Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Shigeru NawanoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works79 from public data
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition3,175
A novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, is proposed, which generates an effective yet much smaller model, which is more practical for real-world application scenarios.
- EAST: An Efficient and Accurate Scene Text Detector1,850
This work proposes a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes, and significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency.
- 906
- Real-Time Scene Text Detection with Differentiable Binarization891
This paper proposes a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network, and validate the performance improvements of DB on five benchmark datasets, which consistently achieves state-of-the-art results, in terms of both detection accuracy and speed.
- 879
- Robust Scene Text Recognition with Automatic Rectification693
RARE (Robust text recognizer with Automatic REctification), a recognition model that is robust to irregular text, which is end-to-end trainable, requiring only images and associated text labels, making it convenient to train and deploy the model in practical systems.
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes650
The recognition module of the Mask TextSpotter method is investigated separately, which significantly outperforms state-of-the-art methods on both regular and irregular text datasets for scene text recognition.
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes636
A more flexible representation for scene text is proposed, termed as TextSnake, which is able to effectively represent text instances in horizontal, oriented and curved forms and outperforms the baseline on Total-Text by more than 40% in F-measure.
- Multi-oriented Text Detection with Fully Convolutional Networks596
A novel approach for text detection in natural images that consistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, I CDAR2015 and ICDAR2013.
- Scene Text Detection and Recognition: The Deep Learning Era527
This survey is aimed at summarizing and analyzing the major changes and significant progresses of scene text detection and recognition in the deep learning era.
- Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion431
A Differentiable Binarization (DB) module that integrates the binarization process, one of the most important steps in the post-processing procedure, into a segmentation network is proposed and an efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively.
- Scene text detection and recognition: recent advances and future trends402
This literature review can serve as a good reference for researchers in the areas of scene text detection and recognition and identify state-of-the-art algorithms, and predict potential research directions in the future.
- Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation389
This paper proposes to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions and achieves better or comparable results in both accuracy and efficiency.
- 343
- 310
- 278
- ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)256
This report introduces RCTW, a new competition that focuses on Chinese text reading with a large-scale dataset with over 12,000 annotated images and calls for more future research on the Chinese textReading problem.
- Scene Text Recognition from Two-Dimensional Perspective251
A simple yet effective model, called Character Attention Fully Convolutional Network (CA-FCN), is devised for recognizing the text of arbitrary shapes with a semantic segmentation network, where an attention mechanism for characters is adopted.
- Scene Text Detection with Supervised Pyramid Context Network238
A supervised pyramid context network (SPCNET) is proposed to precisely locate text regions while suppressing false positives in scene text detection, based on Feature Pyramid Network (FPN) and instance segmentation.
- Deep Learning Representation using Autoencoder for 3D Shape Retrieval187
This work projects 3D shapes into 2D space and uses autoencoder for feature learning on the 2D images and shows the proposed deep learning feature is complementary to conventional local image descriptors, which can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.
- 185
- LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding163
Experiments show that the proposed LayoutLLM significantly outperforms existing methods that adopt open-source 7B LLMs/MLLMs for document understanding, and brings a certain degree of interpretability, which could facilitate manual inspection and correction.
- TextScanner: Reading Characters in Order for Robust Scene Text Recognition162
TextScanner bears three characteristics: it belongs to the semantic segmentation family, as it generates pixel-wise, multi-channel segmentation maps for character class, position and order, and also adopts RNN for context modeling.
- Symmetry-Constrained Rectification Network for Scene Text Recognition153
A Symmetry-constrained Rectification Network (ScRN) based on local attributes of text instances, such as center line, scale and orientation, which enables ScRN to generate better rectification results than existing methods and thus lead to higher recognition accuracy.
- Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis152
This work treats the calligraphy synthesis problem as an image-to-image translation problem and proposes a deep neural network based model which can generate calligraphY images from standard font images directly.
- Script identification in the wild via discriminative convolutional neural network128
The proposed DiscCNN achieves state-of-the-art performances on scene, video and document scripts as well, not requiring any preprocess like binarization, segmentation or hand-crafted features.
- Conditional Text Image Generation with Diffusion Models115
The proposed CTIG-DM is able to produce image samples that simulate real-world complexity and diversity, and thus can boost the performance of existing text recognizers and shows its appealing potential in domain adaptation and generating images containing Out-Of-Vocabulary words.
- 109
- OMNIPARSER: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition107
A universal model, called OmniParser, which can simultaneously handle three typical visually-situated text parsing tasks: text spotting, key information extraction, and table recognition is devised, which achieves state-of-the-art or highly competitive performances on 7 datasets for the three visually-situated text parsing tasks, despite its unified, concise design.
