Data to 14 Oct 2026

Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition

arXiv 1710.10400 ↗First posted 28 Oct 2017cs.CVcited by 162

Not on the map. Why?

Abstract (arXiv)

Text in curve orientation, despite being one of the common text orientations in real world environment, has close to zero existence in well received scene text datasets such as ICDAR2013 and MSRA-TD500. The main motivation of Total-Text is to fill this gap and facilitate a new research direction for the scene text community. On top of the conventional horizontal and multi-oriented texts, it features curved-oriented text. Total-Text is highly diversified in orientations, more than half of its images have a combination of more than two orientations. Recently, a new breed of solutions that casted text detection as a segmentation problem has demonstrated their effectiveness against multi-oriented text. In order to evaluate its robustness against curved text, we fine-tuned DeconvNet and benchmark it on Total-Text. Total-Text with its annotation is available at https://github.com/cs-chan/Total-Text-Dataset

Key facts. Cited by 162 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 35; 2023: 33; 2024: 32; 2025: 21; 2026: 13.

162 papers.

Sort:

By area:

2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
2024TextMonkey: An OCR-Free Large Multimodal Model for Understanding Documentcited by 174
2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 173
2023ImageBind-LLM: Multi-modality Instruction Tuningcited by 142
2024Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Wantcited by 101
2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 97
2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
2021Fourier Contour Embedding for Arbitrary-Shaped Text Detectioncited by 80
2023UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understandingcited by 74
2023SPTS v2: Single-Point Scene Text Spottingcited by 66
2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65

38 more

2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
2022Transformers in Remote Sensing: A Surveycited by 61
2023Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizercited by 53
2025Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videoscited by 51
2021PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Networkcited by 49
2021Open Images V5 Text Annotation and Yet Another Mask Text Spottercited by 46
2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46
2021Rethinking Text Line Recognition Modelscited by 45
2021SPTS: Single-Point Text Spottingcited by 45
2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
2023Revisiting Scene Text Recognition: A Data Perspectivecited by 45
2022Towards Weakly-Supervised Text Spotting using a Multi-Task Transformercited by 41
2024DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimmingcited by 35
2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34
2022Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learningcited by 33
2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
2022Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spottingcited by 27
2023Towards Unified Scene Text Spotting based on Sequence Generationcited by 27
2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
2021A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformercited by 26
2025Advancing Sequential Numerical Prediction in Autoregressive Modelscited by 26
2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
2024From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalitiescited by 22
2025Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understandingcited by 20
2021A Multiplexed Network for End-to-End, Multilingual OCRcited by 18
2022Vision-Language Pre-Training for Boosting Scene Text Detectorscited by 18
2022Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contextcited by 18
2022Kernel Proposal Network for Arbitrary Shape Text Detectioncited by 17
2022Arbitrary Shape Text Detection via Segmentation with Probability Mapscited by 15
2021I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detectioncited by 14
2025A Token-level Text Image Foundation Model for Document Understandingcited by 14
2021CentripetalText: An Efficient Text Instance Representation for Scene Text Detectioncited by 13
2022TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Maskcited by 13
2023ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretrainingcited by 12
2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learningcited by 12
2022Text Growing on Leafcited by 11
2022Out-of-Vocabulary Challenge Reportcited by 11

50 most cited of 162 All 162 (JSON)