# PreSTU: Pre-Training for Scene-Text Understanding

arXiv: https://arxiv.org/abs/2209.05534 · HTML: https://mlsanity.com/paper/2209.05534/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 86 references that are in the map.
- First posted on arXiv 12 Sep 2022.

## Builds on (most cited first, 30 of 66)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)

## Built on by (most cited first, 27 of 27)

- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [PaLI-X: On Scaling up a Multilingual Vision and Language Model](https://mlsanity.com/paper/2305.18565/) (2023)
- [MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering](https://mlsanity.com/paper/2212.09662/) (2022)
- [ScreenAI: A Vision-Language Model for UI and Infographics Understanding](https://mlsanity.com/paper/2402.04615/) (2024)
- [DocFormerv2: Local Features for Document Understanding](https://mlsanity.com/paper/2306.01733/) (2023)
- [ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules](https://mlsanity.com/paper/2304.02173/) (2023)
- [Reading Between the Lanes: Text VideoQA on the Road](https://mlsanity.com/paper/2307.03948/) (2023)
- [OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models](https://mlsanity.com/paper/2502.16161/) (2025)
- [Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness](https://mlsanity.com/paper/2305.05095/) (2023)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs](https://mlsanity.com/paper/2305.18641/) (2023)
- [Visually Guided Generative Text-Layout Pre-training for Document Intelligence](https://mlsanity.com/paper/2403.16516/) (2024)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images](https://mlsanity.com/paper/2404.18397/) (2024)
- [Separate and Locate: Rethink the Text in Text-based Visual Question Answering](https://mlsanity.com/paper/2308.16383/) (2023)
- [ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images](https://mlsanity.com/paper/2404.10652/) (2024)
- [InstructOCR: Instruction Boosting Scene Text Spotting](https://mlsanity.com/paper/2412.15523/) (2024)
- [Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models](https://mlsanity.com/paper/2305.15080/) (2023)
- [Multiple-Question Multiple-Answer Text-VQA](https://mlsanity.com/paper/2311.08622/) (2023)
- [SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap](https://mlsanity.com/paper/2309.12382/) (2023)
- [Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance](https://mlsanity.com/paper/2510.21590/) (2025)
- [Class-Agnostic Region-of-Interest Matching in Document Images](https://mlsanity.com/paper/2506.21055/) (2025)
- [LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts](https://mlsanity.com/paper/2502.19202/) (2025)
- [Towards Signboard-Oriented Visual Question Answering: ViSignVQA Dataset, Method and Benchmark](https://mlsanity.com/paper/2512.22218/) (2025)
- [GenPlot: Increasing the Scale and Diversity of Chart Derendering Data](https://mlsanity.com/paper/2306.11699/) (2023)
- [A Surrogate-Assisted Extended Generative Adversarial Network for Parameter Optimization in Free-Form Metasurface Design](https://mlsanity.com/paper/2401.02961/) (2023)
- [ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question Answering](https://mlsanity.com/paper/2410.14132/) (2024)

## Abstract (arXiv)

The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training objective. In this paper, we propose PreSTU, a novel pre-training recipe dedicated to scene-text understanding (STU). PreSTU introduces OCR-aware pre-training objectives that encourage the model to recognize text from an image and connect it to the rest of the image content. We implement PreSTU using a simple transformer-based encoder-decoder architecture, combined with large-scale image-text datasets with scene text obtained from an off-the-shelf OCR system. We empirically demonstrate the effectiveness of this pre-training approach on eight visual question answering and four image captioning benchmarks.