Jie Jing

PhD Candidate in Computer Vision

1998.12
Chengdu, China
jingcjie@outlook.com
+1 9032513381
Resume
LinkedIn
GitHub

Summary

PhD candidate specializing in computer vision and deep learning for medical imaging applications. Demonstrated expertise in developing novel denoising algorithms, contrastive learning frameworks, and continual learning systems. Published papers with strong focus on practical applications in medical image processing and computational vision.

Research Experience

Visiting PhD Student

September 2023 - April 2025

A*STAR & Nanyang Technological University · Singapore

  • Conducted advanced research in contrastive learning and continual learning dynamics.
  • Developed novel algorithms for image memorability analysis in computer vision tasks.
  • Authored multiple peer-reviewed publications on generalization and forgetting mechanisms.
  • Collaborated with international research teams on cutting-edge deep learning projects.

Graduate Research Assistant

2020 - Present

Sichuan University · Chengdu, China

  • Pioneered unsupervised medical image denoising techniques using contrastive learning.
  • Developed motion correction algorithms for MRI imaging using compressed sensing.
  • Led research on low-dose CT denoising without high-quality reference data.
  • Achieved oral presentation recognition at MICCAI 2023 (top 12% of submissions).

Publications

Lead Author Publications

Co-Author Publications

Generalizable MRI Motion Correction via Compressed Sensing Equivariant Imaging Prior

Z Wang, M Ran, Z Yang, H Yu, J Jing, T Wang, J Lu, Y Zhang

IEEE Transactions on Circuits and Systems for Video Technology, 2024

Projects

Research Projects

Human Psychologically Study (Onsite and Online)

Developed human study program with memorability test using MTurk and psiTurk. Conducted studies with over 2000 participants and analyzed SQLite database using Python for data insights.

Technologies:
PythonpsiTurkMTurkSQLiteData AnalysisHuman-Computer Interaction
Low Dose CT Recovery System

Developed neural networks using PyTorch for unsupervised and semi-supervised CT image recovery. Utilized MATLAB for sinogram processing to enhance low-dose CT image quality.

Technologies:
PyTorchMATLABDeep LearningMedical ImagingUnsupervised LearningSemi-supervised Learning
Continual Learning Analysis

Research on the interplay between generalization and forgetting in continual learning systems. Published in IEEE TNNLS with novel insights into memory dynamics.

Technologies:
PythonContinual LearningNeural NetworksStatistical Analysis

Personal Projects

CloudOTP

A versatile Open-Source One-Time Password (OTP) authenticator application built with Dart, supporting multiple platforms including Windows, Linux, Web, Android, iOS, and macOS. Reached 508 registered users by August 2025.

Technologies:
FlutterDartCross-platform DevelopmentAuthenticationMobile Development
WiFi Direct Cable

An application for seamless data, message, and file transfer using Wi-Fi Direct. Features pure peer-to-peer connection without internet or routers. Android version uses Flutter and Kotlin, Windows version uses WinUI3 with C# WinRT.

Technologies:
FlutterKotlinWinUI3C#WinRTWi-Fi DirectP2P Communication
Personal portrait

Education

PhD, Software Engineering

Sichuan University

2022 - Expected 2026

Master, Software Engineering

Sichuan University

2020 - 2022

Bachelor, Software Engineering

Sichuan University

2016 - 2020

Technical Skills

Programming & Frameworks

PythonPyTorchTensorFlowMATLABC++CUDA

Computer Vision & AI

Deep Learning ArchitectureContrastive LearningContinual LearningMedical Image ProcessingNeural Network Optimization

Research Methodologies

Large-scale Data AnalysisAlgorithm DevelopmentStatistical AnalysisScientific Writing

Medical Imaging

CT/MRI ProcessingImage DenoisingMotion CorrectionLow-dose Imaging

Professional Skills

Research Leadership

Led multiple collaborative research projects with international teams.

Technical Communication

Presented research findings at top-tier conferences and workshops.

Mentoring

Guided junior researchers and students in deep learning methodologies.

Cross-functional Collaboration

Worked effectively with medical professionals and engineers.