Papers with Code 아카이브
Scene Text Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 9
- 보존된 평가 기록
- 146
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Explicit Relational Reasoning Network for Scene Text Detection
KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark
Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera
Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt
Revisiting Tampered Scene Text Detection in the Era of Generative AI
Towards Unified Multi-granularity Text Detection with Interactive Attention
Dataset and Benchmark for Urdu Natural Scenes Text Detection, Recognition and Visual Question Answering
The First Swahili Language Scene Text Detection and Recognition Dataset
FPDIoU Loss: A Loss Function for Efficient Bounding Box Regression of Rotated Object Detection
Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis
MorphText: Deep Morphology Regularized Arbitrary-shape Scene Text Detection
Text in the Dark: Extremely Low-Light Text Image Enhancement
MENTOR: Multilingual tExt detectioN TOward leaRning by analogy
ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
CPN: Complementary Proposal Network for Unconstrained Text Detection
EK-Net:Real-time Scene Text Detection with Expand Kernel Distance
BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection
Text Region Multiple Information Perception Network for Scene Text Detection
Research on Multilingual Natural Scene Text Detection Algorithm
Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models
DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
STEP -- Towards Structured Scene-Text Spotting
MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
Turning a CLIP Model into a Scene Text Spotter
SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression
Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning
Separate Scene Text Detector for Unseen Scripts is Not All You Need
Adaptive Segmentation Network for Scene Text Detection
CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer
LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network
ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining
TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.