HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Scene Text Recognition On Icdar 2003

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	Paper Title	Repository
CRNN	89.4	An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition	-
ViTSTR	94.3	Vision Transformer for Fast and Efficient Scene Text Recognition	-
SIGA_T	97.0	Self-supervised Implicit Glyph Attention for Text Recognition	-
SAFL	95.0	SAFL: A Self-Attention Scene Text Recognizer with Focal Loss	-
DAN	95.0	Decoupled Attention Network for Text Recognition	-
AON	91.5	AON: Towards Arbitrarily-Oriented Text Recognition	-
CSTR	94.8	Revisiting Classification Perspective on Scene Text Recognition	-
SATRN	96.7	On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention	-
STAR-Net	89.9	Star-net: A spatial attention residue network for scene text recognition.
RARE	90.1	Robust Scene Text Recognition with Automatic Rectification	-
Baek et al.	94.4	What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis	-
Yet Another Text Recognizer	97.1	Why You Should Try the Real Data for the Scene Text Recognition	-

0 of 12 row(s) selected.

Scene Text Recognition On Icdar 2003 | SOTA | HyperAI초신경