A5074514262- Handwritten Text Recognition Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Image Retrieval and Classification Techniques
- Vehicle License Plate Recognition
- Natural Language Processing Techniques
- Text and Document Classification Technologies
- Video Surveillance and Tracking Methods
- Speech Recognition and Synthesis
- Image Processing and 3D Reconstruction
- Multimodal Machine Learning Applications
- Domain Adaptation and Few-Shot Learning
- Face and Expression Recognition
- Topic Modeling
- Video Analysis and Summarization
- Speech and Audio Processing
- Web Data Mining and Analysis
- Music and Audio Processing
- Biomedical Text Mining and Ontologies
- Advanced Image Processing Techniques
- Machine Learning and Data Classification
- Recommender Systems and Techniques
- Face recognition and analysis
- Remote-Sensing Image Classification
- Information Retrieval and Search Behavior
University of Science and Technology Beijing
2016-2025
Beijing Institute of Technology
2025
Technical University of Munich
2025
Chongqing University of Technology
2025
First Affiliated Hospital of Hunan University of Traditional Chinese Medicine
2025
Soochow University
2025
China Earthquake Administration
2021-2024
Nanjing University of Posts and Telecommunications
2024
Hebei University of Architecture
2022-2024
Heilongjiang Earthquake Agency
2024
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks. In this paper, we propose accurate and robust method detecting texts images. A fast effective pruning algorithm designed to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations. Character are grouped into text by single-link clustering algorithm, where distance weights threshold learned automatically a...
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks, while most current research efforts only focus on horizontal or near text. In this paper, first we present a unified distance metric learning framework adaptive hierarchical clustering, which can simultaneously learn similarity weights (to adaptively combine different feature similarities) and the clustering threshold automatically determine number of clusters). Then, propose...
Arbitrary shape text detection is a challenging task due to the high variety and complexity of scenes texts. In this paper, we propose novel unified relational reasoning graph network for arbitrary detection. our method, an innovative local bridges proposal model via Convolutional Neural Network (CNN) deep Graph (GCN), making end-to-end trainable. To be concrete, every instance will divided into series small rectangular components, geometry attributes (e.g., height, width, orientation)...
The intelligent analysis of video data is currently in wide demand because a major source sensory our lives. Text prominent and direct information video, while the recent surveys text detection recognition imagery focus mainly on extraction from scene images. Here, this paper presents comprehensive survey detection, tracking, with three contributions. First, generic framework proposed for that uniformly describes recognition, their relations interactions. Second, within framework, variety...
Autism Spectrum Disorder (ASD) is a lifelong neurodevelopmental condition characterized by atypical brain growth. While advances in neuroimaging and openly sharing large-sample datasets such as the Brain Imaging Data Exchange (ABIDE) have improved understanding of ASD, most studies focus on adolescents adults, with early development-critical for diagnosis intervention-remaining underexplored. Existing research predominantly involves Western samples, offering limited insight generalizability...
Graph matching, which refers to a class of computational problems finding an optimal correspondence between the vertices graphs minimize (maximize) their node and edge disagreements (affinities), is fundamental problem in computer science relates many areas such as combinatorics, pattern recognition, multimedia vision. Compared with exact graph (sub)isomorphism often considered theoretical setting, inexact weighted matching receives more attentions due its flexibility practical utility. A...
Arbitrary shape text detection is a challenging task due to the high complexity and variety of scene texts. In this work, we propose novel adaptive boundary proposal network for arbitrary detection, which can learn directly produce accurate without any post-processing. Our method mainly consists model an innovative deformation model. The constructed by multi-layer dilated convolutions adopted prior information (including classification map, distance field, direction field) coarse proposals....
In arbitrary shape text detection, locating accurate boundaries is challenging and non-trivial. Existing methods often suffer from indirect boundary modeling or complex post-processing. this article, we systematically present a unified coarse-to-fine framework via learning for which can accurately efficiently locate without our method, explicitly model the an innovative iterative transformer in manner. way, method directly gain abandon post-processing to improve efficiency. Specifically,...
Detecting pedestrians accurately in urban scenes is significant for realistic applications like autonomous driving or video surveillance. However, confusing human-like objects often lead to wrong detections, and small scale heavily occluded are easily missed due their unusual appearances. To address these challenges, only object regions inadequate, thus how fully utilize more explicit semantic contexts becomes a key problem. Meanwhile, previous context-aware pedestrian detectors either learn...
Video text extraction plays an important role for multimedia understanding and retrieval. Most previous research efforts are conducted within individual frames. A few of recent methods, which pay attention to tracking using multiple frames, however, do not effectively mine the relations among detection, recognition. In this paper, we propose a generic Bayesian-based framework Tracking based Text Detection And Recognition (T DAR) from web videos embedded captions, is composed three major...
Arbitrary shape text detection is a challenging task due to the significantly varied sizes and aspect ratios, arbitrary orientations or shapes, inaccurate annotations, etc. Due scalability of pixel-level prediction, segmentation-based methods can adapt various texts hence attracted considerable attention recently. However, accurate annotations are formidable, existing datasets for scene only provide coarse-grained boundary annotations. Consequently, numerous misclassified pixels background...
Although existing image deep learning super-resolution (SR) methods achieve promising performance on benchmark datasets, they still suffer from severe drops when the degradation of low-resolution (LR) input is not covered in training. To address problem, we propose an innovative unsupervised method Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution. Highly inspired by generalized sampling theory, our aims to enhance strength off-the-shelf...
Scene text spotting is a challenging task, especially for inverse-like scene text, which has complex layouts, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., mirrored, symmetrical, or retro-flexed. In this paper, we propose unified end-to-end trainable antagonistic framework dubbed IATS, can effectively spot texts without sacrificing general ones. Specifically, an innovative reading-order estimation module (REM) that extracts...
Vehicle and license plate detection plays an important role in intelligent transportation systems is still a challenging task real applications, such as on-road scenarios. Recently, Convolutional Neural Network (CNN)-based detectors achieve the state-of-the-art performance. However, it difficult to efficiently detect vehicle simultaneously most cases. With single network, can affect of due inclusion relation. In this paper, we propose end-to-end deep neural network for detecting given image,...
The open-set text recognition task is an emerging chal-lenge that requires extra capability to cognize novel characters during evaluation. We argue a major cause of the limited performance for current methods con-founding effect contextual information over visual individual characters. Under sce-narios, intractable bias in can be passed down information, consequently im-pairing classification performance. In this paper, Character-Context Decoupling framework proposed alleviate problem by...
There are a variety of grand challenges for multi-orientation text detection in scene videos, where the typical issues include skew distortion, low contrast, and arbitrary motion. Most conventional video methods using individual frames have limited performance. In this paper, we propose novel tracking based method multiple within unified framework via dynamic programming. First, multi-information fusion-based each frame is proposed to extensively locate possible character candidates extract...
Segmentation-based methods have achieved great success for arbitrary shape text detection. However, separating neighboring instances is still one of the most challenging problems due to complexity texts in scene images. In this article, we propose an innovative kernel proposal network (dubbed KPN) The proposed KPN can separate by classifying different into instance-independent feature maps, meanwhile avoiding complex aggregation process existing segmentation-based detection methods. To be...