Hierarchical Document Structure Analysis: A Tree Construction Approach for Detecting, Ordering, and Reconstructing Document Layouts
The core message of this paper is to propose a comprehensive tree construction based approach, named Detect-Order-Construct, for hierarchical document structure analysis. This approach decomposes the task into three stages: detecting page objects and assigning logical roles, predicting the reading order of the detected objects, and constructing the intended hierarchical structure, including the table of contents.
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Document Layout Analysis models' robustness is benchmarked using RoDLA, introducing a taxonomy of perturbations and proposing metrics for evaluation.
LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding
Large Language Models (LLMs) integrated with Visual-rich Document Understanding (VrDU) models improve document analysis tasks.
Benchmarking Robustness of Document Layout Analysis Models with RoDLA
Introducing a robustness benchmark for Document Layout Analysis models, proposing metrics to evaluate perturbation impact, and presenting the RoDLA model for improved robust feature extraction.
TextMonkey: A Large Multimodal Model for Document Understanding
TextMonkey is a large multimodal model tailored for text-centric tasks, enhancing document understanding through innovative approaches.
CFRet-DVQA: Coarse-to-Fine Retrieval and Efficient Tuning for Document Visual Question Answering
CFRet-DVQA introduces a retrieval-augmented and efficient tuning framework for Document Visual Question Answering, achieving state-of-the-art results across various datasets.
TextMonkey: Enhancing Document Understanding with Large Multimodal Models
TextMonkey introduces innovative techniques like Shifted Window Attention and Token Resampler to enhance document understanding through large multimodal models.
Transformers and Language Models Revolutionizing Form Understanding: A Comprehensive Review
The authors explore the transformative impact of language models and transformers on form understanding, showcasing their effectiveness in handling noisy scanned documents.
CFRet-DVQA: Coarse-to-Fine Retrieval and Efficient Tuning for Document Visual Question Answering
The author introduces CFRet-DVQA, a framework focusing on retrieval and efficient tuning to enhance Document Visual Question Answering tasks effectively.
© 2024 by Linnk AI