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 141–150 of 595 papers

TitleStatusHype
DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection—0
Detecting Curve Text with Local Segmentation Network and Curve Connection—0
Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping—0
Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning—0
Cursive Caption Text Detection in Videos—0
Adaptive Segmentation Network for Scene Text Detection—0
Domain Gating Ensemble Networks for AI-Generated Text Detection—0
DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents—0
CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer—0
A Single Shot Text Detector with Scale-adaptive Anchors—0
Show:102550
← PrevPage 15 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