News

In October 2014, MCLab has a new visiting scholar, Dr. Zhengning Wang. Dr. Wang is Associate Professor at School of Electronic Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China. We are glad to have an interview with him, talking about his previous research experiences and future expectation at USC.

Could you please give an introduction about yourself and your previous research?

I received my Ph.D degree from Southwest Jiaotong University, Chengdu, China in 2007. In 2008, I joined University of Electronic Science and Technology of China and there I worked with about five graduate students. From 2009 to 2011, I worked as a post-doctoral fellow in the second research institute of Civil Aviation Administration of China (CAAC), where I served as a project leader on remote control tower. My research focus is image/video processing, especially video coding, multimedia communication and image enhancement. I also have research experiences in ground surveillance and guidance in air traffic control, video codec design, target tracking for security, light field data compression and high performance computing based on GPU.

What is your impression about MCLab and USC?

MCLab has a good atmosphere and I was impressed by the hardworking of the group members. They are also quite friendly and warm-hearted. I received lots of help from Xiaqing, Jian and other group members. USC is a well-known university for her top-notch academic achievements. Researchers here collaborate with each other and exchange their ideas actively, making a perfect opportunity to gain academic communication experiences.

What is your expectation and plan in the following academic year?

I hope to work closely with Prof. Kuo to facilitate our research projects. Besides research, I plan to learn about course organization and teaching from USC. I wish [...]

Scene understanding has been a hot topic in computer vision research fields for quite a long time. As a sub-branch of scene understanding, indoor/outdoor scene classification has become increasingly challenging throughout the years as visual data becomes larger and more diverse. As existing approaches are not scalable to large-scale visual data (usually 100,000 images at least), it is extremely important to have an accurate and robust system to handle big visual data for robust indoor/outdoor classification applications.
Mr. Chen Chen and Ms. Yuzhuo Ren, two MCL PhD students, and Professor C.-C. Jay Kuo recently proposed a new framework to tackle the large-scale indoor/outdoor image classification problem via an expert decision fusion system. The proposed solution has been tested on a large-scale and the most challenging scene understanding dataset from the SUN database, and a correct classification rate of 91.2% has been achieved, which is the state-of-the-art technique in the field. This work has been accepted for publication in the 1st Scene Understanding for Autonomous Systems Workshop (SUAS 2014) held in conjunction with ACCV 2014, Singapore, November 2, 2014.

Xue Wang, a recently graduated Ph.D. student from Media Communications Lab at USC, decides to continue her research work as a postdoctoral associate here with us. She is so happy to study with Professor Kuo and other lab members. Now we have an interview with her, talking about the change of roles between a Ph.D. student and a post-doc researcher and lifelong study plan.

Could you briefly describe yourself and your current research?

My research is an extension of the previous work on the objective evaluation of cataract surgical techniques using image processing and computer vision methods. The state-of-art surgeon evaluation tools primarily require human observers to fill out a grading questionnaire after viewing a video of the procedure, a technique that is subject to observer bias and variability. Therefore, it is hoped that our work could be extremely helpful in developing reliable computational analysis methods that can precisely and automatically identify quantitative and qualitative evaluation for surgical techniques.

Why do you choose to take a post-doc position and what’s your future plan?

I set up my career goal to become a faculty in the university when I started my Ph.D. at USC. I enjoy doing research and communicating with fellow workmates, and working as a post-doc is necessary step in the preparation for becoming faculty. To make this decision, I talked with different professors about the ongoing research work and future plan. Also, I got great help from Jing Zhang, one of our MCLab alumni, who is now pursuing her post-doc at Yale University. I’d apply for faculty position in future and I need to improve myself more. One aspect is about the research; I will enhance my work and try to seize any off-campus presentation opportunity [...]

In 2014 Fall semester, Junting Zhang becomes a new master student in MCLab. She received the B.S. degree in Communication Engineering from Xiamen University in 2014. Now we have an interview with her, talking about her background and her thoughts on USC and MCLab.

What were your first impression of USC and MCLab?

USC is famous for its culture diversity and top-notch academic achievements, and it is almost my dream school. I came from Xiamen University, which is also located in a coastal city, so I cannot help comparing these two universities. They both have charming campus landscapes and rich resources, but USC is more idyllic. I found adorable squirrels running through the crowd. During the welcome week, everybody kept saying the slogan “Fight on, Trojans! “, which really cheered me up. I am looking forward to starting a brand new journey here.

As for MCL, Professor Kuo and senior students are really nice and warm-hearted. They make MCL like a home for me. They also helped me a lot to adapt to the new environment, especially Yuzhuo and Xiaqing. I feel lucky to join this group. I have chatted with several group members.  Everyone is self-motivated and experienced in research. I am sure that I will gain tons of hands-on experience and make great friends here.

Could you briefly describe your previous research experience?

When I was an undergraduate student, I majored in communications. I took part in the National Innovation Training Program, working on haze removal for blurred images and surveillance videos. My undergraduate thesis is about LDPC codes decoding algorithm design and analysis over a partial response channel, which is the model of magnetic recording system.

What is your future expectation in MCLab?

My background matches MCL perfectly. [...]

In 2014 Fall semester, Wei-Chih Hung will become a new Ph.D. student in MCLab. He received his B.S. and M.S. degree, both in electrical engineering, from the National Taiwan University, Taipei, Taiwan in 2011 and 2013, respectively. He arrived at USC one week ago, and now we have an interview with him, talking about his background and his thoughts on USC and MCLab.

What were your first impression of USC and MCLab?
USC definitely has a wonderful campus view. The buildings are beautiful and consistent in style. There are trees and grass yards everywhere, and of course I notice the famous fountains in the campus. After the first look on the USC campus, I am so excited that I can pursue my degree in this wonderful place.
As for MCLab, my first impression is that it is really like a big family. People in here are really friendly and willing to help as well as share their own experience, either in academy and living. I have received lots of help since I decided to join MCLab, especially from Professor Kuo, Brian and Joe.

Could you briefly describe your previous research experience?
In the last 2 years of my B.S. program, I was interested in various areas, such as wireless communication, machine learning, video coding, and computer graphics. Since my M.S. program, my research topic mainly focuses on wireless video transmission. I have worked on two projects on wireless video transmission. Both of them tried to adaptively improve video quality over wireless channel with different channel quality. But one tries to improve video quality with video codec parameter selection, and the other proposed a cross-layer video decoding algorithm, exploiting the natural information redundancy with video sequence.

What is [...]