- MOST: A Multi-Oriented Scene Text Detector with Localization Refinement105
A new algorithm for scene text detection is proposed, which puts forward a set of strategies to significantly improve the quality of text localization and achieves state-of-the-art or competitive performance on various standard benchmarks for text detection while keeping a fast running speed.
- 99
- Relaxed Multiple-Instance SVM with Application to Object Discovery90
This paper proposes a novel method to solve the classical MIL problem, named relaxed multiple-instance SVM (RMI-SVM), which treats the positiveness of instance as a continuous variable, use Noisy-OR model to enforce the MIL constraints, and optimize them jointly in a unified framework.
- 78
- On Vocabulary Reliance in Scene Text Recognition72
An analytical framework is established, in which different datasets, metrics and module combinations for quantitative comparisons are devised, to conduct an in-depth study on the problem of vocabulary reliance in scene text recognition, and a simple yet effective mutual learning strategy is proposed to allow models of two families to learn collaboratively.
- Automatic script identification in the wild57
A large-scale dataset with a great quantity of natural images and 10 types of widely-used languages is constructed and a deep learning based algorithm is proposed for script identification at word or line levels in natural scenes.
- Differentiable Feature Aggregation Search for Knowledge Distillation56
This work introduces DFA, a two-stage Differentiable Feature Aggregation search method that motivated by DARTS in neural architecture search, to efficiently find the aggregations in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps.
- 56
- SynthText3D: synthesizing scene text images from 3D virtual worlds53
This paper proposes to synthesize scene text images from the 3D virtual worlds, where the precise descriptions of scenes, editable illumination/visibility, and realistic physics are provided.
- 47
- Shape Recognition by Combining Contour and Skeleton into a Mid-Level Representation45
The proposed shape descriptor provides the complementary geometric information from both contour and skeleton parts, including the spatial distribution and the thickness change along the shape part, which achieves the state-of-the-art performances on several standard shape benchmarks.
- Vision-Language Pre-Training for Boosting Scene Text Detectors42
This paper proposes to learn contextualized, joint representations through vision-language pretraining, for the sake of enhancing the performance of scene text detectors, and devise a pre-training architecture with an image encoder, a text encoder and a cross-modal encoder.
- 39
- Facial Attribute Transformers for Precise and Robust Makeup Transfer33
Extensive qualitative and quantitative experiments demonstrate the effectiveness and superiority of the proposed FATs in the following aspects: ensuring high-fidelity color transfer; allowing for geometric transformation of facial parts; handling facial variations and supporting high-resolution face generation.
- Rotation-Invariant Features for Multi-Oriented Text Detection in Natural Images31
A new algorithm to detect texts of varying orientations is proposed, based on a two-level classification scheme and two sets of features specially designed for capturing the intrinsic characteristics of texts, which achieves significantly enhanced performance on variant texts in complex natural scenes.
- Human Detection Using Learned Part Alphabet and Pose Dictionary30
A compositional model for human detection in natural scenes using a discriminative alphabet, each grapheme of which is a mid-level element representing a body part, which correspond to various human poses and allow for robust, efficient matching.
- 29
- 26
- 24
- HierCode: A lightweight hierarchical codebook for zero-shot Chinese text recognition22
HierCode is proposed, a novel and lightweight codebook that exploits the innate hierarchical nature of Chinese characters and employs a multi-hot encoding strategy, leveraging hierarchical binary tree encoding and prototype learning to create distinctive, informative representations for each character.
- 21
- 20
- 17
- 16
- 16
- A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling15
A pair of coupling modules are proposed, termed as Character Anchoring Module (CAM) and Anchor Pooling Module (APM), to extract high-level semantics from two-dimensional space to form feature sequences to surpass previous state-of-the-art scores on irregular and perspective text datasets.
- 13
- Multiple Stage Residual Model for Accurate Image Classification12
This paper proposes an effective and efficient model, which is called Multiple Stage Residual Model (MSRM), to make full use of the residual vector to generate a multiple stage code.
- Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition11
A Line-Aware Semi-autoregressive Transformer that treats multi-line mathematical expression sequences as two-dimensional dual-end structures and achieves significantly faster decoding speeds while still achieving state-of-the-art performance compared to the existing methods is proposed.
- 9
- 8
- 7
- 6
- 6
- 5
- 4
- Generative compositor for few-shot visual information extraction3
A novel generative model, named Generative Compositor, is proposed to address the challenge of few-shot VIE, a hybrid pointer-generator network that emulates the operations of a compositor by retrieving words from the source text and assembling them based on the provided prompts.
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.