paper-with-me

홈 › Papers

DocBank: A Benchmark Dataset for Document Layout Analysis

2020-06-01 · COLING 2020 8 · Minghao Li, Yiheng Xu, Lei Cui, Shaohan Huang, Furu Wei, Zhoujun Li, Ming Zhou

Document layout analysis usually relies on computer vision models to understand documents while ignoring textual information that is vital to capture. Meanwhile, high quality labeled datasets with both visual and textual information are still insufficient. In this paper, we present \textbf{DocBank}, a benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the \LaTeX{} documents available on the arXiv.com. With DocBank, models from different modalities can be compared fairly and multi-modal approaches will be further investigated and boost the performance of document layout analysis. We build several strong baselines and manually split train/dev/test sets for evaluation. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents. The DocBank dataset is publicly available at \url{https://github.com/doc-analysis/DocBank}.

📄 PDF Abstract BibTeX arXiv:2006.01038

Code (2)

doc-analysis/DocBank 공식 구현
adlnlp/doc_gcn tf

Tasks

Document Layout Analysis

Methods 이 논문이 사용한 방법론

BezierAlign BezierAlign is a feature sampling method for arbitrarily-shaped scene text recognition that exploits parameterization nature of a compact Bezier curve bounding box. Unlike…
ABCNet Adaptive Bezier-Curve Network, or ABCNet, is an end-to-end framework for arbitrarily-shaped scene text spotting. It adaptively fits arbitrary-shaped text by a…

Similar Papers 제목 키워드 기반

DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis

2022-06-02 · Birgit Pfitzmann, Christoph Auer, Michele Dolfi, Ahmed S Nassar 외

Accurate document layout analysis is a key requirement for high-quality PDF document conversion. With the recent availability of public, large ground-truth datasets such as PubLayNet and DocBank, deep-learning models hav…

Document Layout AnalysisObject Detection

Vision Grid Transformer for Document Layout Analysis

2023-08-29 · ICCV 2023 1 · Cheng Da, Chuwei Luo, Qi Zheng, Cong Yao

Document pre-trained models and grid-based models have proven to be very effective on various tasks in Document AI. However, for the document layout analysis (DLA) task, existing document pre-trained models, even those p…

Document AIDocument Layout Analysisdocument understandingOptical Character Recognition (OCR)

IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing

2025-12-23 · Oikantik Nath, Sahithi Kukkala, Mitesh Khapra, Ravi Kiran Sarvadevabhatla arxiv

Document layout analysis is essential for downstream tasks such as information retrieval, extraction, OCR, and digitization. However, existing large-scale datasets like PubLayNet and DocBank lack fine-grained region labe…

Document Layout AnalysisInformation Retrieval

A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents

2023-03-17 · Norman Meuschke, Apurva Jagdale, Timo Spinde, Jelena Mitrović 외

Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically d…

RetrievalTable Extraction

BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset

2023-03-09 · Md. Istiak Hossain Shihab, Md. Rakibul Hasan, Mahfuzur Rahman Emon, Syed Mobassir Hossen 외

While strides have been made in deep learning based Bengali Optical Character Recognition (OCR) in the past decade, the absence of large Document Layout Analysis (DLA) datasets has hindered the application of OCR in docu…

BenchmarkingDeep LearningDocument Layout AnalysisOptical Character Recognition+1