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 311–320 of 595 papers

TitleStatusHype
Text Spotting TransformersCode1
Extremely Low-light Image Enhancement with Scene Text RestorationCode0
Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection—0
Towards End-to-End Unified Scene Text Detection and Layout AnalysisCode2
Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition—0
End-to-End Video Text Spotting with TransformerCode1
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text RecognitionCode2
Unified Line and Paragraph Detection by Graph Convolutional Networks—0
TSR-DSAW: Table Structure Recognition via Deep Spatial Association of Words—0
Kernel Proposal Network for Arbitrary Shape Text DetectionCode1
Show:102550
← PrevPage 32 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