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

Showing 151200 of 595 papers

TitleStatusHype
ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street ViewsCode0
Abusive content detection in transliterated Bengali-English social media corpusCode0
Short-PHD: Detecting Short LLM-generated Text with Topological Data Analysis After Off-topic Content InsertionCode0
Artistic-style text detector and a new Movie-Poster datasetCode0
SKDU at De-Factify 4.0: Natural Language Features for AI-Generated Text-DetectionCode0
Stacking the Odds: Transformer-Based Ensemble for AI-Generated Text DetectionCode0
Convolutional Character NetworksCode0
Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text DetectionCode0
SemEval-2024 Task 8: Weighted Layer Averaging RoBERTa for Black-Box Machine-Generated Text DetectionCode0
Self-Organized Text Detection With Minimal Post-Processing via Border LearningCode0
SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line DetectionCode0
Scene Text Detection with Supervised Pyramid Context NetworkCode0
SEE: Towards Semi-Supervised End-to-End Scene Text RecognitionCode0
Selective Style Transfer for TextCode0
Rosetta: Large scale system for text detection and recognition in imagesCode0
Robust AI-Generated Text Detection by Restricted EmbeddingsCode0
Rethinking Offensive Text Detection as a Multi-Hop Reasoning ProblemCode0
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural ImagesCode0
Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural ScenesCode0
Research on Multilingual Natural Scene Text Detection AlgorithmCode0
Scene Text Detection and Recognition: The Deep Learning EraCode0
SynSciPass: detecting appropriate uses of scientific text generationCode0
'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviewsCode0
Progressive Contour Regression for Arbitrary-Shape Scene Text DetectionCode0
Qwen it detect machine-generated text?Code0
Position: It's Time to Act on the Risk of Efficient Personalized Text GenerationCode0
PixelLink: Detecting Scene Text via Instance SegmentationCode0
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR SystemCode0
R2CNN: Rotational Region CNN for Orientation Robust Scene Text DetectionCode0
Overcoming Language Disparity in Online Content Classification with Multimodal LearningCode0
On Exploring and Improving Robustness of Scene Text Detection ModelsCode0
End-to-End Saliency Mapping via Probability Distribution PredictionCode0
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion ReductionCode0
You Only Recognize Once: Towards Fast Video Text SpottingCode0
MTRNet: A Generic Scene Text EraserCode0
MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and UnderstandingCode0
Multi-Oriented Scene Text Detection via Corner Localization and Region SegmentationCode0
Arbitrary-Oriented Scene Text Detection via Rotation ProposalsCode0
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary ShapesCode0
Pyramid Mask Text DetectorCode0
A Feasible Framework for Arbitrary-Shaped Scene Text RecognitionCode0
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary ShapesCode0
Multi-Oriented Text Detection with Fully Convolutional NetworksCode0
Machine-generated text detection prevents language model collapseCode0
Machine-Generated Text Detection using Deep LearningCode0
DocXChain: A Powerful Open-Source Toolchain for Document Parsing and BeyondCode0
Extremely Low-light Image Enhancement with Scene Text RestorationCode0
Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge DistillationCode0
Facilitating Pornographic Text Detection for Open-Domain Dialogue Systems via Knowledge Distillation of Large Language ModelsCode0
DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and TrustworthinessCode0
Show:102550
← PrevPage 4 of 12Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ContourNet [69]Precision86.99Unverified
2DRRG [72]Precision83.87Unverified
3PSENet [67]Precision78.11Unverified
4EAST [75]Precision71.48Unverified
5EASTPrecision70.43Unverified