TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Scene Text Recognition/ICDAR2013

Scene Text Recognition on ICDAR2013

Metric: Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Accuracy▼Extra DataPaperDate↕Code
1CLIP4STR-L*99.42YesAn Empirical Study of Scaling Law for OCR2023-12-29Code
2DTrOCR 105M99.4NoDTrOCR: Decoder-only Transformer for Optical Cha...2023-08-30Code
3CLIP4STR-L (DataComp-1B)99NoCLIP4STR: A Simple Baseline for Scene Text Recog...2023-05-23Code
4MGP-STR98.5YesMulti-Granularity Prediction for Scene Text Reco...2022-09-08Code
5CLIP4STR-L98.5YesCLIP4STR: A Simple Baseline for Scene Text Recog...2023-05-23Code
6CCD-ViT-Base(ARD_2.8M)98.3YesSelf-supervised Character-to-Character Distillat...2022-11-01Code
7CCD-ViT-Small(ARD_2.8M)98.3YesSelf-supervised Character-to-Character Distillat...2022-11-01Code
8CLIP4STR-B98.3YesCLIP4STR: A Simple Baseline for Scene Text Recog...2023-05-23Code
9MATRN97.9NoMulti-modal Text Recognition Networks: Interacti...2021-11-30Code
10S-GTR97.8YesVisual Semantics Allow for Textual Reasoning Bet...2021-12-24Code
11SIGA_T97.8NoSelf-supervised Implicit Glyph Attention for Tex...2022-03-07Code
12DPAN97.7No--Code
13CDistNet (Ours)97.67NoCDistNet: Perceiving Multi-Domain Character Dist...2021-11-22Code
14CCD-ViT-Tiny(ARD_2.8M)97.5YesSelf-supervised Character-to-Character Distillat...2022-11-01Code
15SVTR-L (Large)97.2NoSVTR: Scene Text Recognition with a Single Visua...2022-04-30Code
16SVTR-B (Base)97.1NoSVTR: Scene Text Recognition with a Single Visua...2022-04-30Code
17DiffusionSTR97.1NoDiffusionSTR: Diffusion Model for Scene Text Rec...2023-06-29-
18Yet Another Text Recognizer96.8NoWhy You Should Try the Real Data for the Scene T...2021-07-29Code
19SVTR-T (Tiny)96.3NoSVTR: Scene Text Recognition with a Single Visua...2022-04-30Code
20SVTR-S (Small)95.7NoSVTR: Scene Text Recognition with a Single Visua...2022-04-30Code
21SRN95.5NoTowards Accurate Scene Text Recognition with Sem...2020-03-27Code
22RCEED94.7NoRepresentation and Correlation Enhanced Encoder-...2021-06-13Code
23SATRN94.1NoOn Recognizing Texts of Arbitrary Shapes with 2D...2019-10-10Code
24DAN93.9NoDecoupled Attention Network for Text Recognition2019-12-21Code
25CSTR93.2NoRevisiting Classification Perspective on Scene T...2021-02-22Code
26TextScanner92.9NoTextScanner: Reading Characters in Order for Rob...2019-12-28-
27SEED92.8NoSEED: Semantics Enhanced Encoder-Decoder Framewo...2020-05-22Code
28SAFL92.8NoSAFL: A Self-Attention Scene Text Recognizer wit...2022-01-01Code
29ViTSTR92.4NoVision Transformer for Fast and Efficient Scene ...2021-05-18Code
30Baek et al.92.3NoWhat Is Wrong With Scene Text Recognition Model ...2019-04-03Code
31ASTER91.8No--Code
32CA-FCN91.5NoScene Text Recognition from Two-Dimensional Pers...2018-09-18-
33SAR91NoShow, Attend and Read: A Simple and Strong Basel...2018-11-02Code
34STAR-Net89.1No--Code
35RARE88.6NoRobust Scene Text Recognition with Automatic Rec...2016-03-12Code
36CRNN86.7NoAn End-to-End Trainable Neural Network for Image...2015-07-21Code
37CHAR79.5NoSynthetic Data and Artificial Neural Networks fo...2014-06-09Code