)
- [SPRINT: Script-agnostic Structure Recognition in Tables](https://mlsanity.com/paper/2503.11932/) (2025)
- [Handling big tabular data of ICT supply chains: a multi-task, machine-interpretable approach](https://mlsanity.com/paper/2208.06031/) (2022)
- [Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition](https://mlsanity.com/paper/2211.02128/) (2022)
- [TableCenterNet: A one-stage network for table structure recognition](https://mlsanity.com/paper/2504.17522/) (2025)

## Abstract (arXiv)

Tabular data in digital documents is widely used to express compact and important information for readers. However, it is challenging to parse tables from unstructured digital documents, such as PDFs and images, into machine-readable format because of the complexity of table structures and the missing of meta-information. Table Structure Recognition (TSR) problem aims to recognize the structure of a table and transform the unstructured tables into a structured and machine-readable format so that the tabular data can be further analysed by the down-stream tasks, such as semantic modeling and information retrieval. In this study, we hypothesize that a complicated table structure can be represented by a graph whose vertices and edges represent the cells and association between cells, respectively. Then we define the table structure recognition problem as a cell association classification problem and propose a conditional attention network (CATT-Net). The experimental results demonstrate the superiority of our proposed method over the state-of-the-art methods on various datasets. Besides, we investigate whether the alignment of a cell bounding box or a text-focused approach has more impact on the model performance. Due to the lack of public dataset annotations based on these two approaches, we further annotate the ICDAR2013 dataset providing both types of bounding boxes, which can be a new benchmark dataset for evaluating the methods in this field. Experimental results show that the alignment of a cell bounding box can help improve the Micro-averaged F1 score from 0.915 to 0.963, and the Macro-average F1 score from 0.787 to 0.923.