awesome-table-structure-recognition
awesome-table-structure-recognition copied to clipboard
A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.
A Curated List of Awesome Table Structure Recognition (TSR) Research.
This is a curated list of awesome table structure recognition (TSR) research.Including sota models, influential papers, popular datasets and open-source codes. Continuously updating.
Popular Datasets
| Name | Tables | Data Type | TD | TSR | TCR | Year |
|---|---|---|---|---|---|---|
| ICDAR2013 | 156 | Digital | √ | √ | √ | 2013 |
| SciTSR | 15K | Digital | × | √ | √ | 2019 |
| TableBank | 417K | Digital | √ | × | × | 2020 |
| TableBank | 145K | Digital | × | √ | × | 2020 |
| PubTabNet | 1M+ | Digital | × | √ | √ | 2020 |
| PubTables-1M | 1M+ | Digital | √ | √ | × | 2021 |
| FinbTabNet | 91596 | Digital | × | √ | √ | 2021 |
| WTW | 14581 | Both | × | √ | × | 2021 |
| SynthTabNet | 600K | Digital | × | √ | √ | 2022 |
| TabRecSet | 38177 | Both | √ | √ | √ | 2023 |
| iFLYTAB | 12104 | Both | √ | √ | × | 2023 |
TD means Table Detection
TSR means Table Structure Recognition
TCD means Table Content Recognition
Both means including both digital and physical data
SOTA Models
| Method Type | Method Name | Citation Count | Year | Venue | Open Source |
|---|---|---|---|---|---|
| Bottom-up | Res2TIM | 37 | 2019 | ICDAR | √ |
| CascadeTabNet | 182 | 2020 | CVPR | √ | |
| TabStruct-Net | 87 | 2020 | ECCV | ||
| LGPMA | 63 | 2021 | ICDAR | √ | |
| Cycle-CenterNet | 39 | 2021 | ICCV | ||
| TGRNet | 42 | 2021 | ICCV | √ | |
| FLAG-NET | 30 | 2021 | MM | ||
| GTE | 116 | 2021 | WACV | ||
| NCGM | 25 | 2022 | CVPR | ||
| LORE | 7 | 2023 | AAAI | ||
| Image2Markup | EDD | 171 | 2020 | ECCV | √ |
| TableMaster | 34 | 2021 | ICDAR | √ | |
| TableFormer | 41 | 2022 | CVPR | ||
| VAST | 12 | 2023 | CVPR | ||
| UniTable | 2024 | √ | |||
| OminParser | 2024 | CVPR | |||
| Split-and-Merge Based | SPLERGE | 91 | 2019 | ICDAR | √ |
| SEM | 40 | 2022 | PR | √ | |
| TSRFormer | 20 | 2022 | MM | ||
| RobusTabNet | 32 | 2023 | PR | ||
| SEMv2 | 3 | 2024 | PR | √ | |
| Others | TableNet | 188 | 2019 | ICDAR | √ |
| DETR | 60 | 2022 | CVPR | √ | |
| TRACE | 3 | 2023 | ICDAR | √ |
Influential Papers
CVPR 2024
- OMNIPARSER: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition-Paper
PR 2024
CVPR 2023
- Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling-Paper
AAAI 2023
- LORE: Logical Location Regression Network for Table Structure Recognition=Paper
PR 2023
- Robust Table Detection and Structure Recognition from Heterogeneous Document Images-Paper
- Scene table structure recognition with segmentation collaboration and alignment-Paper
ACL 2023
- TableVLM: Multi-modal Pre-training for Table Structure Recognition-Paper
ICDAR 2023
- TRACE: Table Reconstruction Aligned to Corner and Edges-Paper
- Aligning benchmark datasets for table structure recognition-Paper
- Optimized Table Tokenization for Table Structure Recognition-Paper
CVPR 2022
- Neural Collaborative Graph Machines for Table Structure Recognition-Paper
- TableFormer: Table Structure Understanding with Transformers-Paper
- PubTables-1M: Towards comprehensive table extraction from unstructured documents-Paper, code
PR 2022
- Split, Embed and Merge: An accurate table structure recognizer-Paper
WACV 2022
- Visual Understanding of Complex Table Structures from Document Images-Paper
MM 2022
- TSRFormer: Table Structure Recognition with Transformers-Paper
ICCV 2021
- Parsing Table Structures in the Wild-Paper
- TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition-Paper, code
WACV 2021
- Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context-Paper
MM 2021
- Show, Read and Reason: Table Structure Recognition with Flexible Context Aggregator-Paper
ICDAR 2021
- LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment-Paper
- PINGAN-VCGROUP’S SOLUTION FOR ICDAR 2021 COMPETITION ON SCIENTIFIC LITERATURE PARSING TASK B:TABLE RECOGNITION TO HTML-Paper, code
- TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables-Paper
CVPRW 2020
- CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents-Paper, code
ECCV 2020
- Image-based table recognition: data, model, and evaluation-Paper
- Table Structure Recognition using Top-Down and Bottom-Up Cues-Paper
LERC 2020
- TableBank: Table Benchmark for Image-based Table Detection and Recognition-Paper
ICDAR 2019
- Challenges in end-to-end neural scientific table recognition-Paper
- Deep Splitting and Merging for Table Structure Decomposition-Paper
- DeepTabStR: Deep Learning based Table Structure Recognition-Paper
- Rethinking Table Recognition using Graph Neural Networks-Paper
- ReS2TIM: Reconstruct Syntactic Structures from Table Images-Paper
- TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images-Paper,code,model
Others
2024
- UniTable: Towards a Unified Framework for Table Structure Recognition via Self-Supervised Pretraining-Paper
2023
2021
- Multi-Type-TD-TSR -- Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations-Paper, code