Scene Text Recognition

See Scene Text Detection for leaderboards in this task.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–150 of 269 papers

Title	Date	Tasks	Status	Score
FOTS: Fast Oriented Text Spotting with a Unified Network	Jan 5, 2018	Scene Text DetectionScene Text Recognition	CodeCode Available	5
Geometric Perception based Efficient Text Recognition	Feb 8, 2023	Scene Text Recognition	CodeCode Available	5
ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)	Sep 16, 2019	Scene Text DetectionScene Text Recognition	CodeCode Available	5
Improving Text Proposals for Scene Images with Fully Convolutional Networks	Feb 16, 2017	ObjectScene Text Recognition	CodeCode Available	5
Instruction-Guided Scene Text Recognition	Jan 31, 2024	Question AnsweringScene Text Recognition	CodeCode Available	5
IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition	Dec 19, 2023	Conditional Text GenerationDecoder	CodeCode Available	5
KISS: Keeping It Simple for Scene Text Recognition	Nov 19, 2019	Scene Text Recognition	CodeCode Available	5
Levenshtein OCR	Sep 8, 2022	Imitation LearningOptical Character Recognition (OCR)	CodeCode Available	5
LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition	Aug 24, 2023	DecoderScene Text Recognition	CodeCode Available	5
Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition	Aug 1, 2021	Language ModellingPosition	CodeCode Available	5
Masked and Permuted Implicit Context Learning for Scene Text Recognition	May 25, 2023	DecoderLanguage Modeling	CodeCode Available	5
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	Aug 22, 2019	Scene Text RecognitionSemantic Segmentation	CodeCode Available	5
MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark	Oct 15, 2024	FairnessScene Text Recognition	CodeCode Available	5
MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition	Jul 26, 2024	Mixture-of-ExpertsScene Text Recognition	CodeCode Available	5
Multi-Granularity Prediction for Scene Text Recognition	Sep 8, 2022	Language ModelingLanguage Modelling	CodeCode Available	5
Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition	Jul 25, 2023	Language ModellingOptical Character Recognition (OCR)	CodeCode Available	5
NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition	Jun 4, 2018	DecoderOptical Character Recognition (OCR)	CodeCode Available	5
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention	Oct 10, 2019	Scene Text Recognition	CodeCode Available	5
OTE: Exploring Accurate Scene Text Recognition Using One Token	Jan 1, 2024	DecoderScene Text Recognition	CodeCode Available	5
Out of Length Text Recognition with Sub-String Matching	Jul 17, 2024	Scene Text Recognition	CodeCode Available	5
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond	Apr 5, 2018	Generative Adversarial NetworkPedestrian Detection	CodeCode Available	5
Platypus: A Generalized Specialist Model for Reading Text in Various Forms	Aug 27, 2024	Handwritten Text RecognitionOptical Character Recognition (OCR)	CodeCode Available	5
Pyramid Mask Text Detector	Mar 28, 2019	ClusteringInstance Segmentation	CodeCode Available	5
Reading Between the Lanes: Text VideoQA on the Road	Jul 8, 2023	Question AnsweringScene Text Recognition	CodeCode Available	5
Reading Scene Text in Deep Convolutional Sequences	Jun 14, 2015	Scene Text Recognition	CodeCode Available	5
Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition	May 13, 2021	Optical Character Recognition (OCR)Scene Text Recognition	CodeCode Available	5
Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition	Nov 18, 2024	Contrastive LearningRepresentation Learning	CodeCode Available	5
Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition	Jun 13, 2021	DecoderScene Text Recognition	CodeCode Available	5
RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles	Jul 23, 2021	Image GenerationScene Text Editing	CodeCode Available	5
RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition	Jul 15, 2020	DecoderIrregular Text Recognition	CodeCode Available	5
Robust Scene Text Recognition with Automatic Rectification	Mar 12, 2016	Optical Character Recognition (OCR)Scene Text Detection	CodeCode Available	5
SAFL: A Self-Attention Scene Text Recognizer with Focal Loss	Jan 1, 2022	Optical Character RecognitionOptical Character Recognition (OCR)	CodeCode Available	5
Scene Text Image Super-Resolution via Parallelly Contextual Attention Network	Oct 17, 2021	Image ReconstructionImage Super-Resolution	CodeCode Available	5
Scene Text Recognition using Higher Order Language Priors	Sep 1, 2012	Scene Text Recognition	CodeCode Available	5
Scene Text Telescope: Text-Focused Scene Image Super-Resolution	Jun 19, 2021	Image Super-ResolutionOptical Character Recognition (OCR)	CodeCode Available	5
SEE: Towards Semi-Supervised End-to-End Scene Text Recognition	Dec 14, 2017	Scene Text DetectionScene Text Recognition	CodeCode Available	5
SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition	May 27, 2020	Color ManipulationScene Text Recognition	CodeCode Available	5
Star-net: A spatial attention residue network for scene text recognition.	Sep 20, 2016	Optical Character Recognition (OCR)Scene Text Recognition	CodeCode Available	5
STN-OCR: A single Neural Network for Text Detection and Text Recognition	Jul 27, 2017	Optical Character Recognition (OCR)Scene Text Detection	CodeCode Available	5
SVTR: Scene Text Recognition with a Single Visual Model	Apr 30, 2022	Scene Text Recognition	CodeCode Available	5
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition	Nov 24, 2024	DecoderOptical Character Recognition (OCR)	CodeCode Available	5
TextBoxes++: A Single-Shot Oriented Scene Text Detector	Jan 9, 2018	object-detectionObject Detection	CodeCode Available	5
The First Swahili Language Scene Text Detection and Recognition Dataset	May 19, 2024	Information RetrievalScene Text Detection	CodeCode Available	5
Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition	Oct 28, 2017	Curved Text DetectionScene Text Detection	CodeCode Available	5
Towards Accurate Scene Text Recognition with Semantic Reasoning Networks	Mar 27, 2020	Optical Character Recognition (OCR)Scene Text Recognition	CodeCode Available	5
Towards Boosting the Accuracy of Non-Latin Scene Text Recognition	Jan 10, 2022	Scene Text Recognition	CodeCode Available	5
Towards Large-scale Building Attribute Mapping using Crowdsourced Images: Scene Text Recognition on Flickr and Problems to be Solved	Sep 14, 2023	AttributeScene Text Recognition	CodeCode Available	5
Visual Re-ranking with Natural Language Understanding for Text Spotting	Oct 29, 2018	Language ModelingLanguage Modelling	CodeCode Available	5
Focusing Attention: Towards Accurate Text Recognition in Natural Images	Sep 7, 2017	DecoderScene Text Recognition	—Unverified	0
A Hardware-Oriented and Memory-Efficient Method for CTC Decoding	May 8, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0

