SOTAVerified

Scene Text Detection

Scene Text Detection is a computer vision task that involves automatically identifying and localizing text within natural images or videos. The goal of scene text detection is to develop algorithms that can robustly detect and and label text with bounding boxes in uncontrolled and complex environments, such as street signs, billboards, or license plates.

Source: ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection

Papers

Showing 1–10 of 213 papers

TitleStatusHype
The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text DetectionCode1
Explicit Relational Reasoning Network for Scene Text Detection—0
KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark—0
Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera—0
Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt—0
Revisiting Tampered Scene Text Detection in the Era of Generative AICode2
Towards Unified Multi-granularity Text Detection with Interactive Attention—0
Dataset and Benchmark for Urdu Natural Scenes Text Detection, Recognition and Visual Question AnsweringCode0
The First Swahili Language Scene Text Detection and Recognition DatasetCode0
FPDIoU Loss: A Loss Function for Efficient Bounding Box Regression of Rotated Object Detection—0
Show:102550
← PrevPage 1 of 22Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MixNetH-Mean79.7—Unverified
2SRFormer (ResNet-50)H-Mean79.3—Unverified
3TextFuseNet (ResNeXt-101)H-Mean78.6—Unverified
4DPText-DETR (ResNet-50)H-Mean78.1—Unverified