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 111–120 of 595 papers

TitleStatusHype
Polygon-free: Unconstrained Scene Text Detection with Box AnnotationsCode1
Unconstrained Text Detection in MangaCode1
RRPN++: Guidance Towards More Accurate Scene Text DetectionCode1
One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information ExtractionCode1
Unconstrained Text Detection in Manga: a New Dataset and BaselineCode1
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the WildCode1
TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text DetectionCode1
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text SpottingCode1
TweepFake: about Detecting Deepfake TweetsCode1
CLEval: Character-Level Evaluation for Text Detection and Recognition TasksCode1
Show:102550
← PrevPage 12 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