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
Adaptive Boundary Proposal Network for Arbitrary Shape Text DetectionCode1
ICDAR 2021 Competition on Scene Video Text Spotting—0
Comprehensive Studies for Arbitrary-shape Scene Text Detection—0
Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem—0
Bidirectional Regression for Arbitrary-Shaped Text Detection—0
CentripetalText: An Efficient Text Instance Representation for Scene Text DetectionCode1
Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text KernelCode1
All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection—0
Progressive Contour Regression for Arbitrary-Shape Scene Text DetectionCode0
Self-Attention Based Text Knowledge Mining for Text DetectionCode1
Semantic-Aware Video Text Detection—0
Dictionary-Guided Scene Text RecognitionCode1
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text SpotterCode1
Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition—0
DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents—0
Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions—0
Abusive content detection in transliterated Bengali-English social media corpusCode0
Machine Translated Text Detection Through Text Similarity with Round-Trip TranslationCode0
RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection—0
TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text—0
MT: Multi-Perspective Feature Learning Network for Scene Text Detection—0
Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines—0
PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and BeyondCode1
PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped TextCode1
Stroke-Based Scene Text Erasing Using Synthetic Data for TrainingCode1
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