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 531–540 of 595 papers

TitleStatusHype
Rotation-Sensitive Regression for Oriented Scene Text Detection—0
An end-to-end TextSpotter with Explicit Alignment and AttentionCode0
Multi-Oriented Scene Text Detection via Corner Localization and Region SegmentationCode0
Sliding Line Point Regression for Shape Robust Scene Text DetectionCode0
TextBoxes++: A Single-Shot Oriented Scene Text DetectorCode0
FOTS: Fast Oriented Text Spotting with a Unified NetworkCode0
PixelLink: Detecting Scene Text via Instance SegmentationCode0
SEE: Towards Semi-SupervisedEnd-to-End Scene Text Recognition—0
SEE: Towards Semi-Supervised End-to-End Scene Text RecognitionCode0
Detecting Curve Text in the Wild: New Dataset and New SolutionCode0
Show:102550
← PrevPage 54 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