Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Text Spotting On Icdar 2015

Metrics

F-measure (%) - Generic Lexicon

F-measure (%) - Strong Lexicon

F-measure (%) - Weak Lexicon

Results

Performance results of various models on this benchmark

Model Name	F-measure (%) - Generic Lexicon	F-measure (%) - Strong Lexicon	F-measure (%) - Weak Lexicon	Paper Title	Repository
TextPerceptron	65.1	80.5	76.6	Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
FOTS	62.2	83.6	74.5	FOTS: Fast Oriented Text Spotting with a Unified Network
DeepSolo(ResNet-50)	76.9	86.8	81.9	DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
DeepSolo(ResNet-50, TextOCR)	79.1	88.0	83.5	DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
ABCNet v2	73.0	82.7	78.5	ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
SPTS	65.8	77.5	70.2	SPTS: Single-Point Text Spotting
TESTR	73.6	85.2	79.4	Text Spotting Transformers
DeepSolo (ViTAEv2-S, TextOCR)	79.5	88.1	83.9	DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
MANGO	67.3	81.8	78.9	MANGO: A Mask Attention Guided One-Stage Scene Text Spotter
SwinTextSpotter	70.5	83.9	77.3	SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
UNITS	80.3	89.0	84.1	Towards Unified Scene Text Spotting based on Sequence Generation
TextDragon	65.2	82.5	78.3	TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting	-
MaskTextSpotter v3	74.2	83.3	78.1	Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
SPTS v2	72.6	82.3	77.7	SPTS v2: Single-Point Scene Text Spotting
A3S	79.6	84.8	83.7	A3S: Adversarial learning of semantic representations for Scene-Text Spotting	-
PGNet	63.5	83.3	78.3	PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
SRTS	74.5	85.6	81.7	Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognition
GLASS	76.3	84.7	80.1	GLASS: Global to Local Attention for Scene-Text Spotting

0 of 18 row(s) selected.