# Hierarchical Document Parsing via Large Margin Feature Matching and Heuristics

arXiv: https://arxiv.org/abs/2502.07442 · HTML: https://mlsanity.com/paper/2502.07442/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding](https://mlsanity.com/paper/2010.11685/) (2020)
- [Entity Relation Extraction as Dependency Parsing in Visually Rich Documents](https://mlsanity.com/paper/2110.09915/) (2021)
- [Deep Learning based Visually Rich Document Content Understanding: A Survey](https://mlsanity.com/paper/2408.01287/) (2024)
- [A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images](https://mlsanity.com/paper/2304.07957/) (2023)
- [Scalable Framework for Classifying AI-Generated Content Across Modalities](https://mlsanity.com/paper/2502.00375/) (2025)
- [Addressing Out-of-Label Hazard Detection in Dashcam Videos: Insights from the COOOL Challenge](https://mlsanity.com/paper/2501.16037/) (2025)

## Abstract (arXiv)

We present our solution to the AAAI-25 VRD-IU challenge, achieving first place in the competition. Our approach integrates large margin loss for improved feature discrimination and employs heuristic rules to refine hierarchical relationships. By combining a deep learning-based matching strategy with greedy algorithms, we achieve a significant boost in accuracy while maintaining computational efficiency. Our method attains an accuracy of 0.98904 on the private leaderboard, demonstrating its effectiveness in document structure parsing. Source codes are publicly available at https://github.com/ffyyytt/VRUID-AAAI-DAKiet