Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks122 from public data
- OCRBench: on the hidden mystery of OCR in large multimodal models574
A comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks, revealing both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression recognition.
- Monkey: Image Resolution and Text Label are Important Things for Large Multi-Modal Models485
Monkey is introduced to enhance LMM capabilities and surpasses existing LMMs in many tasks like Image Captioning and various Visual Question Answering formats, and in qualitative tests focused on dense text question answering, Monkey has exhibited encouraging results.
- ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network457
For the first time, a novel BezierAlign layer is designed for extracting accurate convolution features of a text instance with arbitrary shapes, significantly improving the precision compared with previous methods and introducing negligible computation overhead.
- Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection351
A new Convolutional Neural Networks (CNNs) based method, named Deep Matching Prior Network (DMPNet), to detect text with tighter quadrangle, which has better overall performance than L2 loss and smooth L1 loss in terms of robustness and stability.
- An efficient realization of deep learning for traffic data imputation316
This work developed an algorithm for efficient realization of deep learning for traffic data imputation by training the model hierarchically using the full set of data from all vehicle detector stations, and investigated why the deep leaning model works well for traffic Data Imputation by visualizing the features extracted by the first hidden layer.
- 310
- ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT272
This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT that consists of three major challenges: i) scene text detection, ii) sceneText recognition, and iii) scenetext spotting.
- TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document222
TextMonkey is presented, a large multimodal model (LMM) tailored for text-centric tasks and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding.
- ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling - RRC-LSVT207
This competition aims to explore the abilities of state-of-the-art methods to detect and recognize text instances from large-scale street view images, closing gaps between research benchmarks and real applications.
- ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting189
This work adaptively fit arbitrarily-shaped text by a parameterized Bezier curve, which, compared with segmentation-based methods, can not only provide structured output but also controllable representation, which can be valuable for real-time applications.
- SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition167
A new end-to-end scene text spotting framework termed SwinTextSpotter is proposed, using a transformer encoder with dynamic head as the detector and a novel Recognition Conversion mechanism to explicitly guide text localization through recognition loss.
- On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering132
A dataset that takes a step towards addressing the VQA problem in that it contains questions expressed in two languages, and an evaluation process that co-opts a well understood image-based metric to reflect the method’s ability to reason.
- Aggregation Cross-Entropy for Sequence Recognition124
This paper proposes a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective, which requires only characters and their numbers in the sequence annotation for supervision, which allows it to advance beyond sequence recognition, e.g., counting problem.
- Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization109
This paper proposes an efficient video decomposition that represents each video as keyframes and temporal motions, then adapted to an LLM using well-designed tokenizers that discretize visual and temporal information as a few tokens, thus enabling unified generative pre-training of videos, images, and text.
- 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.
- SPTS v2: Single-Point Scene Text Spotting99
The SPTS v2 can outperform previous state-of-the-art single-point text spotters with fewer parameters while achieving 19× faster inference speed and experiments suggest a potential preference for single- point representation in scene text spotting when compared to other representations.
- Turning a CLIP Model into a Scene Text Detector96
This paper proposes a new method, termed TCM, focusing on Turning the CLIP Model directly for text detection without pretraining process, and achieves promising domain adaptation ability.
- SPTS: Single-Point Text Spotting84
This work demonstrates that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance, and shows that the performance is not very sensitive to the positions of the point annotation, meaning that it can be much easier to be annotated or even be automatically generated than the bounding box that requires precise positions.
- 82
- TextSquare: Scaling up Text-Centric Visual Instruction Tuning79
A new approach for creating a massive, high-quality instruction-tuning dataset, Square-10M, which is generated using closed-source MLLMs and considerably surpasses open-source previous state-of-the-art Text-centric MLLMs, and sets a new standard on OCRBench.
- Structured Multimodal Attentions for TextVQA73
This paper proposes an end-to-end structured multimodal attention (SMA) neural network that outperforms the SoTA models on TextVQA dataset and two tasks of ST-VQ a dataset among all models except pre-training based TAP.
- 69
- 63
- 62
- Feature Enhancement Network: A Refined Scene Text Detector57
A new FEN network with task-specific, low and high level semantic features fusion to improve the performance of text detection and an effective positives mining strategy for efficiently training the network is proposed.
- ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer54
This paper introduces a new model named Explicit Synergy-based Text Spotting Transformer framework (ESTextSpotter), which achieves explicit synergy by modeling discriminative and interactive features for text detection and recognition within a single decoder.
- DeRPN: Taking a Further Step toward More General Object Detection52
A novel dimension-decomposition region proposal network (DeRPN) that can perfectly displace the traditional Region Proposal Network (RPN), which utilizes an anchor string mechanism to independently match object widths and heights, which is conducive to treating variant object shapes.
- 48
- 38
- Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild38
This work proposes an adversarial learning framework for the generation and recognition of multiple characters in an image, which consists of an attention-based recognizer and a generative adversarial architecture, and designs an interactive joint training scheme to tackle the issue of lacking paired training samples.
