SOTAVerified

Table Recognition

Table recognition refers to the process of automatically identifying and extracting tabular structures from unstructured data sources such as text documents, images, or scanned documents. The goal of table recognition is to accurately detect the presence of tables within the data and extract their contents, including rows, columns, headers, and cell values.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 50 papers

TitleStatusHype
Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables—0
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language ModelsCode0
Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain ReasonerCode1
Benchmarking Table Comprehension In The Wild—0
See then Tell: Enhancing Key Information Extraction with Vision Grounding—0
PdfTable: A Unified Toolkit for Deep Learning-Based Table ExtractionCode0
VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction—0
The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses—0
Multi-Cell Decoder and Mutual Learning for Table Structure and Character RecognitionCode1
Synthesizing Realistic Data for Table RecognitionCode0
TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content—0
OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table RecognitionCode0
UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised PretrainingCode4
Enhancement of Bengali OCR by Specialized Models and Advanced Techniques for Diverse Document Types—0
OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table RecognitionCode0
A Review On Table Recognition Based On Deep LearningCode0
High-Performance Transformers for Table Structure Recognition Need Early ConvolutionsCode2
A large-scale dataset for end-to-end table recognition in the wildCode1
An End-to-End Multi-Task Learning Model for Image-based Table RecognitionCode1
Rethinking Image-based Table Recognition Using Weakly Supervised MethodsCode1
LORE: Logical Location Regression Network for Table Structure RecognitionCode0
Aligning benchmark datasets for table structure recognitionCode4
Deep learning for table detection and structure recognition: A surveyCode1
RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild—0
PP-StructureV2: A Stronger Document Analysis SystemCode0
Show:102550
← PrevPage 1 of 2Next →
All datasetsPubTabNetTable Recognition Challenge mini-testTable Recognition Challenge testICDAR2013 table structure recognitionWTW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TSRFormerTEDS-Struct97.5—Unverified
2RTSRTEDS-Struct97—Unverified
3MuTabNetTEDS (all samples)96.87—Unverified
4TableMasterTEDS (all samples)96.76—Unverified
5Multi-Task Learning ModelTEDS (all samples)96.67—Unverified
6ConvStemTEDS (all samples)96.53—Unverified
7SLANetTEDS (all samples)96.3—Unverified
8TRUSTTEDS (all samples)96.2—Unverified
9NCGMTEDS (all samples)95.4—Unverified
10LGPMATEDS (all samples)94.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Re0TEDS (all samples)95.66—Unverified
2VCGroupTEDS (all samples)95.04—Unverified
3Habitat-WebTEDS (all samples)89.97—Unverified
4EDDTEDS (all samples)89.97—Unverified
#ModelMetricClaimedVerifiedStatus
1Habitat-WebTEDS (all samples)89.18—Unverified
2EDDTEDS (all samples)89.18—Unverified
#ModelMetricClaimedVerifiedStatus
1Proposed System (With post- processing)F-Measure95.46—Unverified
#ModelMetricClaimedVerifiedStatus
1StrucTexTv2 (small)F178.9—Unverified