yiyuezhang

  • Permalink Gallery

    Congratulations to MCL Alumni for Joining Facebook, Google, Apple, and Bloomberg

Congratulations to MCL Alumni for Joining Facebook, Google, Apple, and Bloomberg

We would like to say congratulations to five of MCL Alumni–Chen Chen, Shangwen Li, Hao Xu, Jian Li, and Xiaqing Pan–for passing their PhD defenses and starting their career lives in such great companies of the U.S.. This year, we will have Chen and Shangwen joining Facebook, Hao joining Google, Jian joining Apple, and Xiaqing joining Bloomberg. We are so glad to have them to share their experience and advises for us.

Chen Chen:
I joined MCL 6 years ago as a master student. In the first seminar talk, Prof. Kuo’s sharing totally changed my view of being a researcher. It is the moment that I made the hard decision to become a PhD student. As expected, joining MCL creates unexpected benefits to my life. The precious platform provides many opportunities for me to learn and to grow. It allows me to meet many excellent students and scholars. Working with them is like visualizing myself in a mirror, which teaches me to know myself before growing. MCL also creates huge challenges to push me to the extreme. Every exam, project due and paper submission are companied with thousands of hours of rigorous and humble team work. “Aim high and act low” is the most impressive lesson I learned from the hard process.
It is the precious experience in MCL that offers the Facebook position at the end of my PhD. However, different from what I learned in MCL, I expect to gain more working experience and entrepreneurship in Facebook. I would also like to see more students from our lab can join Facebook to strengthen the MCL alumina team in the future.

Shangwen Li:
During my past internship at Facebook, I worked on a [...]

By |February 5th, 2017|News|Comments Off on Congratulations to MCL Alumni for Joining Facebook, Google, Apple, and Bloomberg|

Welcome New MCL Member Yuewei Na

We are so happy to welcome a new graduate member of MCL, Yuewei Na, in Fall 2016. Let’s give him a warm welcome. Here is a short interview with him.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

Before coming to USC, I graduated from Xiamen University majoring computer science. I researched machine learning and low-level vision at Xiamen University. I also have experience in building fraud detection system for e-commerce company using Spark.

2. What’s your first impression of USC and MCL?

USC is very similar to Xiamen University, both of which are beautiful and good places to study. MCL is like a big warming family. I was deeply impressed by Prof. Kuo’s understanding on various topics in research.

3. What’s your future expectation for MCL?

Hope MCL can continuously produce ideas that are influential to the research community or even the whole society in the future. I’m glad to contribute my effort to this goal.

 

By |November 27th, 2016|News|Comments Off on Welcome New MCL Member Yuewei Na|

A Large-Scale Subjective Video Quality Database

The MCL joined a collaborative project to build a large-scale subjective video quality database. The database was proposed to boost a major breakthrough in video coding and processing. On one hand, revolutionary ideas rather than fine-tuning patches are highly expected to accommodate increasing video traffic. On the other hand, PSNR has been the dominant distortion metric for many years, but it has also been criticized for not correlating well with perceptual quality. With this database, perceptual coding is promising to lead to numerous R&D opportunities and revolutionary research with machine learning tools.

The database consists of 200 raw sequences with a duration of 5 seconds, encoded by H.264/AVC with fixed QP as bit rate control method. They are available in 5 resolutions from 3840×2160 to 540×360. Around 1000 students participated in the subjective test and it took around 7000 hours to get sufficient samples about 3 JND points. The database will be freely available for downloading for scientific purposes.

The projected was supported by 4 major multimedia companies, Netflix, Huawei, MediaTek, and Samsung. Meanwhile, 6 universities at Shenzhen joined the project, Shenzhen Institutes of Advanced Technology (Chinese Academy of Science), Shenzhen University, Graduate School at Shenzhen (Tsinghua University), Peking University Shenzhen Graduate School, The Chinese University of Hong Kong (Shenzhen), City University of Hong Kong.

We would like to give special thanks to the participating companies, institutes and universities.

