Data to 7 Oct 2026

SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition

arXiv 2005.10977 ↗First posted 22 May 2020cs.CVcited by 119

Not on the map. Why?

Abstract (arXiv)

Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape. Nevertheless, they still face lots of challenges like image blur, uneven illumination, and incomplete characters. We argue that most encoder-decoder methods are based on local visual features without explicit global semantic information. In this work, we propose a semantics enhanced encoder-decoder framework to robustly recognize low-quality scene texts. The semantic information is used both in the encoder module for supervision and in the decoder module for initializing. In particular, the state-of-the art ASTER method is integrated into the proposed framework as an exemplar. Extensive experiments demonstrate that the proposed framework is more robust for low-quality text images, and achieves state-of-the-art results on several benchmark datasets.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 23; 2023: 24; 2024: 18; 2025: 13; 2026: 5.

119 papers.

Sort:

By area:

2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
2021From Two to One: A New Scene Text Recognizer with Visual Language Modeling Networkcited by 97
2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
2023Conditional Text Image Generation with Diffusion Modelscited by 57
2021Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Studycited by 52
2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
2022Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognitioncited by 45
2024TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Controlcited by 44
2021Split, embed and merge: An accurate table structure recognizercited by 42
2021PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognitioncited by 41

38 more

2022ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spottingcited by 40
2023DTrOCR: Decoder-only Transformer for Optical Character Recognitioncited by 40
2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
2021Multi-View Correlation Distillation for Incremental Object Detectioncited by 36
2021CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognitioncited by 36
2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
2021Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Featurescited by 34
2022MaskOCR: Text Recognition with Masked Encoder-Decoder Pretrainingcited by 34
2025ViMo: A Generative Visual GUI World Model for App Agentscited by 33
2023CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Modelcited by 30
2021Primitive Representation Learning for Scene Text Recognitioncited by 28
2021Text Gestalt: Stroke-Aware Scene Text Image Super-Resolutioncited by 28
2022Self-supervised Character-to-Character Distillation for Text Recognitioncited by 27
2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
2021Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognitioncited by 25
2022Self-supervised Implicit Glyph Attention for Text Recognitioncited by 25
2021Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognitioncited by 24
2021Dense Semantic Contrast for Self-Supervised Visual Representation Learningcited by 24
2022Levenshtein OCRcited by 24
2023Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligningcited by 24
2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
2024SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognitioncited by 23
2023Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognitioncited by 20
2023Context Perception Parallel Decoder for Scene Text Recognitioncited by 19
2023Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognitioncited by 18
2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 18
2024Instruction-Guided Scene Text Recognitioncited by 17
2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
2023CLIPTER: Looking at the Bigger Picture in Scene Text Recognitioncited by 16
2023Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognitioncited by 14
2021PERT: A Progressively Region-based Network for Scene Text Removalcited by 13
2021Towards the Unseen: Iterative Text Recognition by Distilling from Errorscited by 12
2022Towards Open-Set Text Recognition via Label-to-Prototype Learningcited by 12
2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learningcited by 12
2023IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognitioncited by 12
2021TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizerscited by 11
2022Out-of-Vocabulary Challenge Reportcited by 11
2024Out of Length Text Recognition with Sub-String Matchingcited by 11

50 most cited of 119 All 119 (JSON)