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 331–340 of 595 papers

TitleStatusHype
Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection—0
Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection—0
StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks—0
Adaptive Shrink-Mask for Text Detection—0
Offensive Text Detection Across Languages and Datasets Using Rule-based and Hybrid Methods—0
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel RepresentationCode1
Distantly Supervised Semantic Text Detection and Recognition for Broadcast Sports Videos Understanding—0
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text RepresentationCode1
Industrial Scene Text Detection with Refined Feature-attentive NetworkCode1
ARTS: Eliminating Inconsistency between Text Detection and Recognition with Auto-Rectification Text Spotter—0
Show:102550
← PrevPage 34 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