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 71–80 of 595 papers

TitleStatusHype
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defenseCode1
Recurrent Generic Contour-based Instance Segmentation with Progressive LearningCode1
SPTS v2: Single-Point Scene Text SpottingCode1
Towards Robust Tampered Text Detection in Document Image: New Dataset and New SolutionCode1
A Comprehensive Gold Standard and Benchmark for Comics Text Detection and RecognitionCode1
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive LearningCode1
CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text DetectionCode1
TPFNet: A Novel Text In-painting Transformer for Text RemovalCode1
Deepfake Text Detection: Limitations and OpportunitiesCode1
Threat Scenarios and Best Practices to Detect Neural Fake NewsCode1
Show:102550
← PrevPage 8 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