HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Scene Text Recognition On Svt

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
CLIP4STR-H (DFN-5B)99.1CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
DTrOCR 105M98.9DTrOCR: Decoder-only Transformer for Optical Character Recognition
CLIP4STR-B*98.76An Empirical Study of Scaling Law for OCR
CLIP4STR-L (DataComp-1B)98.6CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
MGP-STR98.6Multi-Granularity Prediction for Scene Text Recognition
CLIP4STR-L98.5CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
CPPD98.5Context Perception Parallel Decoder for Scene Text Recognition
CLIP4STR-B98.3CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
PARSeq97.9±0.2Scene Text Recognition with Permuted Autoregressive Sequence Models
CCD-ViT-Base(ARD_2.8M)97.8Self-supervised Character-to-Character Distillation for Text Recognition
CCD-ViT-Small(ARD_2.8M)96.4Self-supervised Character-to-Character Distillation for Text Recognition
CCD-ViT-Tiny(ARD_2.8M)96.0Self-supervised Character-to-Character Distillation for Text Recognition
S-GTR95.8Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
SIGA_T95.1Self-supervised Implicit Glyph Attention for Text Recognition
MATRN95Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Yet Another Text Recognizer94.7Why You Should Try the Real Data for the Scene Text Recognition
NRTR+TPS++94.6TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition
DPAN93.9Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
CDistNet (Ours)93.82CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
DiffusionSTR93.6DiffusionSTR: Diffusion Model for Scene Text Recognition
0 of 37 row(s) selected.