- An open dataset for oracle bone character recognition and decipherment37
This dataset encompasses 77,064 images of 1,588 individual deciphered characters and 62,989 images of 9,411 undeciphered characters, with a total of 140,053 images, compiled from diverse sources, and the hope is that this dataset could inspire and assist future research in deciphering those unknown OBCs.
- PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition36
Extensive experiments conducted on five datasets demonstrate the superiority of PageNet over existing weakly supervised and fully supervised page-level methods, and may spark further research beyond the realms of existing methods based on connectionist temporal classification or attention.
- 36
- Tightness-Aware Evaluation Protocol for Scene Text Detection34
A novel evaluation protocol called Tightness-aware Intersect-over-Union (TIoU) metric that could quantify completeness of ground truth, compactness of detection, and tightness of matching degree is proposed.
- 33
- Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection33
A new method, Orderless Box Discretization (OBD), which first discretizes the quadrilateral box into several key edges containing all potential horizontal and vertical positions is proposed, which solves the ambiguity issue and achieves state-of-the-art performance on various benchmarks, including ICDAR 2015 and MLT.
- Semantic Segmentation of Hyperspectral Remote Sensing Images Based on PSE-UNet Model29
The experimental results with the Salinas dataset show that the PSE-UNet is superior to other semantic segmentation algorithms and the results can provide a reference for HSRSI semantics segmentation.
- Turning a CLIP Model Into a Scene Text Spotter27
This work exploits the potential of the large-scale Contrastive Language-Image Pretraining model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50, which showcases robust few-shot training capabilities.
- SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting24
A new end-to-end scene text spotting framework termed SwinTextSpotter v2 is proposed, which seeks to find a better synergy between text detection and recognition and enhances the relationship between two tasks using novel Recognition Conversion and Recognition Alignment modules.
- 24
- 23
- AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence23
This work proposes AdaptiveStep, a method that divides reasoning steps based on the model's confidence in predicting the next word, which provides more decision-making information at each step, enhancing downstream tasks, such as reward model learning.
- Managing Impression Formation in Computer-Mediated Communication.23
Based on the research and teaching experience, this work recommends a variety of impression management strategies for online instructors and others engaged in CMC.
- 22
- 21
- 21
- 20
- DocThinker: Explainable Multimodal Large Language Models with Rule-Based Reinforcement Learning for Document Understanding19
This paper proposes DocThinker, a rule-based Reinforcement Learning (RL) framework for dynamic inference-time reasoning that mitigates catastrophic forgetting and enhances both adaptability and transparency in MLLMbased document understanding.
- Robust License Plate Recognition With Shared Adversarial Training Network18
An effective and efficient shared adversarial training network (SATN) is proposed in this paper, which can learn the environment-independent and perspective-free semantic features from wild license plates with the prior knowledge of standard stencil-rendered license plates, as standards are independent of complicated environments and various perspectives.
- 17
- 16
- An open dataset for oracle bone script recognition and decipherment16
The creation of the HUST-OBS dataset, which encompasses 77,064 images of 1,588 individual deciphered scripts and 62,989 images of 9,411 undeciphered characters, with a total of 140,053 images, compiled from diverse sources is detailed.
- 12
- 11
- Privacy-Preserving Biometric Verification With Handwritten Random Digit String10
This work underscores the feasibility of privacy-preserving biometric verification and propels the prospects of its broader acceptance and application through comprehensive evaluations of the applicability of online RDS verification and showcases a pronounced outperformance of the model over existing methods.
- 10
- 10
- [Study on dynamic spectrum and its frequency domain extracting method].10
A new method of detecting blood components is presented, which is based on the principle of photoplethysmography and Fourier transform, and it is shown that the method can be realized and has many advantages.
- VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning8
This work investigates the bottlenecks in current MLLMs and synthesizes training data to improve their abstract visual perception, and introduces the Perceptual Riddle Synthesizer (PRS), an automated framework for generating riddles with fine-grained perceptual descriptions.
- Lesion-aware attention network for diabetic nephropathy diagnosis with optical coherence tomography images8
The proposed lesion-aware attention model can provide reliable screening of high-risk patients with diabetic nephropathy from retinal images of diabetic patients and performs even better in disease classification.
- 8
- 8
- Impact of Online Instruction on Teachers’ Learning and Attitudes toward Technology Integration8
Online instruction significantly promoted online learner’s concern only in stage 2-personal stage, and no significant differences were found in students’ final course grades between two groups, and Implications for K-12 teacher education were proposed.
- 7
- 6
- 6
- SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting5
A new Semi-supervised framework for End-to-end Text Spotting, namely SemiETS that leverages the complementarity of text detection and recognition and gradually generates reliable hierarchical pseudo labels for each task, thereby reducing noisy labels.
- VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization5
This paper introduces a new method, termed VimTS, which enhances the generalization ability of the model by achieving better synergy among different tasks, and proposes a synthetic video text dataset (VTD-368 k) by leveraging the Content Deformation Fields (CoDeF) algorithm.
- Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection.5
The proposed Sequential-free Box Discretization (SBD) departs from the learning ambiguity which has a significant influence during the learning process, and achieves state-of-the-art performance on various benchmarks, including ICDAR 2015, and MLT.
- 4
- 4
- KwaiYiiMath: Technical Report4
The KwaiyiiMath is introduced, which enhances the mathematical reasoning abilities of KwaiYiiBase1, by applying Supervised Fine-Tuning (SFT) and Reinforced Learning from Human Feedback (RLHF), including on both English and Chinese mathematical tasks.
- 4
- 4
- ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment4
A text on chips dataset, ICText is used as the main target for the proposed Robust Reading Challenge on Integrated Circuit Text Spotting and Aesthetic Assessment (RRC-ICText) 2021 to encourage the research on this problem.
- Robust Adaptive Learning Control for Spacecraft Autonomous Proximity Maneuver4
The robust adaptive learning control for spacecraft autonomous proximity is investigated and the asymptotic stability of the proposed controllers for the closed-loop systems is proven based on the Lyapunov theory.
- 4
- 4
- Distance and Traditional Education Teaching the Same Course via Instructional Television and Traditional Educational Formats: A Case Study4
It is suggested that the instructor who teaches the same course in both ITV and traditional education formats exhibits both similarities and differences among the three instructional phases (before-class, in- class, and after-class) in both situations.
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- A robust heart rate measurement framework based on videos2
Noise robustness of diverse methods employed in rPPG-based physiological measurement, including face detection and tracking, region of interest (ROI) selection, rPPG signal extraction and heart rate calculation are assessed.
- 2
- 2
- On Point Affiliation in Feature Upsampling2
It is shown that an upsampled point can resort to its low-res decoder neighbors and high-res encoder point to reason the affiliation, conditioned on the mutual similarity between them, and it is proved that such kernels encourage not only semantic smoothness but also boundary sharpness.
- 2
- 2
- 2
- Distance and Traditional Education2
It is suggested that the instructor who teaches the same course in both ITV and traditional education formats exhibits both similarities and differences among the three instructional phases (before-class, in- class, and after-class) in both situations.
- 1
- AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning1
AlphaOracle is introduced, a human-workflow-inspired framework that systematizes OBS decipherment using the largest digitized corpus to date and resolves the character"Lao"as a toponymic or clan designation, offering concrete revisions to Shang administrative and social interpretations.
- 1
- 1
- Looking and Listening: Audio Guided Text Recognition1
The AudioOCR is proposed, a simple yet effective probabilistic audio decoder for mel spectrogram sequence prediction to guide the scene text recognition, which only participates in the training phase and brings no extra cost during the inference stage.
- An improved image segmentation algorithm for monitoring height growth of bamboo shoots1
Computer simulation results show that the growth information such as position and height relationship of bamboo shoots, is accurately obtained by the novel image segmentation algorithm proposed in this paper.
- 1
- 1
- Underwater range-gated laser imaging enhancement based on contrast-limited adaptive histogram equalization1
The experimental results demonstrate that the CLAHE has a good result of image enhancement for target detection by underwater range-gated laser imaging system.
- 1
- 1
- 1
- Application of a Wavelet Adaptive Filter Based on Neural Network to Minimize Distortion of the Pulsatile Spectrum1
This wavelet adaptive filter based on Adaptive Linear Neuron networks is used to extract the signal of the pulse wave and is found to be very effective in detection of symptoms from pulsatile part of the entire optical signal.
- –
- –
- –
- –
- –
- –
- CTRNet++: Dual-Path Learning with Local-Global Context Modeling for Scene Text Removal–
Experiments on benchmark datasets, SCUT-EnsText and SCUT-Syn, demonstrate that CTRNet++ significantly outperforms existing state-of-the-art methods and exhibits a stronger ability for complex background reconstruction.
- –
- Image Marketing Methods for Submarine Manganese Nodule Statistics–
In order to improve statistics speed and accuracy of submarine manganese nodule particles, two image marking methods are discussed in this paper and it is shown that statistics accuracy of both the methods is similar.
- Implementation of Traffic Control Algorithm on PARAMICS Platform Using MATLAB Language–
Through file-sharing method, the mechanism of data exchange between PARAMICS platform and MATLAB is established and the logical structure and algorithm of the system are described in detail.
- Research on ADHDP Based Traffic Signal Control Method–
Experimental results show that compared with traditional Fix-Time Control, the ADHDP method has the ability of on-line learning, can effectively improve the average speed of vehicles and reduce traffic congestion.
- –
- –
- Signal area extraction in range-gated images using average gray value information–
The algorithm can handle images under the impact of EBE effect, reduce the noise in the images and segment the objects from the noise area effectively without many morphological operations which keeps the certain figure from distortion.
- –
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 2026-10-15. 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.