HyperAIHyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAIHyperAI

Scene Text Recognition On Iiit5K

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Accuracy
Paper TitleRepository
DPAN96.2Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
CLIP4STR-B (DataComp-1B)99.5CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model-
SIGA_S96.9Self-supervised Implicit Glyph Attention for Text Recognition-
MATRN96.6Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features-
DTrOCR 105M99.6DTrOCR: Decoder-only Transformer for Optical Character Recognition-
CLIP4STR-L99.5CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model-
MGP-STR98.8Multi-Granularity Prediction for Scene Text Recognition-
PARSeq99.1±0.1Scene Text Recognition with Permuted Autoregressive Sequence Models-
CCD-ViT-Small(ARD_2.8M)98.0Self-supervised Character-to-Character Distillation for Text Recognition-
CDistNet (Ours)96.57CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition-
CCD-ViT-Tiny(ARD_2.8M)97.1Self-supervised Character-to-Character Distillation for Text Recognition-
CLIP4STR-B99.2CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model-
CLIP4STR-L (DataComp-1B)99.6CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model-
CCD-ViT-Base(ARD_2.8M)98.0Self-supervised Character-to-Character Distillation for Text Recognition-
S-GTR97.5Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition-
DiffusionSTR97.3DiffusionSTR: Diffusion Model for Scene Text Recognition-
CPPD99.3Context Perception Parallel Decoder for Scene Text Recognition-
0 of 17 row(s) selected.
Scene Text Recognition On Iiit5K | SOTA | HyperAI