SOTAVerified

Scene Text Recognition

See Scene Text Detection for leaderboards in this task.

Papers

Showing 110 of 269 papers

TitleStatusHype
Linguistics-aware Masked Image Modeling for Self-supervised Scene Text RecognitionCode1
Efficient and Accurate Scene Text Recognition with Cascaded-Transformers0
Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation0
A Context-Driven Training-Free Network for Lightweight Scene Text Segmentation and Recognition0
Billet Number Recognition Based on Test-Time Adaptation0
EventSTR: A Benchmark Dataset and Baselines for Event Stream based Scene Text RecognitionCode0
Ocean-OCR: Towards General OCR Application via a Vision-Language ModelCode1
Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance0
TextSSR: Diffusion-based Data Synthesis for Scene Text RecognitionCode2
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text RecognitionCode0
Show:102550
← PrevPage 1 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CLIP4STR-L*Accuracy99.42Unverified
2DTrOCR 105MAccuracy99.4Unverified
3CLIP4STR-L (DataComp-1B)Accuracy99Unverified
4MGP-STRAccuracy98.5Unverified
5CLIP4STR-LAccuracy98.5Unverified
6CLIP4STR-BAccuracy98.3Unverified
7CCD-ViT-Base(ARD_2.8M)Accuracy98.3Unverified
8CCD-ViT-Small(ARD_2.8M)Accuracy98.3Unverified
9MATRNAccuracy97.9Unverified
10S-GTRAccuracy97.8Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4STR-H (DFN-5B)Accuracy99.1Unverified
2DTrOCR 105MAccuracy98.9Unverified
3CLIP4STR-B*Accuracy98.76Unverified
4MGP-STRAccuracy98.6Unverified
5CLIP4STR-L (DataComp-1B)Accuracy98.6Unverified
6CLIP4STR-LAccuracy98.5Unverified
7CPPDAccuracy98.5Unverified
8CLIP4STR-BAccuracy98.3Unverified
9CCD-ViT-Base(ARD_2.8M)Accuracy97.8Unverified
10CCD-ViT-Small(ARD_2.8M)Accuracy96.4Unverified
#ModelMetricClaimedVerifiedStatus
1DTrOCR 105MAccuracy93.5Unverified
2CLIP4STR-L*Accuracy92.6Unverified
3CPPDAccuracy91.7Unverified
4CLIP4STR-L (DataComp-1B)Accuracy91.4Unverified
5MGP-STRAccuracy90.9Unverified
6CLIP4STR-LAccuracy90.8Unverified
7CLIP4STR-BAccuracy90.6Unverified
8SIGA_SAccuracy87.6Unverified
9S-GTRAccuracy87.3Unverified
10MATRNAccuracy86.6Unverified
#ModelMetricClaimedVerifiedStatus
1CPPDAccuracy99.7Unverified
2CLIP4STR-L (DataComp-1B)Accuracy99.7Unverified
3CLIP4STR-B*Accuracy99.65Unverified
4MGP-STRAccuracy99.31Unverified
5CLIP4STR-BAccuracy99.3Unverified
6DTrOCR 105MAccuracy99.1Unverified
7CLIP4STR-LAccuracy99Unverified
8CCD-ViT-Base(ARD_2.8M)Accuracy98.3Unverified
9CCD-ViT-Small(ARD_2.8M)Accuracy98.3Unverified
10CCD-ViT-Tiny(ARD_2.8M)Accuracy95.8Unverified
#ModelMetricClaimedVerifiedStatus
1DTrOCR 105MAccuracy99.6Unverified
2CLIP4STR-L (DataComp-1B)Accuracy99.6Unverified
3CLIP4STR-LAccuracy99.5Unverified
4CLIP4STR-B (DataComp-1B)Accuracy99.5Unverified
5CPPDAccuracy99.3Unverified
6CLIP4STR-BAccuracy99.2Unverified
7MGP-STRAccuracy98.8Unverified
8CCD-ViT-Base(ARD_2.8M)Accuracy98Unverified
9CCD-ViT-Small(ARD_2.8M)Accuracy98Unverified
10S-GTRAccuracy97.5Unverified
#ModelMetricClaimedVerifiedStatus
1DTrOCR 105MAccuracy98.6Unverified
2MGP-STRAccuracy98.3Unverified
3CLIP4STR-L*Accuracy98.13Unverified
4CLIP4STR-L (DataComp-1B)Accuracy98.1Unverified
5CLIP4STR-LAccuracy97.4Unverified
6CLIP4STR-BAccuracy97.2Unverified
7CPPDAccuracy96.7Unverified
8CCD-ViT-BaseAccuracy96.1Unverified
9CCD-ViT-SmallAccuracy92.7Unverified
10CCD-ViT-TinyAccuracy91.6Unverified
#ModelMetricClaimedVerifiedStatus
1Yet Another Text RecognizerAccuracy97.1Unverified
2SIGA_TAccuracy97Unverified
3SATRNAccuracy96.7Unverified
4DANAccuracy95Unverified
5SAFLAccuracy95Unverified
6CSTRAccuracy94.8Unverified
7Baek et al.Accuracy94.4Unverified
8ViTSTRAccuracy94.3Unverified
9AONAccuracy91.5Unverified
10RAREAccuracy90.1Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4STR-H (DFN-5B)1:1 Accuracy90.9Unverified
2CLIP4STR-L (DataComp-1B)1:1 Accuracy90.6Unverified
3CLIP4STR-L1:1 Accuracy88.8Unverified
4CLIP4STR-B1:1 Accuracy87Unverified
5CCD-ViT-Base1:1 Accuracy86Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4STR-L (DataComp-1B)Accuracy (%)86.4Unverified
2CLIP4STR-LAccuracy (%)85.9Unverified
3CLIP4STR-BAccuracy (%)85.8Unverified
4MGP-STRAccuracy (%)85.5Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4STR-L1:1 Accuracy81.9Unverified
2MGP-STR1:1 Accuracy81.7Unverified
3CLIP4STR-B1:1 Accuracy81.1Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4STR-L1:1 Accuracy82.7Unverified
2CLIP4STR-B1:1 Accuracy79.8Unverified
3CCD-ViT-Base1:1 Accuracy77.3Unverified
#ModelMetricClaimedVerifiedStatus
1CLIP4STR-L (DataComp-1B)Accuracy (%)92.2Unverified
2MGP-STRAccuracy (%)91Unverified
3CLIP4STR-BAccuracy (%)86.8Unverified
#ModelMetricClaimedVerifiedStatus
1ABINet-LV+TPS++Accuracy97.8Unverified
#ModelMetricClaimedVerifiedStatus
1MLDGAverage Accuracy19.02Unverified
#ModelMetricClaimedVerifiedStatus
1ABINet-LV+TPS++Accuracy89.6Unverified