Papers with Code 아카이브
Scene Text Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 15
- 보존된 평가 기록
- 190
See Scene Text Detection for leaderboards in this task.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Scene Text Recognition with Permuted Autoregressive Sequence Models
Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition
GIT: A Generative Image-to-text Transformer for Vision and Language
Multimodal Semi-Supervised Learning for Text Recognition
SVTR: Scene Text Recognition with a Single Visual Model
Automated player identification and indexing using two-stage deep learning network
Pushing the Performance Limit of Scene Text Recognizer without Human Annotation
IterVM: Iterative Vision Modeling Module for Scene Text Recognition
SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization
Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching
Towards Open-Set Text Recognition via Label-to-Prototype Learning
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Self-supervised Implicit Glyph Attention for Text Recognition
Transfer Learning for Scene Text Recognition in Indian Languages
Towards Boosting the Accuracy of Non-Latin Scene Text Recognition
On the Cross-dataset Generalization in License Plate Recognition
SAFL: A Self-Attention Scene Text Recognizer with Focal Loss
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
Visual-Semantic Transformer for Scene Text Recognition
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages
Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition
CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models
Ultra Light OCR Competition Technical Report
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
Learning Meta-path-aware Embeddings for Recommender Systems
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
Multi-task learning for jersey number recognition in Ice Hockey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.