# MASTER: Multi-Aspect Non-local Network for Scene Text Recognition

arXiv: https://arxiv.org/abs/1910.02562 · HTML: https://mlsanity.com/paper/1910.02562/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 30 of 65)

- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [Towards End-to-End Unified Scene Text Detection and Layout Analysis](https://mlsanity.com/paper/2203.15143/) (2022)
- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition](https://mlsanity.com/paper/2207.00193/) (2022)
- [Revisiting Scene Text Recognition: A Data Perspective](https://mlsanity.com/paper/2307.08723/) (2023)
- [Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling](https://mlsanity.com/paper/2303.06949/) (2023)
- [DTrOCR: Decoder-only Transformer for Optical Character Recognition](https://mlsanity.com/paper/2308.15996/) (2023)
- [PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML](https://mlsanity.com/paper/2105.01848/) (2021)
- [Multi-Granularity Prediction for Scene Text Recognition](https://mlsanity.com/paper/2209.03592/) (2022)
- [GLASS: Global to Local Attention for Scene-Text Spotting](https://mlsanity.com/paper/2208.03364/) (2022)
- [Aligning Correlation Information for Domain Adaptation in Action Recognition](https://mlsanity.com/paper/2107.04932/) (2021)
- [A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer](https://mlsanity.com/paper/2112.04888/) (2021)
- [Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning](https://mlsanity.com/paper/2309.01083/) (2023)
- [Levenshtein OCR](https://mlsanity.com/paper/2209.03594/) (2022)
- [SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition](https://mlsanity.com/paper/2411.15858/) (2024)
- [TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers](https://mlsanity.com/paper/2208.14687/) (2022)
- [Context Perception Parallel Decoder for Scene Text Recognition](https://mlsanity.com/paper/2307.12270/) (2023)
- [Instruction-Guided Scene Text Recognition](https://mlsanity.com/paper/2401.17851/) (2024)
- [An End-to-End Multi-Task Learning Model for Image-based Table Recognition](https://mlsanity.com/paper/2303.08648/) (2023)
- [COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts](https://mlsanity.com/paper/2207.04675/) (2022)
- [LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition](https://mlsanity.com/paper/2308.12774/) (2023)
- [GridFormer: Towards Accurate Table Structure Recognition via Grid Prediction](https://mlsanity.com/paper/2309.14962/) (2023)
- [UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining](https://mlsanity.com/paper/2403.04822/) (2024)
- [IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition](https://mlsanity.com/paper/2312.11923/) (2023)
- [Out of Length Text Recognition with Sub-String Matching](https://mlsanity.com/paper/2407.12317/) (2024)
- [PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex](https://mlsanity.com/paper/2105.01846/) (2021)
- [Rethinking Image-based Table Recognition Using Weakly Supervised Methods](https://mlsanity.com/paper/2303.07641/) (2023)
- [Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition](https://mlsanity.com/paper/2402.13643/) (2024)
- [ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX](https://mlsanity.com/paper/2105.14426/) (2021)

## Abstract (arXiv)

Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture. However, such methods suffer from attention-drift problem because high similarity among encoded features leads to attention confusion under the RNN-based local attention mechanism. Moreover, RNN-based methods have low efficiency due to poor parallelization. To overcome these problems, we propose the MASTER, a self-attention based scene text recognizer that (1) not only encodes the input-output attention but also learns self-attention which encodes feature-feature and target-target relationships inside the encoder and decoder and (2) learns a more powerful and robust intermediate representation to spatial distortion, and (3) owns a great training efficiency because of high training parallelization and a high-speed inference because of an efficient memory-cache mechanism. Extensive experiments on various benchmarks demonstrate the superior performance of our MASTER on both regular and irregular scene text. Pytorch code can be found at https://github.com/wenwenyu/MASTER-pytorch, and Tensorflow code can be found at https://github.com/jiangxiluning/MASTER-TF.