TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment

• URL: http://arxiv.org/abs/2603.22819v1
• Date: Tue, 24 Mar 2026 05:45:02 GMT
• Title: TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment
• Abstract summary: TDATR (Table Detail-Aware Table Recognition) improves end-to-end TR through table detail-aware learning and cell-level visual alignment.<n>We achieve state-of-the-art or highly competitive performance on seven benchmarks without dataset-specific fine-tuning.
• Score: 70.83664203825235
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex workflows. End-to-end approaches rely heavily on large-scale TR data and struggle in data-constrained scenarios. To address these issues, we propose TDATR (Table Detail-Aware Table Recognition) improves end-to-end TR through table detail-aware learning and cell-level visual alignment. TDATR adopts a ``perceive-then-fuse'' strategy. The model first performs table detail-aware learning to jointly perceive table structure and content through multiple structure understanding and content recognition tasks designed under a language modeling paradigm. These tasks can naturally leverage document data from diverse scenarios to enhance model robustness. The model then integrates implicit table details to generate structured HTML outputs, enabling more efficient TR modeling when trained with limited data. Furthermore, we design a structure-guided cell localization module integrated into the end-to-end TR framework, which efficiently locates cell and strengthens vision-language alignment. It enhances the interpretability and accuracy of TR. We achieve state-of-the-art or highly competitive performance on seven benchmarks without dataset-specific fine-tuning.

Related papers

• InstructTable: Improving Table Structure Recognition Through Instructions [18.36576098544595]
  Table structure recognition (TSR) holds widespread practical importance.<n>Traditional visual-centric models rely exclusively on visual information while lacking crucial semantic support.<n> Vision-guided table instruction pre-training addresses these limitations.
  arXiv  Detail & Related papers  (2026-04-03T08:44:45Z)
• TableNet A Large-Scale Table Dataset with LLM-Powered Autonomous [4.207642146162365]
  Table Structure Recognition (TSR) requires the logical reasoning ability of large language models (LLMs) to handle complex table layouts.<n>We present TableNet dataset, a new table structure recognition dataset collected and generated through multiple sources.
  arXiv  Detail & Related papers  (2026-02-27T02:44:38Z)
• TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition [54.85932472676512]
  Table recognition (TR) aims to transform table images into semi-structured representations such as HTML or markdown.<n>We introduce TRivia, a self-supervised fine-tuning method that enables pretrained vision-language models to learn TR directly from unlabeled table images.<n>We present TRivia-3B, an open-sourced, compact, and state-of-the-art TR model that surpasses existing systems.
  arXiv  Detail & Related papers  (2025-12-01T03:49:00Z)
• TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding [52.59372043981724]
  TableDART is a training-efficient framework that integrates multimodal views by reusing pretrained single-modality models.<n>In addition, we propose a novel agent to cross-modal knowledge integration by analyzing outputs from text- and image-based models.
  arXiv  Detail & Related papers  (2025-09-18T07:00:13Z)
• From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis [9.526986293067576]
  DOTABLER is a table-centric semantic document parsing framework.<n>It delivers comprehensive table-anchored semantic analysis and precise extraction of semantically relevant tables.<n> evaluated on nearly 4,000 pages with over 1,000 tables from real-world PDFs.
  arXiv  Detail & Related papers  (2025-08-14T03:29:51Z)
• RAPTOR: Refined Approach for Product Table Object Recognition [0.1516287840715525]
  This research introduces RAPTOR, a modular post-processing system designed to enhance state-of-the-art models for improved table extraction.<n>RAPTOR addresses recurrent Table Detection (TD) and Table Structure Recognition (TSR) issues, improving both precision structural predictions.<n>The results demonstrate that while our approach excels at product tables, it also maintains reasonable performance across diverse table formats.
  arXiv  Detail & Related papers  (2025-02-19T13:59:06Z)
• UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition [55.153629718464565]
  We introduce UniTabNet, a novel framework for table structure parsing based on the image-to-text model. UniTabNet employs a divide-and-conquer'' strategy, utilizing an image-to-text model to decouple table cells and integrating both physical and logical decoders to reconstruct the complete table structure.
  arXiv  Detail & Related papers  (2024-09-20T01:26:32Z)
• UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining [22.031699293366486]
  We present UniTable, a training framework that unifies the training paradigm and training objective of table recognition. Our framework unifies the training objectives of all three TR tasks into a unified task-agnostic training objective: language modeling. UniTable's table parsing capability has surpassed both existing TR methods and general large vision-language models.
  arXiv  Detail & Related papers  (2024-03-07T15:44:50Z)
• TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers [56.56591337457137]
  We propose an accurate and end-to-end transformer-based table structure recognition method, referred to as TRUST. Transformers are suitable for table structure recognition because of their global computations, perfect memory, and parallel computation. We conduct experiments on several popular benchmarks including PubTabNet and SynthTable, our method achieves new state-of-the-art results.
  arXiv  Detail & Related papers  (2022-08-31T08:33:36Z)
• A Graph Representation of Semi-structured Data for Web Question Answering [96.46484690047491]
  We propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-10-14T04:01:54Z)
• TURL: Table Understanding through Representation Learning [29.6016859927782]
  TURL is a novel framework that introduces the pre-training/finetuning paradigm to relational Web tables. During pre-training, our framework learns deep contextualized representations on relational tables in an unsupervised manner. We show that TURL generalizes well to all tasks and substantially outperforms existing methods in almost all instances.
  arXiv  Detail & Related papers  (2020-06-26T05:44:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.