paper-with-me

Scene Text Detection

9개 벤치마크 · 논문 220편 · 이 태스크의 논문 보기 →

Benchmarks

ICDAR 2015

결과 43개

Total-Text

결과 27개

MSRA-TD500

결과 18개

SCUT-CTW1500

결과 17개

ICDAR 2013

결과 16개

ICDAR 2017 MLT

결과 14개

COCO-Text

결과 6개

IC19-Art

결과 4개

IC19-ReCTs

결과 1개

Most implemented

Papers

TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts

2026-06-26 · Boyuan Chen, Zichen Dang, Chuang Yang, Lap-Pui Chau 외 arxiv

In real-world deployments, scene text detectors inevitably face distribution shifts beyond the training distribution. Prior work often depends on large-scale scene-text pretraining, yet evaluation under cross-domain chan…

Scene Text Detection

ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis

2026-03-26 · Xike Zhang, Maoyuan Ye, Juhua Liu, Bo Du arxiv

Previous works based on Segment Anything Model (SAM) have achieved promising performance in unified scene text detection and layout analysis. However, the typical reliance on pixel-level text segmentation for sampling th…

Scene Text Detection

TextMamba: Scene Text Detector with Mamba

2025-12-07 · Qiyan Zhao, Yue Yan, Da-Han Wang arxiv

In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transfor…

Scene Text Detection

Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding

2025-11-28 · Anik De, Abhirama Subramanyam Penamakuri, Rajeev Yadav, Aditya Rathore 외 arxiv

Reading scene text, that is, text appearing in images, has numerous application areas, including assistive technology, search, and e-commerce. Although scene text recognition in English has advanced significantly and is …

Scene Text RecognitionScene Text Detection

A Large-scale Dataset for Robust Complex Anime Scene Text Detection

2025-10-09 · Ziyi Dong, Yurui Zhang, Changmao Li, Naomi Rue Golding 외 arxiv

Current text detection datasets primarily target natural or document scenes, where text typically appear in regular font and shapes, monotonous colors, and orderly layouts. The text usually arranged along straight or cur…

Scene Text Detection

Human + AI for Accelerating Ad Localization Evaluation

2025-09-16 · Harshit Rajgarhia, Shivali Dalmia, Mengyang Zhao, Mukherji Abhishek 외 arxiv

Adapting advertisements for multilingual audiences requires more than simple text translation; it demands preservation of visual consistency, spatial alignment, and stylistic integrity across diverse languages and format…

Scene Text DetectionMachine Translation

전체 220편 보기 →