HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Scene Text Recognition On Icdar2013

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper TitleRepository
CLIP4STR-L*99.42An Empirical Study of Scaling Law for OCR
DTrOCR 105M99.4DTrOCR: Decoder-only Transformer for Optical Character Recognition
CLIP4STR-L (DataComp-1B)99.0CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CLIP4STR-L98.5CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
MGP-STR98.5Multi-Granularity Prediction for Scene Text Recognition
PARSeq98.4±0.2Scene Text Recognition with Permuted Autoregressive Sequence Models
CLIP4STR-B98.3CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CCD-ViT-Base(ARD_2.8M)98.3Self-supervised Character-to-Character Distillation for Text Recognition
CCD-ViT-Small(ARD_2.8M)98.3Self-supervised Character-to-Character Distillation for Text Recognition
MATRN97.9Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
SIGA_T97.8Self-supervised Implicit Glyph Attention for Text Recognition
S-GTR97.8Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
DPAN97.7Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition-
CDistNet (Ours)97.67CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
CCD-ViT-Tiny(ARD_2.8M)97.5Self-supervised Character-to-Character Distillation for Text Recognition
SVTR-L (Large)97.2SVTR: Scene Text Recognition with a Single Visual Model
SVTR-B (Base)97.1SVTR: Scene Text Recognition with a Single Visual Model
DiffusionSTR97.1DiffusionSTR: Diffusion Model for Scene Text Recognition-
Yet Another Text Recognizer96.8Why You Should Try the Real Data for the Scene Text Recognition
SVTR-T (Tiny)96.3SVTR: Scene Text Recognition with a Single Visual Model
0 of 38 row(s) selected.
Scene Text Recognition On Icdar2013 | SOTA | HyperAI