Pith. sign in

REVIEW 6 cited by

TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2109.10282 v5 pith:QXJI5MUP submitted 2021-09-21 cs.CL cs.CV

Minghao Li , Tengchao Lv , Jingye Chen , Lei Cui , Yijuan Lu , Dinei Florencio , Cha Zhang , Zhoujun Li
show 1 more author
Furu Wei
This is my paper · ORCID
classification cs.CLcs.CV
keywords texttrocrmodelsrecognitionimagemodelpre-trainedtransformer
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is usually needed to improve the overall accuracy as a post-processing step. In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. The TrOCR model is simple but effective, and can be pre-trained with large-scale synthetic data and fine-tuned with human-labeled datasets. Experiments show that the TrOCR model outperforms the current state-of-the-art models on the printed, handwritten and scene text recognition tasks. The TrOCR models and code are publicly available at \url{https://aka.ms/trocr}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A hand-annotated dataset of 1933 Hamilton County property appraisals is extracted with template-aligned OCR, and a random forest trained on contemporary features estimates those historical values with about 17% MAPE.

  2. HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis

    cs.CV 2024-12 conditional novelty 6.0 of 10

    HAND is an end-to-end handwritten document recognition network that jointly performs text recognition and layout analysis and reports state-of-the-art results on READ 2016, scaling to triple-page documents.

  3. WriteViT: Handwritten Text Generation with Vision Transformer

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A ViT-based GAN framework for one-shot handwriting synthesis that reports state-of-the-art FID/KID on IAM and VNOnDB and improves HTR performance when used as a data augmenter.

  4. Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction

    cs.CL 2024-11 conditional novelty 5.0 of 10

    Arabic-specific fine-tunes of Nougat, trained on a synthetic Hindawi-derived dataset, report high in-distribution BLEU and structure accuracy for Arabic book page OCR.

  5. LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

    cs.CV 2026-01 conditional novelty 4.0 of 10

    A 1B end-to-end VLM reports 83.2 on OlmOCR-Bench after excluding the headers/footers category, plus a new image-localization benchmark.

  6. Low-Resource Language Processing: An OCR-Driven Summarization and Translation Pipeline

    cs.CL 2025-05 reject novelty 2.0 of 10

    A pipeline combining Tesseract, Gemini, and Google Translate claims 88% classification accuracy and moderate BLEU/ROUGE scores, but provides no reproducible evaluation.

Pith tools