HyperAI초신경

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

한국어

HyperAI초신경

Scene Text Recognition On Svtp

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	Paper Title	Repository
CLIP4STR-L	97.4	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
DPAN	89.0	Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
CLIP4STR-B	97.2	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
CLIP4STR-L (DataComp-1B)	98.1	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
SIGA_T	90.5	Self-supervised Implicit Glyph Attention for Text Recognition
MATRN	90.6	Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
CCD-ViT-Base	96.1	Self-supervised Character-to-Character Distillation for Text Recognition	-
CCD-ViT-Small	92.7	Self-supervised Character-to-Character Distillation for Text Recognition	-
CCD-ViT-Tiny	91.6	Self-supervised Character-to-Character Distillation for Text Recognition	-
DTrOCR 105M	98.6	DTrOCR: Decoder-only Transformer for Optical Character Recognition
CDistNet (Ours)	89.77	CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
PARSeq	95.7±0.9	Scene Text Recognition with Permuted Autoregressive Sequence Models
CPPD	96.7	Context Perception Parallel Decoder for Scene Text Recognition
DiffusionSTR	89.2	DiffusionSTR: Diffusion Model for Scene Text Recognition	-
CLIP4STR-L*	98.13	An Empirical Study of Scaling Law for OCR
S-GTR	90.6	Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
MGP-STR	98.3	Multi-Granularity Prediction for Scene Text Recognition

0 of 17 row(s) selected.