Jie Cai

Jie Cai

Senior Staff Research Scientist | AI & Multi-Modal Expert

About Me

I am a Senior Staff Research Scientist at OPPO US AI Center, specializing in Computer Vision and Vision-Language Models. My expertise spans across Visual Enhancement (including Super-Resolution, Reflection Removal, and Deblurring) and Visual Understanding. I have a strong track record of building cutting-edge and efficient AI models for real-world applications.

Education

Ph.D. in Computer Science and Engineering

University of South Carolina

Aug. 2015 - Dec. 2019 | Columbia, SC, US | Advisor: Prof. Yan Tong

M.S. in Electrical and Computer Engineering

University of Illinois at Chicago

Aug. 2013 - May 2015 | Chicago, IL, US

B.S. in Mathematics and Statistics

Northeastern University

Sept. 2010 - June 2014 | China

Work Experience

OPPO US AI Center

Senior Staff Research Scientist

Sept. 2019 - Present

12 Sigma Technologies

Summer Research Intern

May 2019 - Aug. 2019

  • Implemented Mask R-CNN for medical image segmentation (CT & MRI)
  • Achieved top ranking in CHAOS challenge for abdominal organ segmentation

University of South Carolina

Research Assistant

Aug. 2015 - Aug. 2019

  • Developed facial expression analysis techniques using CNN, GAN & LSTM
  • Proposed novel loss functions (Probabilistic Attribute Tree-CNN, Island Loss) for FER

Technical Skills

Multi-Modal Models

Qwen2.5-VL

AI Models

Diffusion Model, CodeFormer, RealESRGAN, NAFNet, LaMa, PaddleOCR, YOLO, YOSO

Computer Vision

Image Enhancement, Super-Resolution, Reflection Removal, Facial Expression Analysis

Development

Model Quantization, Model Deployment, Pipeline Implementation

Contact Me

Feel free to reach out for research collaborations or professional inquiries!