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.
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection
Turning a CLIP Model into a Scene Text Detector
Recurrent Generic Contour-based Instance Segmentation with Progressive Learning
CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection
Domain Adaptive Scene Text Detection via Subcategorization
Aggregated Text Transformer for Scene Text Detection
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Text Growing on Leaf
Arbitrary Shape Text Detection via Segmentation with Probability Maps
DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection
Shift Variance in Scene Text Detection
DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Explore Faster Localization Learning For Scene Text Detection
TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask
UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection
Vision-Language Pre-Training for Boosting Scene Text Detectors
Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
Towards End-to-End Unified Scene Text Detection and Layout Analysis
Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
Real-time Scene Text Detection Based on Global Level and Word Level Features
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting
Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
Weakly Supervised Scene Text Detection using Deep Reinforcement Learning
CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning
Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection
StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
Industrial Scene Text Detection with Refined Feature-attentive Network
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
On Exploring and Improving Robustness of Scene Text Detection Models
Moving Object Detection for Event-based vision using Graph Spectral Clustering
Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.