AI Paper Atlas

Research map / Benchmarks / SVTP

SVTP leaderboard

29 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SVTP. Best accuracy: 93.3 (DARLING, CVPR 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

SVTP · accuracy

17 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
193.3DARLINGChoose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing
CVPR 2024 · Table 1
Editing and style transfer
293.3TRBA-cr
TRBA
Pushing the Performance Limit of Scene Text Recognizer Without Human Annotation
CVPR 2022 · Table 1
Semi-supervised learning
391.5CornerTransformerToward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition
ECCV 2022 · Table 7
Human and embodied modeling
489.3ABINet-ConCLR
ABINet
Context-Based Contrastive Learning for Scene Text Recognition
AAAI 2022 · Table 3
Human and embodied modeling
589.3ABINet-LVRead Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
CVPR 2021 · Table: Accuracy comparison wit
Human and embodied modeling
686.9SCATTER (5 Block)SCATTER: Selective Context Attentional Scene Text Recognizer
CVPR 2020 · Table 1
Attention and transformers
786.2GTC (2D) + GCN *
ResNet50
GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition
AAAI 2020 · Table 2
CNN features
886VisionLANFrom Two to One: A New Scene Text Recognizer With Visual Language Modeling Network
ICCV 2021 · Table 5
Human and embodied modeling
985.1SRN
ResNet50+FPN
Towards Accurate Scene Text Recognition With Semantic Reasoning Networks
CVPR 2020 · Table: Comparisons of scene te
Human and embodied modeling
1083.7TextScanner-mutual
ResNet-50
TextScanner: Reading Characters in Order for Robust Scene Text Recognition
AAAI 2020 · Table 1
CNN features
7 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SVTP · word accuracy

12 papers, each with its best reported number for its own method; higher is better.

#word accuracy ↑MethodPaperTopic
198.13CLIP4STR-L*
CLIP4STR-L
An Empirical Study of Scaling Law for Scene Text Recognition
CVPR 2024 · Table 11
RNNs and normalization
296.74E2STR-ICL
ViT + OPT-125M
Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
CVPR 2024 · Table 1
Human and embodied modeling
396.4OursTowards Ship License Plate Recognition in the Wild: A Large Benchmark and Strong Baseline
AAAI 2025 · Table 6
Self-supervised and contrastive
490.6S-GTR
Segmentation-based VR + SRN LM
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
AAAI 2022 · Table 1
Human and embodied modeling
590.6MATRNMulti-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
ECCV 2022 · Table 1
Cross-modal learning
687.6PREN2DPrimitive Representation Learning for Scene Text Recognition
CVPR 2021 · Table 1
Human and embodied modeling
781.7AutoSTRAutoSTR: Efficient Backbone Search for Scene Text Recognition
ECCV 2020 · Table 2
Neural architecture search
879.2Recognizer on generated images (full method)
ResNet-45 attention recognizer
Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
IJCV 2021 · Table 1
GANs
979.2ASTER + Ours
ASTER
Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
CVPR 2020 · Table: Word accuracy on irregu
Text-to-image diffusion
1077.7PerSec-ViT + UTI-100M
ViT
Perceiving Stroke-Semantic Context: Hierarchical Contrastive Learning for Robust Scene Text Recognition
AAAI 2022 · Table 3
Self-supervised and contrastive
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.