mlsanityData to 14 Oct 2026

FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers

arXiv 2605.22422 ↗First posted 21 May 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding by combining (i) a lightweight Tiny Recursive Module (TRM) for global reasoning and (ii) axial 1D Transformer encoders that capture long-range dependencies along rows and columns. The model predicts row/column counts, header rows, and separators to construct a grid, then infers rowspan/colspan using ROI-aligned cell features. Across four benchmarks (PubTabNet, FinTabNet, PubTables-1M, and SciTSR), FastTab achieves competitive structure recovery performance while operating at low-latency inference. We further study robustness under pixel-level anonymisation and show an extension to curved separators for camera-captured documents. The source code will be made publicly available at https://github.com/hamdilaziz/FastTab .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

26 of 38 references.

References · 26

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  2. 2021OCR-free Document Understanding Transformercited by 407
  3. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
  4. 2019Image-based table recognition: data, model, and evaluationcited by 237
  5. 2020Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Contextcited by 147
  6. 2021PubTables-1M: Towards comprehensive table extraction from unstructured documentscited by 126
  7. 2022TableFormer: Table Structure Understanding with Transformerscited by 94
  8. 2019Complicated Table Structure Recognitioncited by 92
  9. 2024OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognitioncited by 74
  10. 2020TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Imagescited by 69
  11. 2021LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignmentcited by 46
  12. 2021Split, embed and merge: An accurate table structure recognizercited by 42
14 more
  1. 2023Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modelingcited by 41
  2. 2021PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTMLcited by 39
  3. 2023Optimized Table Tokenization for Table Structure Recognitioncited by 34
  4. 2021Neural Collaborative Graph Machines for Table Structure Recognitioncited by 30
  5. 2021TGRNet: A Table Graph Reconstruction Network for Table Structure Recognitioncited by 27
  6. 2022TSRFormer: Table Structure Recognition with Transformerscited by 27
  7. 2022TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformerscited by 19
  8. 2023LORE: Logical Location Regression Network for Table Structure Recognitioncited by 19
  9. 2023An End-to-End Multi-Task Learning Model for Image-based Table Recognitioncited by 14
  10. 2023GridFormer: Towards Accurate Table Structure Recognition via Grid Predictioncited by 13
  11. 2024UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognitioncited by 11
  12. 2025TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanismcited by 9
  13. 2024LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-trainingcited by 8
  14. 2025TABLET: Table Structure Recognition using Encoder-only Transformerscited by 5

Built on by

Not cited yet.