Show:10 25 50

← PrevPage 3 of 6Next →

All datasets ICDAR2013 SVT ICDAR2015 CUTE80 IIIT5k SVTP ICDAR 2003 WOST IC19-Art COCO-Text HOST Uber-Text

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-L*	Accuracy	99.42	—	Unverified
2	DTrOCR 105M	Accuracy	99.4	—	Unverified
3	CLIP4STR-L (DataComp-1B)	Accuracy	99	—	Unverified
4	MGP-STR	Accuracy	98.5	—	Unverified
5	CLIP4STR-L	Accuracy	98.5	—	Unverified
6	CLIP4STR-B	Accuracy	98.3	—	Unverified
7	CCD-ViT-Base(ARD_2.8M)	Accuracy	98.3	—	Unverified
8	CCD-ViT-Small(ARD_2.8M)	Accuracy	98.3	—	Unverified
9	MATRN	Accuracy	97.9	—	Unverified
10	S-GTR	Accuracy	97.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-H (DFN-5B)	Accuracy	99.1	—	Unverified
2	DTrOCR 105M	Accuracy	98.9	—	Unverified
3	CLIP4STR-B*	Accuracy	98.76	—	Unverified
4	MGP-STR	Accuracy	98.6	—	Unverified
5	CLIP4STR-L (DataComp-1B)	Accuracy	98.6	—	Unverified
6	CLIP4STR-L	Accuracy	98.5	—	Unverified
7	CPPD	Accuracy	98.5	—	Unverified
8	CLIP4STR-B	Accuracy	98.3	—	Unverified
9	CCD-ViT-Base(ARD_2.8M)	Accuracy	97.8	—	Unverified
10	CCD-ViT-Small(ARD_2.8M)	Accuracy	96.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DTrOCR 105M	Accuracy	93.5	—	Unverified
2	CLIP4STR-L*	Accuracy	92.6	—	Unverified
3	CPPD	Accuracy	91.7	—	Unverified
4	CLIP4STR-L (DataComp-1B)	Accuracy	91.4	—	Unverified
5	MGP-STR	Accuracy	90.9	—	Unverified
6	CLIP4STR-L	Accuracy	90.8	—	Unverified
7	CLIP4STR-B	Accuracy	90.6	—	Unverified
8	SIGA_S	Accuracy	87.6	—	Unverified
9	S-GTR	Accuracy	87.3	—	Unverified
10	MATRN	Accuracy	86.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CPPD	Accuracy	99.7	—	Unverified
2	CLIP4STR-L (DataComp-1B)	Accuracy	99.7	—	Unverified
3	CLIP4STR-B*	Accuracy	99.65	—	Unverified
4	MGP-STR	Accuracy	99.31	—	Unverified
5	CLIP4STR-B	Accuracy	99.3	—	Unverified
6	DTrOCR 105M	Accuracy	99.1	—	Unverified
7	CLIP4STR-L	Accuracy	99	—	Unverified
8	CCD-ViT-Base(ARD_2.8M)	Accuracy	98.3	—	Unverified
9	CCD-ViT-Small(ARD_2.8M)	Accuracy	98.3	—	Unverified
10	CCD-ViT-Tiny(ARD_2.8M)	Accuracy	95.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DTrOCR 105M	Accuracy	99.6	—	Unverified
2	CLIP4STR-L (DataComp-1B)	Accuracy	99.6	—	Unverified
3	CLIP4STR-L	Accuracy	99.5	—	Unverified
4	CLIP4STR-B (DataComp-1B)	Accuracy	99.5	—	Unverified
5	CPPD	Accuracy	99.3	—	Unverified
6	CLIP4STR-B	Accuracy	99.2	—	Unverified
7	MGP-STR	Accuracy	98.8	—	Unverified
8	CCD-ViT-Base(ARD_2.8M)	Accuracy	98	—	Unverified
9	CCD-ViT-Small(ARD_2.8M)	Accuracy	98	—	Unverified
10	S-GTR	Accuracy	97.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DTrOCR 105M	Accuracy	98.6	—	Unverified
2	MGP-STR	Accuracy	98.3	—	Unverified
3	CLIP4STR-L*	Accuracy	98.13	—	Unverified
4	CLIP4STR-L (DataComp-1B)	Accuracy	98.1	—	Unverified
5	CLIP4STR-L	Accuracy	97.4	—	Unverified
6	CLIP4STR-B	Accuracy	97.2	—	Unverified
7	CPPD	Accuracy	96.7	—	Unverified
8	CCD-ViT-Base	Accuracy	96.1	—	Unverified
9	CCD-ViT-Small	Accuracy	92.7	—	Unverified
10	CCD-ViT-Tiny	Accuracy	91.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Yet Another Text Recognizer	Accuracy	97.1	—	Unverified
2	SIGA_T	Accuracy	97	—	Unverified
3	SATRN	Accuracy	96.7	—	Unverified
4	DAN	Accuracy	95	—	Unverified
5	SAFL	Accuracy	95	—	Unverified
6	CSTR	Accuracy	94.8	—	Unverified
7	Baek et al.	Accuracy	94.4	—	Unverified
8	ViTSTR	Accuracy	94.3	—	Unverified
9	AON	Accuracy	91.5	—	Unverified
10	RARE	Accuracy	90.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-H (DFN-5B)	1:1 Accuracy	90.9	—	Unverified
2	CLIP4STR-L (DataComp-1B)	1:1 Accuracy	90.6	—	Unverified
3	CLIP4STR-L	1:1 Accuracy	88.8	—	Unverified
4	CLIP4STR-B	1:1 Accuracy	87	—	Unverified
5	CCD-ViT-Base	1:1 Accuracy	86	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-L (DataComp-1B)	Accuracy (%)	86.4	—	Unverified
2	CLIP4STR-L	Accuracy (%)	85.9	—	Unverified
3	CLIP4STR-B	Accuracy (%)	85.8	—	Unverified
4	MGP-STR	Accuracy (%)	85.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-L	1:1 Accuracy	81.9	—	Unverified
2	MGP-STR	1:1 Accuracy	81.7	—	Unverified
3	CLIP4STR-B	1:1 Accuracy	81.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-L	1:1 Accuracy	82.7	—	Unverified
2	CLIP4STR-B	1:1 Accuracy	79.8	—	Unverified
3	CCD-ViT-Base	1:1 Accuracy	77.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CLIP4STR-L (DataComp-1B)	Accuracy (%)	92.2	—	Unverified
2	MGP-STR	Accuracy (%)	91	—	Unverified
3	CLIP4STR-B	Accuracy (%)	86.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ABINet-LV+TPS++	Accuracy	97.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MLDG	Average Accuracy	19.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ABINet-LV+TPS++	Accuracy	89.6	—	Unverified