OpenCodePapers
scene-text-recognition-on-wost
Optical Character Recognition (OCR)
Scene Text Recognition
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
1:1 Accuracy
↕
ModelName
ReleaseDate
↕
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
✓ Link
90.9
CLIP4STR-H (DFN-5B)
2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
✓ Link
90.6
CLIP4STR-L (DataComp-1B)
2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
✓ Link
88.8
CLIP4STR-L
2023-05-23
Font-Agent: Enhancing Font Understanding with Large Language Models
87.7
Font-Agent (extra data)
2025-06-11
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
✓ Link
87.0
CLIP4STR-B
2023-05-23
Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition
✓ Link
86.9
CAM-Base
2024-02-21
Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
✓ Link
86.59
E²STR-ICL
2023-11-22
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition
✓ Link
86.26
SVTRv2-B
2024-11-24
Self-supervised Character-to-Character Distillation for Text Recognition
✓ Link
86.0
CCD-ViT-Base
2022-11-01
Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing
82.5
DARLING (extra data)
2024-05-07
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
✓ Link
70.3
VisionLAN (extra data)
2021-08-22
×