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 411–420 of 595 papers

TitleStatusHype
Character Proposal Network for Robust Text Extraction—0
Character Region Attention For Text Spotting—0
Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts—0
ChartEye: A Deep Learning Framework for Chart Information Extraction—0
CL-ISR: A Contrastive Learning and Implicit Stance Reasoning Framework for Misleading Text Detection on Social Media—0
COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation—0
Collaborative Evaluation of Deepfake Text with Deliberation-Enhancing Dialogue Systems—0
Combining Shallow and Deep Learning for Aggressive Text Detection—0
Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition—0
Comprehensive Studies for Arbitrary-shape Scene Text Detection—0
Show:102550
← PrevPage 42 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