A5100735597- Robotics and Sensor-Based Localization
- Advanced Image and Video Retrieval Techniques
- AI in cancer detection
- Advanced Vision and Imaging
- Text and Document Classification Technologies
- Domain Adaptation and Few-Shot Learning
- Face and Expression Recognition
- Music and Audio Processing
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- 3D Surveying and Cultural Heritage
- Image and Object Detection Techniques
- Advanced Neural Network Applications
- Image Processing Techniques and Applications
- 3D Shape Modeling and Analysis
- Medical Image Segmentation Techniques
- Video Surveillance and Tracking Methods
- Remote-Sensing Image Classification
- Robotic Path Planning Algorithms
- Image and Signal Denoising Methods
- Advanced Computing and Algorithms
- Retinal Imaging and Analysis
- COVID-19 diagnosis using AI
- Advanced Image Processing Techniques
- Digital Imaging for Blood Diseases
Shandong Transportation Research Institute
2025
Xi'an Jiaotong University
2014-2024
Yunnan University
2024
Northeast Agricultural University
2015-2024
Xi’an University
2023
Xi'an University of Technology
2010-2023
China Southern Power Grid (China)
2022
Shanghai Tunnel Engineering Rail Transit Design & Research Institute
2022
Ningbo University
2021
California Maritime Academy
2021
Recently, label distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from labelel instances. Different single-label and multi-label annotations, distributions describe the instance by multiple labels with different intensities accommodate to more general scenes. Since most existing datasets merely provide logical labels, are unavailable many real-world applications. To handle this problem, we propose two novel enhancement methods, i.e., Label...
Current antiviral therapy for the chronic hepatitis B virus (HBV) has a low clinical cure rate, high administration frequency, and limited efficacy in reducing HBsAg levels, leading to poor patient compliance. Novel agents are required achieve HBV functional cure, reduction of antigenemia may enhance activation effective long-lasting host immune control. HT-101 is siRNA currently phase I trials with promising prospects future applications. By designing synthesizing targeting conserved S...
The intersection of medical imaging and artificial intelligence has become an important research direction in intelligent treatment, particularly the analysis images using deep learning for clinical diagnosis. Despite advances, existing keyframe classification methods lack extraction time series features, while ultrasonic video based on three-dimensional convolution requires uniform frame numbers across patients, resulting poor feature efficiency model performance. This study proposes a...
This study focuses on the optimization of electric vehicle delivery routes for multiple distribution centers, proposing a dynamic route model based an improved Plant Growth Simulation Algorithm (PGSA). Inspired by growth mechanisms plants in nature, PGSA simulates behavior under light and resource distribution. According to knowledge molecular cellular biomechanics, process can be seen as series mechanical biological responses. By simulating this behavior, optimizes path selection through...
In this paper, we delve into the challenging problem in multi-view learning, namely unsupervised representation goal of which is to effectively integrate information from multiple views and learn unified feature with comprehensive an manner. Despite progress attained recent years, it still a issue since correlations across are complex difficult model during learning process, especially absence label information. To address problem, introduce novel method, termed Collaborative Unsupervised...
Without the valuable label information to guide learning process, it is demanding fully excavate and integrate underlying from different views learn unified multi-view representation. This paper focuses on this challenge presents a novel method, termed Graph-guided Unsupervised Multi-view Representation Learning (GUMRL), taking full advantage of graph during process. To be specific, GUMRL jointly conducts view-specific feature representation learning, which under guidance information, fuses...
Recently, genetic algorithm (GA) has been introduced as an effective method to solve the registration problem. It maintains a population of candidate solutions for problem and evolves by iteratively applying set stochastic operators. Accordingly, key question is how reduce size. In this study, authors present two techniques reducing size in GA partially overlapping point sets. Based on trimmed iterative closest algorithm, they introduce growth operator into GA. The operator, which also...
To address the surface reconstruction issue, this paper proposes an efficient and accurate approach for registration of multiview range scans. It has a good objective function designed, where all parameters are involved. solve function, coarse-to-fine is proposed, each scan should be sequentially registered to coarse model, which reconstructed by other scans with initial alignment. By applying trimmed iterative closest point algorithm, it can obtain results scan, then immediately utilized...
Compared with single-label and multi-label annotations, label distribution describes the instance by multiple labels different intensities accommodates to more-general conditions. Nevertheless, learning is unavailable in many real-world applications because most existing datasets merely provide logical labels. To handle this problem, a novel enhancement method, Label Enhancement Sample Correlations via low-rank representation, proposed paper. Unlike methods, representation method employed so...
Electrical impedance tomography (EIT) is a noninvasive and radiation-free imaging method. As "soft-field" technique, in EIT, the target signal center of measured field frequently swamped by at edge, which restricts its further application. To alleviate this problem, study presents an enhanced encoder-decoder (EED) method with atrous spatial pyramid pooling (ASPP) module. The proposed enhances ability to detect central weak targets constructing ASPP module that integrates multiscale...
Multi-view registration plays a critical role in 3D model reconstruction. To solve this problem, most previous methods align point sets by either partially exploring available information or blindly utilizing unnecessary information, which may lead to undesired results extra computation complexity. Accordingly, we propose novel solution for the multi-view under perspective of Expectation-Maximization (EM). The proposed method assumes that each data is generated from one unique Gaussian...