Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Scene Text Recognition On Cute80

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
CLIP4STR-L	99.0	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
CLIP4STR-L (DataComp-1B)	99.7	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
DTrOCR 105M	99.1	DTrOCR: Decoder-only Transformer for Optical Character Recognition
CCD-ViT-Base(ARD_2.8M)	98.3	Self-supervised Character-to-Character Distillation for Text Recognition	-
DiffusionSTR	92.5	DiffusionSTR: Diffusion Model for Scene Text Recognition	-
S-GTR	94.7	Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
PARSeq	98.3±0.6	Scene Text Recognition with Permuted Autoregressive Sequence Models
MATRN	93.5	Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
SIGA_T	93.1	Self-supervised Implicit Glyph Attention for Text Recognition
CDistNet (Ours)	89.58	CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
CCD-ViT-Small(ARD_2.8M)	98.3	Self-supervised Character-to-Character Distillation for Text Recognition	-
NRTR+TPS++	92.4	TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition
DPAN	91.9	Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
CLIP4STR-B*	99.65	An Empirical Study of Scaling Law for OCR
CLIP4STR-B	99.3	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model	-
MGP-STR	99.31	Multi-Granularity Prediction for Scene Text Recognition
CPPD	99.7	Context Perception Parallel Decoder for Scene Text Recognition
CCD-ViT-Tiny(ARD_2.8M)	95.8	Self-supervised Character-to-Character Distillation for Text Recognition	-

0 of 18 row(s) selected.