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 21–30 of 595 papers

TitleStatusHype
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text SpottingCode2
Text Detection Forgot About Document OCRCode2
DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in TransformerCode2
Arbitrary Shape Text Detection via Boundary TransformerCode2
Towards End-to-End Unified Scene Text Detection and Layout AnalysisCode2
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text RecognitionCode2
Real-time Scene Text Detection with Differentiable BinarizationCode2
The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text DetectionCode1
SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text SpottingCode1
Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial TrainingCode1
Show:102550
← PrevPage 3 of 60Next →

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