News

We are so happy to welcome a new MCL member, Laurence Palmer joining MCL this semester. Here is a quick interview with Laurence:

1. Could you briefly introduce yourself and your research interests?

My name is Laurence Palmer. I’m a current Master’s student studying Computer Science at USC. Prior to USC, I worked as an analyst to detect fraud, waste, and abuse in government programs. Before then, I obtained degrees in Applied Mathematics, Economics, and Operations Research from UC Santa Barbara and UC Berkeley respectively. Some of my research interests include computer vision. Outside of academics, I enjoy all things outdoors and sports like skiing or basketball. 

2. What is your impression about MCL and USC?

USC is a beautiful campus, and I really appreciate the warm weather, especially coming from San Francisco. As for MCL, it has been a great experience to learn from some of the brightest people I have been around. I’ve especially enjoyed hearing about other MCL member’s research projects, and it’s exciting to be a part of such a wonderful community. I am also grateful for the support that Professor Kuo is willing to provide to all his students given how busy he is.

3. What is your future expectation and plan in MCL?

I will be working on dehazing using green learning techniques for this upcoming year. I am hoping to prove the feasibility of green learning techniques for the dehazing task and present my work to others in the MCL/computer vision community.

We are so happy to welcome a new MCL member, Alexander Jou joining MCL this semester. Here is a quick interview with Alexander:

1. Could you briefly introduce yourself and your research interests?

My name is Alexander Jou and I am a first year Master’s Student at USC studying Electrical Engineering. Before attending USC, I received my undergraduate degree from the University of California at Berkeley with a double major in Statistics and Economics. I am interested in Artificial Intelligence and using it to develop tools to improve people’s quality of life. Outside of school I enjoy golfing, surfing, and playing soccer. 

2. What is your impression about MCL and USC?

I am very glad to be a part of the passionate community that MCL fosters. In each of our weekly seminars, you can see the strong desire of both Professor Kuo and the students to continually develop new breakthroughs. Professor Kuo speaks not only with incredible understanding, but also an innate belief that we are doing meaningful work that can impact the field. This creates a very hard-working and enjoyable environment which breeds a lot of success.

3. What is your future expectation and plan in MCL?

I am currently working on a paper to apply Green Learning to detect cardiovascular diseases through analysis of heart sounds. My goal is to conduct a thorough review of green learning’s applicability to this challenge and write a paper on my findings. I also plan on collaborating with peers in the lab to develop other useful tools using Artificial Intelligence that can help people’s lives. 

We are so happy to welcome a new MCL member, Youngrae Kim joining MCL this semester. Here is a quick interview with Youngrae: 1. Could you briefly introduce yourself and your research interests?

My name is Youngrae Kim, and I am a first-year PhD student in Computer Engineering at USC. Before starting my PhD, I completed my undergraduate studies at Hongik University and earned my master’s degree at the Korea Advanced Institute of Science and Technology (KAIST). My research interests lie in computer vision, machine learning, and green learning. Outside of academics, I enjoy hiking, working out, and traveling.

What is your impression of MCL and USC?

For me, MCL is an impressive research institute where there’s a strong sense of trust, not only in academic collaborations but also on a personal level. The community is welcoming, and I’ve felt a great sense of support from everyone here. I’m excited to be advised by Professor Kuo, one of the leading researchers in computer vision. The atmosphere at USC is also fantastic—people seem genuinely happy, enjoying life while working hard. I’m very glad to have joined USC, particularly MCL.

What are your future expectations and plans in MCL?

During my PhD, I plan to focus on Federated Learning for the medical domain. I expect to encounter various challenges in applying this technology to real-world scenarios, and I aim to address these through my research, ultimately proposing a comprehensive thesis that has practical applications. I also look forward to collaborating with peers in different areas, which I believe will broaden my academic perspective.

Congratulations to Zhanxuan Mei for passing his defense. Zhanxuan’s thesis is titled “Explainable and Lightweight Techniques for Blind Visual Quality Assessment and Saliency Detection.” His Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Ulrich Neumann (Outside Member). The Committee members praised the quality of Zhanxuan’s work very much. The MCL News team invited Zhanxuan for a short talk on his thesis and PhD experience. Here is the summary. We thank Zhanxuan for his kind sharing and wish him all the best on his next journey. A high-level abstract of Zhanxuan’s thesis is given below:

Thesis:

Explainable and Lightweight Techniques for Blind Visual Quality Assessment and Saliency Detection

The thesis contains four main research topics:

We begin by presenting our proposed GreenBIQA method, a novel approach to BIQA characterized by its compact model size, low computational complexity, and high performance. Building on the foundation of GreenBIQA, we extend its application to BVQA through the development of GreenBVQA. To further enhance the performance of GreenBIQA, we introduce a lightweight and efficient image saliency detection method, termed GreenSaliency. Ultimately, we integrate GreenSaliency with GreenBIQA, culminating in the development of the Green Saliency-guided BIQA method (GSBIQA).

PhD Experience Sharing:

The PhD journey at MCL has been an unforgettable experience. Over the course of this long and challenging path, I navigated through the unprecedented COVID era, multiple rounds of rigorous exams, and a diverse range of responsibilities, including teaching assistantships and intensive research projects. Each challenge presented an opportunity to grow, expand my perspectives, and enhance my skill set. I have honed my communication skills, developed the ability to tackle real-world problems through collaborative projects, and cultivated teamwork skills by engaging in discussions and joint efforts with exceptionally talented peers. These valuable experiences and abilities [...]

Objective image quality assessment (IQA) plays a crucial role in various multimedia applications and is generally categorized into three distinct types: Full-Reference IQA (FR-IQA), Reduced-Reference IQA (RR-IQA), and No-Reference IQA (NR-IQA). FR-IQA involves a direct comparison between a distorted image and its original reference image to evaluate quality. RR-IQA, in contrast, relies on partial information from reference images to assess the quality of the target images. NR-IQA, also known as blind image quality assessment (BIQA), is indispensable in situations where reference images are unavailable, such as at the receiver’s end or for user-generated content on social media platforms. The increasing prevalence of such platforms has driven a significant rise in the demand for BIQA. BIQA is critical for estimating the perceptual quality of images without reference, making it particularly relevant in the context of user-generated content and mobile applications, where reference images are typically not accessible.

The challenge of BIQA lies in its need to handle a wide variety of content and the presence of multiple types of distortions. Although many BIQA methods leverage deep neural networks (DNNs) and incorporate saliency detectors to improve performance, their large model sizes pose significant limitations for deployment on resource-constrained devices.

To overcome these challenges, we propose a novel non-deep-learning BIQA method, termed Green Saliency-guided Blind Image Quality Assessment (GSBIQA). GSBIQA is distinguished by its compact model size, low computational requirements, and strong performance. The method integrates a lightweight saliency detection module that aids in data cropping and decision ensemble processes, generating features that effectively mimic the human attention mechanism. The GSBIQA framework is composed of five key processes: 1) green saliency detection, 2) saliency-guided data cropping, 3) GreenBIQA feature extraction, 4) local patch prediction, and 5) saliency-guided decision ensemble. [...]