Computer Vision, Graphics, Image Processing, Multimedia Computing and Pattern Recognition

Faculty working in this area

Faculty Email website
Patrick H. Chen Chen's Group
Kenneth Chiu Chiu's Group
Weiying Dai Dai's Group
Adnan Siraj Rakin Rakin's Group
Lijun Yin Graphics and Image Computing Laboratory
Zhongfei (Mark) Zhang Multimedia Research Lab

Highlights in this area

Patrick H. Chen focuses on the fundamental, uncertainty and efficiency aspects of machine learning. To make models reliably applicable, his research group studies the fundamental aspects of ML, such as factualness and robustness, and analyzes uncertainty issues in various applications, such as continual learning. To make models more efficient for practical usage, his research focuses on compressing machine learning models to make them deployable on devices with limited memory, and accelerating the training and inference time of machine learning models to meet latency requirements.  

Weiying Dai researches medical imaging, healthcare bioinformatics, biomedical image processing, functional magnetic resonance imaging (fMRI), machine learning and pattern recognition. She co-directs the Center for Advanced Magnetic Resonance Imaging Sciences (CAMRIS). She is working on the aging-related brain patterns, imaging biomarkers for schizophrenia and diabetes, formation of brain folding patterns, automatic sleep stage learning, and LLM and deep learning on fMRI image registration and image reconstruction.  

Adnan Siraj Rakin focuses on unsupervised machine learning. His research group is dealing with three important research questions: 

  • How to improve the performance of deep learning model with limited data in a collaborative environment? The investigation also looks into the challenges of domain shift and domain generalization of data.
  • What are the security challenges in such a collaborative un-supervised training scheme? His group is investigating potential defensive solutions as well. 
  • How to incorporate a wide range of hardware fault injection techniques from CPU, GPU and FPGA to evaluate ML security and privacy threats?  

Lijun Yin researches affective computing, human emotion analysis, biometrics and human computer interaction. He leads the Graphics and Image Computing (GAIC) Laboratory. He is working on the automatic detection of emotion and behavior status using multimodal approaches for health-care in collaborating with a medical practitioner.  

Zhongfei (Mark) Zhang  researches machine learning and artificial intelligence, data mining and knowledge discovery, multimedia indexing and retrieval, computer vision and image understanding, and pattern recognition. Accordingly, he is currently working on several projects in these areas including LLM compression, multimodal data learning, out of domain learning, learning with noise and novelty learning.