By |November 20th, 2016|News|Comments Off on A Large-Scale Subjective Video Quality Database|

Welcome New MCL Visiting Professor Xin Zhou

We are so glad to welcome a new visiting Professor, Xin Zhou, in fall 2016. Here is an interview with Professor Zhou about her pervious academic experience and her future expectations at MCL.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)
My name is Xin ZHOU. I come from China and work in Northwestern Polytechnical University (NPU) as a teacher. I received all of my Bachelor degree, Master degree and PH.D degree in NPU and studied as a visiting student in Nagoya University, Japan from 2009 to 2010. My research is mainly about the multimedia processing, especially video compression.

2. What’s your first impression of USC and MCL?
USC is a wonderful university. The UPC is so beautiful and the people are very warm-hearted. Prof. Kuo is a respectable and kind supervisor. Everyone in MCL is very friendly and knowledgeable. I would like to work with them and learn more from them.

3. What’s your future expectation for MCL?
I would like to do research about Video Quality Assessment and try my best to keep pace with other members in this project.

By |November 13th, 2016|News|Comments Off on Welcome New MCL Visiting Professor Xin Zhou|

MCL Research on Understanding CNN Behavior

Convolutional neural networks (CNNs) have received a lot of attention in recent years due to their superior performance in computer vision benchmarking datasets. Yet, little theory has been developed to explain the underlying principle of CNNs.

Professor C.-C. Jay Kuo, Director of the Media Communication Lab, has recently published important theoretical results about two CNN fundamental properties. They are: 1) why a non-linear activation function is essential at the filter output of every intermediate layer? and 2) what is the advantage of the two-layer cascade system over the one-layer system? To answer these two questions, he developed a mathematical model called the “REctified-COrrelations on a Sphere” (RECOS).

Professor Kuo said, “CNNs need to store the knowledge learned from a large amount training data somewhere. The only places to store the knowledge are the converged filter weights. They must play a critical role in CNN understanding.” Professor Kuo coined a new term “anchor vectors” for the converged filter weights since they serve as a set of vectors for an arbitrary input vector to project onto at one layer. The projected values are the response from the previous layer while their rectified values serve as the input to the next layer. In his paper entitled with “Understanding Convolutional Neural Networks with A Mathematical Model”, Professor Kuo used the anchor vector concept to explain the necessity of nonlinear activation, analyze the behavior of a two-layer RECOS system, and compare it with its one-layer counterpart. He used the LeNet-5 applied to the MNIST dataset as an illustration example throughout the paper.

Professor Kuo emphasized that the new “anchor vector” viewpoint will lead to more interesting research in the near future. His paper has recently been accepted for publication [...]

By |November 6th, 2016|News|Comments Off on MCL Research on Understanding CNN Behavior|

Welcome New MCL Visiting Post-Doctor Bing Li

We are so glad to welcome a new visiting Post-Doctor, Bing Li, in fall 2016. Here is an interview with Doctor Bing about her pervious academic experience and her future expectations at MCL.
 
1.Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

My name is Bing Li. I received my PH.D degree from Chinese academy of Sciences in 2016. My research interests include image/video processing, visual search and machine learning.
 
2.What’s your first impression of USC and MCL?

USC is a beautiful university.  People in MCL are so friendly and help me a lot. MCL also provide good academic environment to conduct research.
 
3.What’s your future expectation for MCL?

Prof. Kuo is well-respected and does an excellent job in his research field. He provides valuable research experience. I hope I will learn a lot from Prof Kuo and do good research at MCL

By |October 30th, 2016|News|Comments Off on Welcome New MCL Visiting Post-Doctor Bing Li|

Welcome New MCL Member Jacob Dormuth

We are so happy to welcome a new undergraduate member of MCL, Jacob Dormuth. Here is an interview with Jacob:

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

This is my first year doing research and am not sure which expertise I would like to pursue.

