# HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction

arXiv: https://arxiv.org/abs/2411.01139 · HTML: https://mlsanity.com/paper/2411.01139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 2 Nov 2024.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://mlsanity.com/paper/2103.06495/) (2021)
- [ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network](https://mlsanity.com/paper/2002.10200/) (2020)
- [Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting](https://mlsanity.com/paper/2007.09482/) (2020)
- [FOTS: Fast Oriented Text Spotting with a Unified Network](https://mlsanity.com/paper/1801.01671/) (2018)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [Towards End-to-End Unified Scene Text Detection and Layout Analysis](https://mlsanity.com/paper/2203.15143/) (2022)
- [StrucTexT: Structured Text Understanding with Multi-Modal Transformers](https://mlsanity.com/paper/2108.02923/) (2021)
- [Detecting Oriented Text in Natural Images by Linking Segments](https://mlsanity.com/paper/1703.06520/) (2017)
- [DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting](https://mlsanity.com/paper/2211.10772/) (2022)
- [End-to-end Document Recognition and Understanding with Dessurt](https://mlsanity.com/paper/2203.16618/) (2022)
- [SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition](https://mlsanity.com/paper/2203.10209/) (2022)
- [XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding](https://mlsanity.com/paper/2203.06947/) (2022)
- [PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text](https://mlsanity.com/paper/2105.00405/) (2021)
- [Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution](https://mlsanity.com/paper/2102.06732/) (2021)
- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [Convolutional Character Networks](https://mlsanity.com/paper/1910.07954/) (2019)
- [TRIE: End-to-End Text Reading and Information Extraction for Document Understanding](https://mlsanity.com/paper/2005.13118/) (2020)
- [Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1707.03985/) (2017)
- [An end-to-end TextSpotter with Explicit Alignment and Attention](https://mlsanity.com/paper/1803.03474/) (2018)
- [PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network](https://mlsanity.com/paper/2104.05458/) (2021)
- [Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer](https://mlsanity.com/paper/2202.05508/) (2022)

## Abstract (arXiv)

End-to-end visual information extraction (VIE) aims at integrating the hierarchical subtasks of VIE, including text spotting, word grouping, and entity labeling, into a unified framework. Dealing with the gaps among the three subtasks plays a pivotal role in designing an effective VIE model. OCR-dependent methods heavily rely on offline OCR engines and inevitably suffer from OCR errors, while OCR-free methods, particularly those employing a black-box model, might produce outputs that lack interpretability or contain hallucinated content. Inspired by CenterNet, DeepSolo, and ESP, we propose HIP, which models entities as HIerarchical Points to better conform to the hierarchical nature of the end-to-end VIE task. Specifically, such hierarchical points can be flexibly encoded and subsequently decoded into desired text transcripts, centers of various regions, and categories of entities. Furthermore, we devise corresponding hierarchical pre-training strategies, categorized as image reconstruction, layout learning, and language enhancement, to reinforce the cross-modality representation of the hierarchical encoders. Quantitative experiments on public benchmarks demonstrate that HIP outperforms previous state-of-the-art methods, while qualitative results show its excellent interpretability.