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 91–100 of 595 papers

TitleStatusHype
Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion ModelsCode1
CLEval: Character-Level Evaluation for Text Detection and Recognition TasksCode1
A Multiplexed Network for End-to-End, Multilingual OCRCode1
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive LearningCode1
DALD: Improving Logits-based Detector without Logits from Black-box LLMsCode1
Kernel Proposal Network for Arbitrary Shape Text DetectionCode1
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated TextsCode1
Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in RussianCode1
ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text DetectionCode1
IMGTB: A Framework for Machine-Generated Text Detection BenchmarkingCode1
Show:102550
← PrevPage 10 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