Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations

• URL: http://arxiv.org/abs/2606.17874v1
• Date: Tue, 16 Jun 2026 12:45:57 GMT
• Title: Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations
• Abstract summary: Multi-task table recognition jointly addresses table structure prediction, cell localization, and cell content recognition.<n>This paper proposes a structural refinement module that produces order-independent cell features through non-causal attention.
• Score: 0.47379911264912167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-task table recognition jointly addresses table structure prediction, cell localization, and cell content recognition within a unified framework. Existing approaches often rely on autoregressive decoders to generate table structures and reuse their hidden states for cell localization and content recognition. This autoregressive generation process can make cell representations order-dependent, degrading global consistency across cells. This paper proposes a structural refinement module that produces order-independent cell features through non-causal attention. This design enables parallel inference of cell contents while conditioning each cell on global context encoded in the refined features. Experiments on two large datasets demonstrate consistent gains in cell localization and end-to-end recognition, while reducing overall inference time by around threefold.

Related papers

• How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location [53.68149869349268]
  We investigate the process of table understanding by dissecting the atomic task of cell location.<n>We demonstrate that models locate the target cell via an ordinal mechanism that counts discretes to resolve coordinates.<n>We reveal that models generalize to multi-cell location tasks by multiplexing the identical attention heads identified during atomic location.
  arXiv  Detail & Related papers  (2026-02-09T11:47:34Z)
• Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition [1.2328446298523066]
  We propose a multi-cell content decoder and bidirectional mutual learning mechanism to improve the end-to-end approach. The effectiveness is demonstrated on two large datasets, and the experimental results show comparable performance to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-04-20T04:30:38Z)
• UniCell: Universal Cell Nucleus Classification via Prompt Learning [76.11864242047074]
  We propose a universal cell nucleus classification framework (UniCell) It employs a novel prompt learning mechanism to uniformly predict the corresponding categories of pathological images from different dataset domains. In particular, our framework adopts an end-to-end architecture for nuclei detection and classification, and utilizes flexible prediction heads for adapting various datasets.
  arXiv  Detail & Related papers  (2024-02-20T11:50:27Z)
• RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning [75.61681328968714]
  We propose recurrent independent Grid LSTM (RigLSTM) to exploit the underlying modular structure of the target task. Our model adopts cell selection, input feature selection, hidden state selection, and soft state updating to achieve a better generalization ability.
  arXiv  Detail & Related papers  (2023-11-03T07:40:06Z)
• 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)
• Visual Understanding of Complex Table Structures from Document Images [32.95187519339354]
  We propose a novel object-detection-based deep model that captures the inherent alignments of cells within tables. We also aim to improve structure recognition by deducing a novel rectilinear graph-based formulation. Our framework improves the previous state-of-the-art performance by a 2.7% average F1-score on benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-13T14:54:33Z)
• TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition [76.06530816349763]
  We propose an end-to-end trainable table graph reconstruction network (TGRNet) for table structure recognition. Specifically, the proposed method has two main branches, a cell detection branch and a cell logical location branch, to jointly predict the spatial location and the logical location of different cells.
  arXiv  Detail & Related papers  (2021-06-20T01:57:05Z)
• LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment [54.768354427967296]
  Table structure recognition is a challenging task due to the various structures and complicated cell spanning relations. We propose the framework of Local and Global Pyramid Mask Alignment, which adopts the soft pyramid mask learning mechanism in both the local and global feature maps. A pyramid mask re-scoring module is then integrated to compromise the local and global information and refine the predicted boundaries.
  arXiv  Detail & Related papers  (2021-05-13T12:24:12Z)
• Table Structure Recognition using Top-Down and Bottom-Up Cues [28.65687982486627]
  We present an approach for table structure recognition that combines cell detection and interaction modules. We empirically validate our method on the publicly available real-world datasets.
  arXiv  Detail & Related papers  (2020-10-09T13:32:53Z)
• Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context [11.99452212008243]
  We present a vision-guided systematic framework for joint table detection and cell structured recognition. With GTE-Table, we invent a new penalty based on the natural cell containment constraint of tables to train our table network. We use this to enhance PubTabNet with cell labels and create FinTabNet, real-world and complex scientific and financial datasets.
  arXiv  Detail & Related papers  (2020-05-01T20:14:49Z)

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.