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 226–250 of 595 papers

TitleStatusHype
You Only Recognize Once: Towards Fast Video Text Spotting—0
GOF at Arabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced Arabic Offensive Text Detection—0
Character Region Attention For Text Spotting—0
Efficient Scene Text Detection with Textual Attention Tower—0
DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection—0
Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection—0
HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis—0
CPN: Complementary Proposal Network for Unconstrained Text Detection—0
How do Convolutional Neural Networks Learn Design?—0
Efficiently Leveraging Linguistic Priors for Scene Text Spotting—0
A Single Shot Text Detector with Scale-adaptive Anchors—0
Character Proposal Network for Robust Text Extraction—0
IndicSTR12: A Dataset for Indic Scene Text Recognition—0
Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling—0
ICDAR 2015 Text Reading in the Wild Competition—0
Characterness: An Indicator of Text in the Wild—0
Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning—0
EAGLE: A Domain Generalization Framework for AI-generated Text Detection—0
ICDAR 2021 Competition on Scene Video Text Spotting—0
A Novel Integrated Framework for Learning both Text Detection and Recognition—0
ICDAR 2023 Competition on Reading the Seal Title—0
ICDAR 2023 Video Text Reading Competition for Dense and Small Text—0
IIITH at SemEval-2021 Task 7: Leveraging transformer-based humourous and offensive text detection architectures using lexical and hurtlex features and task adaptive pretraining—0
Image Processing Based Scene-Text Detection and Recognition with Tesseract—0
DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents—0
Show:102550
← PrevPage 10 of 24Next →

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