SOTAVerified

Text Detection

Detecting the text in the image and localise it using a bounding box. The text can be in any shape and size. We need to localise all such instances of text in the entire image along with bounding box for each word.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–375 of 595 papers

TitleStatusHype
Contextual Text Block Detection towards Scene Text Understanding—0
Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning—0
Real-time End-to-End Video Text Spotter with Contrastive Representation LearningCode0
Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and RecognitionCode0
Explore Faster Localization Learning For Scene Text Detection—0
BusiNet -- a Light and Fast Text Detection Network for Business Documents—0
TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask—0
DIALOG-22 RuATD Generated Text DetectionCode0
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System—0
GOF at Arabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced Arabic Offensive Text Detection—0
Overcoming Language Disparity in Online Content Classification with Multimodal LearningCode0
TraffSign: Multilingual Traffic Signboard Text Detection and Recognition for Urdu and EnglishCode0
Text Detection & Recognition in the Wild for Robot Localization—0
UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection—0
Text Detection on Technical Drawings for the Digitization of Brown-field Processes—0
Vision-Language Pre-Training for Boosting Scene Text DetectorsCode0
Rethinking Offensive Text Detection as a Multi-Hop Reasoning ProblemCode0
Extremely Low-light Image Enhancement with Scene Text RestorationCode0
Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection—0
Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition—0
Unified Line and Paragraph Detection by Graph Convolutional Networks—0
TSR-DSAW: Table Structure Recognition via Deep Spatial Association of Words—0
Real-time Scene Text Detection Based on Global Level and Word Level Features—0
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting—0
Arbitrary Shape Text Detection using Transformers—0
Show:102550
← PrevPage 15 of 24Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ContourNet [69]Precision86.99—Unverified
2DRRG [72]Precision83.87—Unverified
3PSENet [67]Precision78.11—Unverified
4EAST [75]Precision71.48—Unverified
5EASTPrecision70.43—Unverified