A5082021344- Advanced Steganography and Watermarking Techniques
- Medical Image Segmentation Techniques
- Advanced Image and Video Retrieval Techniques
- Chaos-based Image/Signal Encryption
- Blockchain Technology Applications and Security
- Image Retrieval and Classification Techniques
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
- Digital Media Forensic Detection
- Visual Attention and Saliency Detection
- Advanced Algorithms and Applications
- Caching and Content Delivery
- Olfactory and Sensory Function Studies
- Cryptography and Data Security
- Nonlinear Dynamics and Pattern Formation
- Recommender Systems and Techniques
- Opportunistic and Delay-Tolerant Networks
- Fluid Dynamics and Mixing
- Medical Imaging and Analysis
- Biometric Identification and Security
- Handwritten Text Recognition Techniques
- Vehicular Ad Hoc Networks (VANETs)
- Human Pose and Action Recognition
- Gene Regulatory Network Analysis
- Peer-to-Peer Network Technologies
Linyi University
2015-2025
Chinese Academy of Sciences
2005-2022
Changchun Institute of Applied Chemistry
2022
Qinghai University
2015
Zhejiang University
2014
Jilin Agricultural Science and Technology University
2013
Harbin Engineering University
2013
New Jersey Institute of Technology
2011
Tianjin University
2008-2009
Ningxia Academy of Agriculture and Forestry Sciences
2009
Land use and land cover (LULC) change analysis is a systematic technique that aids in the comprehension of physical non-physical interaction with natural habitat pursuit environmental sustainability. Research regarding LULC’s spatiotemporal changing patterns simulation future scenarios offers complete view present development possibilities. To simulate transition potential LULC simulation, we utilized multi-temporal remotely sensed big data from 1990 to 2020 10-year interval. Independent...
Vehicular social networking is an emerging application of the Internet Vehicles (IoV) which aims to achieve seamless integration vehicular networks and networks. However, unique characteristics networks, such as high mobility frequent communication interruptions, make content delivery end-users under strict delay constraints extremely challenging. In this paper, we propose a social-aware edge computing architecture that solves problem by using some vehicles in network servers can store...
In this paper, a large-scale underwater image database for salient object detection or saliency is presented in detail. This called the OUC-VISION database, which contains 4400 images of 220 individual objects. Each captured with four pose variations (the frontal-, opposite-, left-, and right-views each object) five spatial locations located at top-left corner, top-right center, bottom-left bottom-right corner) to obtain 20 images. Meanwhile, publicly available also provides relevant...
Cryptocurrency based on blockchain technology has gradually become a choice for people to invest in, and several users have participated in the accumulation of massive transaction data. Complete records blockchains openness data provide researchers with opportunities mine analyze blockchains. Network modeling analysis cryptocurrency are common methods analysis. The attribute graphs can insights into various economic indicators, illegal activities, general Internet security, among others....
Extrapolating future human motion based on the historical pose sequence is foundation of various intelligent applications. Numerous deep learning-based algorithms have been designed to address this task, achieving state-of-the-art performance different benchmark datasets. However, most existing methods employ three-dimensional coordinates joints demonstrate dynamic contexts implicitly. Unfortunately, it remains challenging in capturing information from sequence. In paper, we advocate...
Abstract Hypoxia, overexpressed glutathione (GSH) and depletable H 2 O in tumor microenvironment (TME) are three major obstacles to the development of reactive oxygen species (ROS)‐mediated antitumor therapy. Herein, a photodynamic/chemodynamic synergistic therapeutic nanoagent, DMOS@CuO /ICG‐HA (DCI), is synthesized based on copper peroxide (CuO ) indocyanine green (ICG) co‐loaded disulfide‐bond‐incorporated dendritic mesoporous organosilica (DMOS), with modification hyaluronic acid (HA)....
To tackle the problems of questioning authenticity products faced in e-commerce live streaming and low data integrity process product transactions, concept traceability a authentication scheme that integrates blockchain technology are proposed. The proposed deploys strategy on Ethereum form smart contract calls method body by executing to realize quality. A combination on-chain off-chain is used store private information guarantee integrity. Security analysis results show can make risk...
Deep learning has allowed great progress to be made in obtaining more accurate prediction results for brain tumor segmentation. The current mainstream research approaches obtain segmentation accuracy improvements by modifying deep-learning model architectures, while ignoring the computational and storage efficiency issues of In this paper, we proposed an improved knowledge distillation method: coordinate (CD), which integrates channel space information completes training student network with...
A novel watermarking technique for Chinese text is presented in this paper, based on the thought of mathematical expression a character and its automatic generation. The proposed method embeds signals into some characters with occlusive components by readjusting size closed rectangular regions these components. algorithm very simple totally content. Experiments show that more robust transparent than counterpart methods. It will play an important role protecting security documents over Internet.
Deep-learning-based registration methods can not only save time but also automatically extract deep features from images. In order to obtain better performance, many scholars use cascade networks realize a coarse-to-fine progress. However, such will increase network parameters by an n-times multiplication factor and entail long training testing stages. this paper, we in the stage. Unlike others, role of second is improve performance first function as augmented regularization term whole...
Image segmentation is the foundation of multi-flow high speed video analysis. Based on improved canny operator, we provide a method to bubble gas/liquid two-phase flow image segmentation, which takes more gray distribution information into account, uses gauss sigma smooth filter maintain edges and eliminate noise, then by non-maximum control grads lag-threshold process, clear edge obtained. The very effective for analysis recognition multi-flow.
A visual secret sharing (VSS) scheme is intended to share information in a group avoid potential treat of interruption and modification. In this paper, we present novel VSS based on the improved local binary pattern (LBP) operator. It makes full use contrast features LBP for concealing image data into different shares, which can be used recover easily exactly. By varying extensions, design various kinds schemes information. Compared currently available algorithms, proposed demonstrates...