Skip to main navigation
Skip to search
Skip to main content
Hong Kong Baptist University Home
Help & FAQ
Home
Scholars
Departments / Units
Research Output
Projects / Grants
Prizes / Awards
Activities
Press/Media
Student theses
Datasets
Search by expertise, name or affiliation
View Scopus Profile
Jun QI, Dr
Research Assistant Professor
,
Department of Computer Science
https://orcid.org/0000-0001-7533-2630
Email
jun-qi
hkbu.edu
hk
Accepting PhD Students
2023
2025
Research activity per year
Overview
Fingerprint
Network
Projects / Grants
(1)
Research Output
(8)
Fingerprint
Dive into the research topics where Jun QI is active. Topic labels come from the works of this scholar. Together they form a unique fingerprint.
Sort by:
Weight
Alphabetically
Keyphrases
Variational Quantum Circuits
100%
Tensor-train Deep Neural Network
90%
Quantum Neural Network
71%
Circuit-based
54%
Learning Approaches
51%
Quantum Tensor Network
51%
Voice Command Recognition
48%
Error Performance Analysis
45%
Spectrum Transformation
45%
Modified Discrete Cosine Transform
45%
Multicarrier Transmission
45%
Projection Learning
45%
Natural Gradient Descent
45%
Clipping Distortion
45%
Peak-to-average Power Ratio (PAPR)
45%
Riemannian Gradient Descent
45%
Theoretical Error
45%
Multiple Kernel Learning
45%
Low-resource
45%
Neural Network
45%
Spectral Transformation
45%
Functional Regression
45%
Learning Framework
45%
Multiple Kernels
45%
Low-rank Tensor
45%
Transferability
45%
Speech Processing
45%
Speaker Recognition System
45%
Learning-based
45%
Quantum Federated Learning
45%
White-box
45%
Hybrid Quantum-classical Neural Networks
45%
Privacy Algorithm
45%
Time-frequency Domain
30%
Speaker Recognition
30%
Surrogate Model
30%
Comparison Method
30%
Class Activation Map
30%
Black Box
30%
Attacker
30%
Tensor Train
29%
Low-resource Speech
22%
Output Embeddings
22%
Lithuanian
22%
Chuvash
22%
Neural Network Kernel
22%
Acoustic Modeling
22%
Representation Error
22%
Kernel-based Classifier
22%
Single Quantum System
22%
Computer Science
Quantum Circuit
98%
Gradient Descent
90%
Deep Neural Network
90%
Neural Network
70%
Learning Framework
60%
Tensor Network
54%
Learning Approach
51%
Spectral Efficiency
45%
Gaussian Kernel
45%
Discrete Cosine Transform
45%
Recurrent Neural Network
45%
Multiple Kernel Learning
45%
Speaker Recognition
45%
Speech Processing
45%
Federated Learning
45%
Recognition System
45%
Performance Analysis
45%
Privacy Algorithm
45%
Quantum Machine Learning
45%
Frequency Domain
30%
Feature Map
30%
Attackers
30%
Quantum Device
27%
Power Amplifier
22%
multipath fading channel
22%
Division Multiplexing
22%
Neural Network Architecture
22%
Performance Loss
22%
handwritten digit
19%
Convolutional Neural Network
19%
Voice Input
15%
Successful Attack
15%
Communication Overhead
15%
Interpretability
15%
Adversarial Machine Learning
15%
Black-Box Attack
15%
Optimization Algorithm
15%
Comparison Result
15%
Salient Region
15%
Imperceptibility
15%
Qubit
15%
Quantum Extension
7%
Fast Convergence
7%
Gradient Descent Method
7%
Convergence Rate
7%
Horizontal Structure
6%
Vertical Structure
6%
Graphics Processing Unit
6%
Neural Network Model
6%
Dimensionality Reduction
5%
Engineering
Quantum Circuit
90%
Deep Neural Network
90%
Learning System
51%
Error Performance
45%
Multicarrier Transmission
45%
Peak-to-Average Power Ratio
45%
Performance Analysis
45%
Recognition Accuracy
45%
Conducted Experiment
22%
Front End
22%
Posterior Probability
22%
Gradient Descent
22%
Feature Model
22%
Qubit
22%
Spectral Efficiency
11%
Performance Loss
11%
High Spectral Efficiency
11%
Division Multiplexing
11%
Frequency Chirp
11%
Peak Power
11%
Dimensionality
11%
Nonlinear Distortion
11%
Neural Network Architecture
11%
Power Amplifier
11%
Input Power
11%
Fading Channel
11%
Learning Task
5%