2. What is your impression about MCL and USC?

My experience so far at USC has been terrific, especially at the MCL. I love getting the chance to see all of the high caliber projects that members of the MCL are pursuing. I also like talking and interacting with the other members because I get the chance to experience other cultures.

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

My goal for the MCL in the future is to find a area of research to pursue. I would also like to get involved with the entrepreneurship aspects that the MCL offers.

By |October 23rd, 2016|News|Comments Off on Welcome New MCL Member Jacob Dormuth|

Welcome New MCL Member Andrew Szot

We are so happy to welcome a new undergraduate member of MCL, Andrew Szot. Here is an interview with Andrew:
 
1. Could you briefly introduce yourself and your research interests?

My name is Andrew Szot, I am a freshman undergraduate here at USC pursuing a Computer Science BS degree. I have been exploring my passion for computer science for some time now. I have created several projects with a highlight being a math solving program to help high school students that shows steps to math problems ranging from basic algebra to advanced calculus. I have a passion for full stack software solutions and love using Laravel and Vue.js on projects. I have also developed an interest in machine learning topics and particularly find convolutional neural networks to be immensely interesting. I hope to research the underlying models of convolutional neural networks in an attempt to better understand them in practical applications.
 
2. What is your impression about MCL and USC?

Based off of my first weeks here I love the environment at USC. So far I have met a great group of motivated and passionate individuals all offering unique perspectives. Being at USC truly does mean being a part of a great network. I see this same type of attitude at the MCL group. The MCL is a community of passionate and very intelligent indivduals. I cannot wait to get to know them all.
 
3. What is your future expectation and plan in MCL?

My future expectation of the MCL is to learn a lot about convolutional neural networks and applications of machine learning in image processing. I also hope to make lasting connections with individuals in the lab.

By |October 9th, 2016|News|Comments Off on Welcome New MCL Member Andrew Szot|

Welcome New MCL Member Anubhuti Mittal

We are so glad to welcome a new MCL member, Anubhuti Mittal. Here is an interview with Anubhuti.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)
 
I am presently pursuing Master’s in Electrical Engineering at USC. I have done my Bachelor’s in Electrical Engineering at Indian Institute of Technology, Jodhpur, India. I have research interests in Computer Vision and Image Processing. Previously, I have worked on a project on ‘Statistical Analysis of Moving Tongue Contours using Ultrasound Video Sequences’ as a research intern in ETS, Montreal. In this project I quantitatively estimated the variability in tongue shapes of various speech sounds. I also worked on similar projects in my undergraduate.

 

2. What’s your first impression of USC and MCL?
 
I was introduced to MCL during the Friday seminar with the inspirational words of Prof. Kuo. It was quite motivating to know the culture of the lab and the fact that it is not just about learning but also sharing that learning with everyone. I was glad to meet the members of the lab, who were so friendly!

 

3. What’s your future expectation for MCL?
 
Since one month working in the lab, I feel I have already learnt so many new things in Computer Vision and am still learning many more. I believe, working in MCL would not only teach me Computer Vision but also improve my communication skills which are as much important in industry as research experience.

By |September 25th, 2016|News|Comments Off on Welcome New MCL Member Anubhuti Mittal|

Welcome New MCL Member Ruiyuan Lin

We are so glad to welcome Ruiyuan Lin to join our group as a Ph.D. student, starting from Fall 2016 . Here is an interview with Ruiyuan.
 

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)
 
 I received my BEng degree in Information Engineering from City University of Hong Kong in July 2016. My previous project experiences are mainly in the field of image processing and computer vision. I also have strong interest in seismic signal processing.

 

2. What’s your first impression of USC and MCL?
 
 People in MCL are all very nice and helpful. I have received a lot of help from them since I joined the group. Also, MCL members are all very enthusiastic about their research and work really hard.

 

3. What’s your future expectation for MCL?
 
 I wish to make good friends with other members. And I hope to learn a lot of new stuff and get involved in cool research.

By |September 18th, 2016|News|Comments Off on Welcome New MCL Member Ruiyuan Lin|