paper-with-me

Scene Text Recognition

15개 벤치마크 · 논문 281편 · 이 태스크의 논문 보기 →

Benchmarks

ICDAR2013

결과 114개

SVT

결과 111개

ICDAR2015

결과 81개

CUTE80

결과 54개

IIIT5k

결과 51개

SVTP

결과 51개

ICDAR 2003

결과 36개

IC19-Art

결과 15개

WOST

결과 15개

COCO-Text

결과 12개

HOST

결과 9개

Uber-Text

결과 9개

MSDA

결과 6개

IC13

결과 3개

SVT-P

결과 3개

Most implemented

Papers

Out-of-Length Scene Text Recognition: A Two-Axis Diagnosis and a Training-Free Fix

2026-07-25 · Zobeir Raisi, John Zelek arxiv

Scene Text Recognition (STR) models are trained almost exclusively on word crops of at most 25 characters, yet real deployments (signage, product labels, dense captions) require reading much longer text. This paper diagn…

Scene Text Recognition

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

2026-06-23 · Xingsong Ye, Yongkun Du, Jiaxin Zhang, Haojie Zhang 외 arxiv

WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing S…

Scene Text Recognition

Reading in the Dark: Low-light Scene Text Recognition

2026-04-26 · Xuanshuo Fu, Lei Kang, Ernest Valveny, Dimosthenis Karatzas 외 arxiv

Accurate text recognition in low-light environments is essential for intelligent systems in applications ranging from autonomous vehicles to smart surveillance. However, challenges such as poor illumination and noise int…

Low-Light Image EnhancementScene Text RecognitionAutonomous Vehicles

Multi-Modal Character Localization and Extraction for Chinese Text Recognition

2026-03-14 · Qilong Li, Chongsheng Zhang arxiv

Scene text recognition (STR) methods have demonstrated their excellent capability in English text images. However, due to the complex inner structures of Chinese and the extensive character categories, it poses challenge…

Scene Text Recognition

An Effective Data Augmentation Method by Asking Questions about Scene Text Images

2026-03-03 · Xu Yao, Lei Kang arxiv

Scene text recognition (STR) and handwritten text recognition (HTR) face significant challenges in accurately transcribing textual content from images into machine-readable formats. Conventional OCR models often predict …

Handwritten Text RecognitionScene Text RecognitionData Augmentation

What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution

2026-02-06 · Xingsong Ye, Yongkun Du, JiaXin Zhang, Chen Li 외 arxiv

Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Synthetic data offers a cost-effective and perfe…

Scene Text Recognition

전체 281편 보기 →