Scene Text Recognition on WOST

Metric: 1:1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	1:1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	CLIP4STR-H (DFN-5B)	90.9	No	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
2	CLIP4STR-L (DataComp-1B)	90.6	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
3	CLIP4STR-L	88.8	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
4	CLIP4STR-B	87	Yes	CLIP4STR: A Simple Baseline for Scene Text Recog...	2023-05-23	Code
5	CCD-ViT-Base	86	Yes	Self-supervised Character-to-Character Distillat...	2022-11-01	Code

#1CLIP4STR-H (DFN-5B)SOTA
90.9
1:1 Accuracy· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#2CLIP4STR-L (DataComp-1B)
90.6
1:1 Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#3CLIP4STR-L
88.8
1:1 Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#4CLIP4STR-B
87
1:1 Accuracy· Extra Data· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code
#5CCD-ViT-BaseSOTA
86
1:1 Accuracy· Extra Data· 2022-11-01
Self-supervised Character-to-Character Distillation for Text Recognition Code