The paper introduces BGTR, a Bounding Box-Guided Table Recognizer that first predicts cell bounding boxes and then uses this information to generate HTML sequences for table structure recognition. It addresses the limitation of current image-to-sequence methods that ignore explicit bounding box data, which can cause errors in complex scenes. To overcome limited natural scene table data, the authors employ progressive training and create the synthetic SNSTab dataset, achieving state‑of‑the‑art results on five benchmark datasets.
arXiv:2607. 00734v1 Announce Type: cross Abstract: Table Structure Recognition (TSR) aims to recover the row and column layout of tables from document images, a key step in document understanding pipelines.
Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approaches predominantly rel...
arXiv:2609.17458v1 Announce Type: cross Abstract: Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering...
arXiv:2608. 12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations.
TeleOCR is a unified framework for document parsing that tackles challenges in both decoupled and end-to-end Vision‑Language Models. It introduces deformation‑aware learning to handle geometric distortions, an adaptive sampling mechanism for complex layouts, and a content‑structure decoupled strategy to model formula grammars and table structures. The approach achieves state‑of‑the‑art results on multiple benchmarks, including top placement in the ICDAR 2026 Sci‑ImageMiner Challenge.
WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing STR datasets and methods, typically built around regular scene text and fixed-template inputs, struggle to scale to WATER.
arXiv:2607. 00747v1 Announce Type: cross Abstract: Table extraction from business documents relies on a cascaded pipeline where Table Detection (TD) first localizes tables and Table Structure Recognition (TSR) then recovers their internal layout.
arXiv:2608. 03557v1 Announce Type: cross Abstract: Tabular-to-image methods that convert tabular data into visual representations have emerged as a novel paradigm for leveraging the high performance of deep learning models.
arXiv:2608.24845v1 Announce Type: cross Abstract: We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from Commo...
We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from CommonCrawl. From these, we download 80M videos with a t...
arXiv:2608. 13513v1 Announce Type: cross Abstract: Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers.
Key Information Extraction (KIE) converts visually rich documents into structured data, but practical deployment remains challenging: strong performance often relies on costly on-server Large Multimodal Models (LMMs), while compact locally deployable models lack sufficient KIE supervision. We present SAYRE, a scene-aware document synthesis framework for generating scalable KIE training data without hand-crafted template design.