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 161–170 of 595 papers

TitleStatusHype
R2CNN: Rotational Region CNN for Orientation Robust Scene Text DetectionCode0
PixelLink: Detecting Scene Text via Instance SegmentationCode0
Progressive Contour Regression for Arbitrary-Shape Scene Text DetectionCode0
On Exploring and Improving Robustness of Scene Text Detection ModelsCode0
Overcoming Language Disparity in Online Content Classification with Multimodal LearningCode0
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural ImagesCode0
Pyramid Mask Text DetectorCode0
Arbitrary-Oriented Scene Text Detection via Rotation ProposalsCode0
Multi-Oriented Text Detection with Fully Convolutional NetworksCode0
MTRNet: A Generic Scene Text EraserCode0
Show:102550
← PrevPage 17 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