52 Result(s)
-
Article
Open AccessA Parallel Model for Jointly Extracting Entities and Relations
Extracting relational triples from a piece of text is an essential task in knowledge graph construction. However, most existing methods either identify entities before predicting their relations, or detect rel...
-
Chapter and Conference Paper
Adaptive Fuzzy Fault-Tolerant Event-Triggered Consensus for Switched Nonlinear Multi-agent Systems
In this paper, an adaptive fuzzy fault-tolerant event-triggered consensus problem is considered for the switched nonlinear multi-agent systems (SNMASs). In the considered systems, the dynamics of agents are sw...
-
Chapter and Conference Paper
Enhancing Multi-physics Coupling on ARM Many-Core Cluster
In scientific and engineering computing, there are a large number of complex physical simulations involving multiple physical fields. This complex physical simulation in which multiple physical fields superimp...
-
Article
Deep Constraints Space of Medium Modality for RGB-Infrared Person Re-identification
Reducing the gap between modalities is key to RGB-Infrared cross-modality person re-identification. In this paper, we propose an architecture based on the Deep Constrains Space of Medium Modality (DCSMM) for R...
-
Chapter and Conference Paper
An Adaptive Feature Fusion Network for Alzheimer’s Disease Prediction
Structural Magnetic Resonance Imaging (sMRI) of brain structures has proven effective in predicting early lesions associated with Alzheimer’s disease (AD). However, identifying the AD lesion area solely throug...
-
Chapter and Conference Paper
Ascent Phase Trajectory Optimization for Hypersonic Vehicle Using hp-Adaptive Pseudo-spectral Method
An improved hp adaptive pseudo-spectral method ia scaling parameters designed for the hypersonic vehicle trajectory optimization problem. In this paper, we take hypersonic vehicle as the research object, consi...
-
Article
Gaussian-based probability fusion for person re-identification with Taylor angular margin loss
Person re-identification (ReID) aims to match the specific pedestrians in the public environment with cross-domain cameras. Posture change, occlusion, and viewpoint change complicate ReID. Representation learn...
-
Article
Joining features by global guidance with bi-relevance trihard loss for person re-identification
Person re-identification (ReID) aims to associate the person with the given identity across different cameras, which has wide application in the field of intelligent video. In this work, an efficient method is...
-
Article
TriEP: Expansion-Pool TriHard Loss for Person Re-Identification
Person re-identification aims to identify the same person across different cameras, which is widely applied in the intelligent monitoring field. The research of TriHard loss has been verified to improve perfor...
-
Chapter and Conference Paper
Mitigating Targeted Bit-Flip Attacks via Data Augmentation: An Empirical Study
As deep neural networks (DNNs) become more widely used in various safety-critical applications, protecting their security has been an urgent and important task. Recently, one critical security issue is propose...
-
Chapter and Conference Paper
PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform
Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which le...
-
Chapter and Conference Paper
Group Consensus Control for Networked Lagrange Systems Under the Switching Parameters and Topology Based on Average Dwell Time Approach
This brief mainly focus on the group consensus problem for networked Euler-Lagrange systems in the presence of parameters and communication topologies switching. A unified group consensus control protocol is d...
-
Chapter
Leveraging Artificial Intelligence Capabilities for Real-Time Monitoring of Cybersecurity Threats
The number of cybersecurity incidents perpetrated by adversaries using modern complex and emerging technologies is growing exponentially. To curb this threat, advanced countermeasures need to be developed and ...
-
Chapter
Network Forensics in the Era of Artificial Intelligence
Network forensics investigates a network attack by tracing the source of the attack and attributing the crime to a person, host or network. It can anticipate prospective attacks by establishing attack patterns...
-
Chapter and Conference Paper
On Building a Knowledge Graph of Open Courses
To help online learners to efficiently get open courses they want to learn, we build a large knowledge graph of open courses. Our knowledge graph contains structured information of a large number of open cours...
-
Chapter and Conference Paper
Design and Engineering Realization of the Joint for Chang’E-5 Surface Sampling Arm
Joints are the basis for the dexterous movement and precise positioning of China Chang’E-5(CE-5) Surface Sampling Arm which had successfully completed the lunar soil sampling. The sampling arm consists of four...
-
Chapter and Conference Paper
Wheel and Track Hybrid Planetary Surface Locomotion Mechanism
Presently, most of the planetary locomotion mechanisms are in the form of Rocker-Bogie and wheels. This kind of locomotion mechanism has weak advantage in subsidence or obstacle terrains. In the paper, a kind ...
-
Chapter and Conference Paper
Delay-Constrained Minimum Shortest Path Trees and Related Problems
Motivated by applications in communication networks of the diameter-constrained minimum spanning tree problem, we consider the delay-constrained minimum shortest path tree (DcMSPT) problem. Specifically, given...
-
Chapter and Conference Paper
The Impact of Digital Currency on Foreign Exchange Management and Countermeasures
The first application scenario of digital currency by the People’s Bank of China was launched in Suzhou on April 16, 2020. Digital economy is an increasingly important driving force of global economic growth. ...
-
Chapter and Conference Paper
Dense Attention-Guided Network for Boundary-Aware Salient Object Detection
Recently, salient object detection methods have achieved significant performance with the development of deep supervised learning. However, most existing methods just simply combine low-level and high-level fe...
