News

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

My name is Mozhdeh Rouhsedaghat. I received my bachelor’s degree from EE department of Sharif University of Technology. I am currently a Ph.D. student at the Media Communications Lab (MCL) at USC and supervised by professor C. -C. Jay Kuo. My research interests include image processing, computer vision, and deep learning.

2. What is your impression about MCL and USC?

USC is a top university and has a beautiful architecture. I really enjoy fresh air in the mornings and walking through amazing buildings on the campus. MCL has a friendly environment and a dynamic atmosphere. Its members are kind and talented and support each other. Professor Kuo is very wise, kind, and caring, and working in this atmosphere is pleasurable for me.

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

I am going to improve my research skills in computer vision and I hope I can reach great achievements during my studies.

Congratulations to Haiqiang Wang for passing his PhD defense on August 21, 2018. His PhD thesis is entitled “A Data-Driven Approach to Compressed Video Quality Assessment Using Just Noticeable Difference”.

Abstract of thesis:
The problem of human-centric compressed video quality assessment (VQA) is studied in the research. In this thesis, he propose a new methodology for compressed video quality measurement and assessment based on the just-noticeable-difference (JND) notion. The process of building a large-scale coded H.264/AVC video quality dataset is described. Then, he measure the JND-based video quality using the satisfied user ratio (SUR) curve and designing an SUR prediction method with video quality degradation feature and masking feature. The method consists of the following steps: 1) partition a video clip into local spatial-temporal segments and evaluate the quality of each segment using the VMAF quality index, 2) aggregate these local VMAF measures to derive a global index, 3) significant segments are selected based on the slope of quality scores between neighboring coded clips, and 4) incorporate the masking effect that reflects the unique characteristics of each video clip. Then use the support vector regression (SVR) to minimize the distance of the SUR curves, and derive the JND point accordingly. At last, propose a JND-based VQA model that takes subject variabilities and content variabilities into account. He build a user model by utilizing user’s capability to discern the quality difference. He study the SUR difference as it varies with user profile as well as content with variable level of difficulty. The proposed model aggregates quality ratings per user group to address inter-group difference.
We are so glad to have him share his PhD experience with us. Here is his sharing.
I would like to thank Professor Kuo for [...]

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

Hello, my name is Zhiyu Yao. I am a third-year student from Tsinghua University. I like playing tennis, table tennis, and soccer. My research interest is deep learning and computer vision, especially in video recognition and transfer learning. I think lots of open questions are worth studying in the field of computer vision.

2. What is your impression about MCL and USC?

USC is one of the top universities in the world. I am very glad to study as an intern in MCL. MCL is a warm family and everyone here is very kind and warmhearted. I am very lucky to do research with Prof. Kuo participating in deep learning group, and I am impressed by the strong passion for research from MCL members. Everyone here is self-motivated and is willing to help each other not only in research but also in daily life.

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

In this summer, I am working with Prof. Kuo and his PhD student Yueru in the study of face detection. Hopefully I can solve the monkey face detection problem well the help of them. I believe doing research in MCL can help me grow up quickly in computer vision.

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

I am Hong-Shuo Chen, and my English name is Max. I am a senior undergraduate student studying Electrical Engineering and Computer Science at National Chiao Tung University in Taiwan. I like coding, math and everything about engineering. It gives me great pleasure to come to MCL as a summer intern. My research interests are image segmentation and texture analysis. The world of the computer vision is very broad that I want to explore more in this field.

2. What is your impression about MCL and USC?

MCL is really a cooperative and warm lab which makes me the feel at home. I really enjoy the period of time staying in MCL and like this place. Every time I have problems, MCL members are always willing to help, which makes me feel very warm. Doing research here is really an enchanting experience that I would never forget. People in MCL are all very warm and nice. I want to especially thank Prof. Kuo and my mentor Kaitai Zhang. With their help, I could do research smoothly and learn a lot of knowledge.

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

In this summer, with the guidance of Prof. Kuo and Kaitai, I hope I can finish a decent project and learn a lot in image segmentation and texture analysis. In the future, I also want to study in the United States and broaden my horizons. I hope I can become a good engineer, and contribute myself to this society.

We are happy to welcome a MCL summer intern – JiGyun Kim! Here is an interview with JiGyun:

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

My name is JiGyun Kim, I am a rising junior undergraduate from Korea Aerospace University. I major in Electronics and Avionics. Although I am pretty new in Deep Learning, I am interested in it, and its wide application attracts me very much. I am also interested in semiconductor design, as I had some design experience about it, like making digital clock and Mips CPU with Verilog HDL and making video game and karaoke machine with De1-SoC board. Moreover, I want to do some study in autonomous vehicles, what is why I am constructing a autonomous RC car navigated by image processing in my Bachelor’s degree capstone design.

2. What is your impression about MCL and USC?

The first thing I was impressed when I came to USC is its beautiful campus, and also various people diversity. I think summer internship is a great chance for me to have a different perspective to the world.

MCL in USC is a really large research group, full of professional people. I believe I can a lot here, thanks to Prof. Kuo’s and other lab colleagues’ kindness and help. Additionally, One of the exciting things about MCL is the weekly seminar, which is a great communication platform with people from variant backgrounds.

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

I want to complete projects by Deep Learning in MCL. My current summer study proposal is on the real-time recognition on car license plate number using YOLO v3. I plan to study the structure of Neural Networks, and then implement YOLO v3 by TensorFlow.