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 401–410 of 595 papers

TitleStatusHype
Unconstrained Text Detection in Manga: a New Dataset and BaselineCode1
One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information ExtractionCode1
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the WildCode1
Scene Text Detection with Selected Anchor—0
Robust Handwriting Recognition with Limited and Noisy Data—0
TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text DetectionCode1
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text SpottingCode1
Sequential Deformation for Accurate Scene Text Detection—0
TweepFake: about Detecting Deepfake TweetsCode1
Character Region Attention For Text Spotting—0
Show:102550
← PrevPage 41 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